Skip to content

2
2026_Article_RESILINK_ML
Commit f2ad8555 by Joaquín Irazábal González
Options

Update bibliography and manuscript files with new references and corrections

- Added five new references related to the development and optimization of steel shear panel dampers in the bibliography. - Updated the manuscript to reflect changes in section labels and improved formatting for tables and figures. - Corrected multiple defined labels in the manuscript to ensure proper referencing. - Adjusted LaTeX settings and resolved warnings related to font sizes and unused options. - Updated the PDF and auxiliary files to reflect the latest changes in the manuscript.
parent 692674ab
Showing with 479 additions and 288 deletions
Code/reports/hysteretic_curves/2W/H30_B29/case_12_with_rnn_preds.csv
This source diff could not be displayed because it is too large. You can view the blob instead.
Code/reports/hysteretic_curves/2W/H30_B34/case_12_with_rnn_preds.csv
This source diff could not be displayed because it is too large. You can view the blob instead.
Code/src/hysteretic_curves/predict_hysteretic_curves.py
......@@ -27,22 +27,27 @@ Stability fix:
from __future__ import annotations
import argparse
from typing import Dict, Tuple, List, Optional, cast
import gc
import os
import joblib
from typing import Dict, List, Optional, Tuple, cast
import joblib
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import KFold
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
try:
import optuna
except ImportError:
optuna = None # type: ignore
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from torch.utils.data import DataLoader, Dataset
try:
from numpy.lib.stride_tricks import sliding_window_view
_HAS_SWV = True
except Exception:
_HAS_SWV = False
......@@ -81,10 +86,7 @@ def _make_grad_scaler(use_amp: bool):
def make_windows_for_case_fast(
df_case: pd.DataFrame,
feature_cols: List[str],
target_col: str,
window_size: int
df_case: pd.DataFrame, feature_cols: List[str], target_col: str, window_size: int
) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
"""
Vectorized sliding windows.
......@@ -111,18 +113,20 @@ def make_windows_for_case_fast(
else:
# fallback
xw = np.stack(
[x[i - window_size + 1:i + 1] for i in range(window_size - 1, n)],
axis=0).astype(np.float32)
[x[i - window_size + 1 : i + 1] for i in range(window_size - 1, n)], axis=0
).astype(np.float32)
yw = y[window_size - 1:]
iw = idx[window_size - 1:]
yw = y[window_size - 1 :]
iw = idx[window_size - 1 :]
return xw.astype(np.float32, copy=False), yw.astype(np.float32, copy=False), iw
# -------------------------
# Window cache per window_size
# -------------------------
CaseWindows = Dict[int, Tuple[np.ndarray, np.ndarray, np.ndarray]] # case -> (x, y, idx)
CaseWindows = Dict[
int, Tuple[np.ndarray, np.ndarray, np.ndarray]
] # case -> (x, y, idx)
WINDOW_CACHE: Dict[int, CaseWindows] = {} # window_size -> cache
......@@ -136,7 +140,9 @@ def precompute_windows_for_cases(
cache: CaseWindows = {}
for c in cases:
dfc = df[df["Case"] == c]
xw, yw, iw = make_windows_for_case_fast(dfc, feature_cols, target_col, window_size)
xw, yw, iw = make_windows_for_case_fast(
dfc, feature_cols, target_col, window_size
)
cache[int(c)] = (xw, yw, iw)
return cache
......@@ -146,7 +152,7 @@ def get_cache_for_window_size(
cases_to_cache: List[int],
feature_cols: List[str],
target_col: str,
window_size: int
window_size: int,
) -> CaseWindows:
if window_size not in WINDOW_CACHE:
WINDOW_CACHE[window_size] = precompute_windows_for_cases(
......@@ -154,14 +160,13 @@ def get_cache_for_window_size(
cases=cases_to_cache,
feature_cols=feature_cols,
target_col=target_col,
window_size=window_size
window_size=window_size,
)
return WINDOW_CACHE[window_size]
def build_from_cache(
cache_ws: CaseWindows,
cases: List[int]
cache_ws: CaseWindows, cases: List[int]
) -> Tuple[Optional[np.ndarray], Optional[np.ndarray]]:
xs, ys = [], []
for c in cases:
......@@ -194,14 +199,16 @@ class WindowDataset(Dataset):
# Model
# -------------------------
class LSTMRegressor(nn.Module):
def __init__(self, input_dim, hidden_dim=64, dense_dim=32, num_layers=1, dropout=0.0):
def __init__(
self, input_dim, hidden_dim=64, dense_dim=32, num_layers=1, dropout=0.0
):
super().__init__()
self.lstm = nn.LSTM(
input_dim,
hidden_dim,
num_layers=num_layers,
dropout=(dropout if num_layers > 1 else 0.0),
batch_first=True
batch_first=True,
)
self.fc1 = nn.Linear(hidden_dim, dense_dim)
self.fc2 = nn.Linear(dense_dim, 1)
......@@ -256,11 +263,7 @@ def make_case_folds(train_pool: List[int], seed=123, n_splits=5):
# DataLoader: STABLE (no multiprocessing in CV)
# -------------------------
def make_loader(
ds: Dataset,
batch_size: int,
shuffle: bool,
device: str,
use_workers: bool
ds: Dataset, batch_size: int, shuffle: bool, device: str, use_workers: bool
) -> DataLoader:
pin = (device == "cuda") and PIN_MEMORY_ON_CUDA
......@@ -310,37 +313,50 @@ def train_one_fold_cached( # type: ignore
# --- scalers on TRAIN only ---
scaler_x = StandardScaler()
scaler_x.fit(x_train.reshape(-1, feature_dim))
x_train_scaled = scaler_x.transform(
x_train.reshape(-1, feature_dim)).reshape(x_train.shape).astype(np.float32, copy=False)
x_val_scaled = scaler_x.transform(
x_val.reshape(-1, feature_dim)).reshape(x_val.shape).astype(np.float32, copy=False)
x_train_scaled = (
scaler_x.transform(x_train.reshape(-1, feature_dim))
.reshape(x_train.shape)
.astype(np.float32, copy=False)
)
x_val_scaled = (
scaler_x.transform(x_val.reshape(-1, feature_dim))
.reshape(x_val.shape)
.astype(np.float32, copy=False)
)
scaler_y = StandardScaler()
y_train_scaled = scaler_y.fit_transform(
y_train.reshape(-1, 1)).ravel().astype(np.float32, copy=False)
y_train_scaled = (
scaler_y.fit_transform(y_train.reshape(-1, 1))
.ravel()
.astype(np.float32, copy=False)
)
train_ds = WindowDataset(x_train_scaled, y_train_scaled)
val_ds = WindowDataset(x_val_scaled, np.zeros((x_val_scaled.shape[0],), dtype=np.float32))
val_ds = WindowDataset(
x_val_scaled, np.zeros((x_val_scaled.shape[0],), dtype=np.float32)
)
# CV: use_workers=False (avoid too many open files)
train_loader = make_loader(
train_ds, batch_size=batch_size, shuffle=True, device=device, use_workers=False)
train_ds, batch_size=batch_size, shuffle=True, device=device, use_workers=False
)
val_loader = make_loader(
val_ds, batch_size=batch_size, shuffle=False, device=device, use_workers=False)
val_ds, batch_size=batch_size, shuffle=False, device=device, use_workers=False
)
model = LSTMRegressor(
input_dim=feature_dim,
hidden_dim=hidden_dim,
dense_dim=dense_dim,
num_layers=num_layers,
dropout=dropout
dropout=dropout,
).to(device)
model = maybe_compile(model, device=device, enable=compile_model)
optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=weight_decay)
criterion = nn.SmoothL1Loss(beta=huber_beta)
use_amp = (device == "cuda")
use_amp = device == "cuda"
scaler_amp = _make_grad_scaler(use_amp)
best_val_rmse = np.inf
......@@ -396,7 +412,9 @@ def train_one_fold_cached( # type: ignore
preds_scaled.append(pb.detach().float().cpu().numpy())
y_val_pred_scaled = np.concatenate(preds_scaled, axis=0).ravel()
y_val_pred = scaler_y.inverse_transform(y_val_pred_scaled.reshape(-1, 1)).ravel()
y_val_pred = scaler_y.inverse_transform(
y_val_pred_scaled.reshape(-1, 1)
).ravel()
val_rmse = rmse(y_val, y_val_pred)
if val_rmse < best_val_rmse:
......@@ -428,10 +446,11 @@ def cv_score_for_params_cached(
grad_clip,
device,
compile_model: bool,
trial: Optional[object] = None,
):
fold_rmses = []
for _, (train_cases, val_cases) in enumerate(folds, start=1):
for fold_idx, (train_cases, val_cases) in enumerate(folds, start=1):
try:
fold_rmse = train_one_fold_cached(
cache_ws=cache_ws,
......@@ -443,7 +462,7 @@ def cv_score_for_params_cached(
grad_clip=grad_clip,
device=device,
compile_model=compile_model,
**params_model
**params_model,
)
except torch.cuda.OutOfMemoryError:
if torch.cuda.is_available():
......@@ -452,6 +471,11 @@ def cv_score_for_params_cached(
fold_rmses.append(fold_rmse)
if trial is not None and optuna is not None:
trial.report(float(np.mean(fold_rmses)), step=fold_idx)
if trial.should_prune():
raise optuna.TrialPruned()
gc.collect()
if torch.cuda.is_available():
torch.cuda.empty_cache()
......@@ -496,32 +520,39 @@ def train_final_full_trainpool_cached( # type: ignore
scaler_x = StandardScaler()
scaler_x.fit(x_train.reshape(-1, feature_dim))
x_train_scaled = scaler_x.transform(
x_train.reshape(-1, feature_dim)).reshape(x_train.shape).astype(np.float32, copy=False)
x_train_scaled = (
scaler_x.transform(x_train.reshape(-1, feature_dim))
.reshape(x_train.shape)
.astype(np.float32, copy=False)
)
scaler_y = StandardScaler()
y_train_scaled = scaler_y.fit_transform(
y_train.reshape(-1, 1)).ravel().astype(np.float32, copy=False)
y_train_scaled = (
scaler_y.fit_transform(y_train.reshape(-1, 1))
.ravel()
.astype(np.float32, copy=False)
)
train_ds = WindowDataset(x_train_scaled, y_train_scaled)
# Final: still keep workers OFF for stability; you can try True later.
train_loader = make_loader(
train_ds, batch_size=batch_size, shuffle=True, device=device, use_workers=False)
train_ds, batch_size=batch_size, shuffle=True, device=device, use_workers=False
)
model = LSTMRegressor(
input_dim=feature_dim,
hidden_dim=hidden_dim,
dense_dim=dense_dim,
num_layers=num_layers,
dropout=dropout
dropout=dropout,
).to(device)
model = maybe_compile(model, device=device, enable=compile_model)
optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=weight_decay)
criterion = nn.SmoothL1Loss(beta=huber_beta)
use_amp = (device == "cuda")
use_amp = device == "cuda"
scaler_amp = _make_grad_scaler(use_amp)
best_train_loss = np.inf
......@@ -568,7 +599,9 @@ def train_final_full_trainpool_cached( # type: ignore
epoch_loss = running / max(1, n_batches)
if epoch_loss < best_train_loss:
best_train_loss = epoch_loss
raw_state = {k: v.detach().cpu().clone() for k, v in model.state_dict().items()}
raw_state = {
k: v.detach().cpu().clone() for k, v in model.state_dict().items()
}
best_state = strip_compile_prefix(raw_state)
del model, optimizer, criterion, train_loader, train_ds
......@@ -585,16 +618,16 @@ def train_final_full_trainpool_cached( # type: ignore
# -------------------------
# Hyperparameter sampler
# -------------------------
def sample_params(device: str = "cpu"):
window_size = int(np.random.choice([40, 60], p=[0.6, 0.4]))
hidden_dim = int(np.random.choice([32, 64, 128], p=[0.30, 0.45, 0.25]))
dense_dim = int(np.random.choice([16, 32, 64], p=[0.25, 0.50, 0.25]))
num_layers = int(np.random.choice([1, 2], p=[0.55, 0.45]))
dropout = float(np.random.choice([0.0, 0.1, 0.2]))
def suggest_params(trial, device: str = "cpu"):
window_size = int(trial.suggest_categorical("window_size", [10, 20, 30]))
hidden_dim = int(trial.suggest_categorical("hidden_dim", [32, 64, 128]))
dense_dim = int(trial.suggest_categorical("dense_dim", [16, 32, 64]))
num_layers = int(trial.suggest_categorical("num_layers", [1, 2]))
dropout = float(trial.suggest_categorical("dropout", [0.0, 0.1, 0.2]))
lr = float(10 ** np.random.uniform(-4.0, -2.6))
weight_decay = float(10 ** np.random.uniform(-6.0, -3.5))
huber_beta = float(np.random.choice([0.5, 1.0, 2.0]))
lr = float(trial.suggest_float("lr", 1e-4, 10**-2.6, log=True))
weight_decay = float(trial.suggest_float("weight_decay", 1e-6, 10**-3.5, log=True))
huber_beta = float(trial.suggest_categorical("huber_beta", [0.5, 1.0, 2.0]))
cost = window_size * hidden_dim * num_layers
......@@ -604,12 +637,12 @@ def sample_params(device: str = "cpu"):
elif cost >= 60 * 128 * 2 or cost >= 80 * 64 * 2:
batch_size = 32
else:
batch_size = int(np.random.choice([32, 64], p=[0.55, 0.45]))
batch_size = int(trial.suggest_categorical("batch_size", [32, 64]))
if hidden_dim >= 256 and num_layers >= 2 and dense_dim > 64:
dense_dim = 64
else:
batch_size = int(np.random.choice([32, 64, 128]))
batch_size = int(trial.suggest_categorical("batch_size", [32, 64, 128]))
return {
"window_size": window_size,
......@@ -620,7 +653,7 @@ def sample_params(device: str = "cpu"):
"lr": lr,
"weight_decay": weight_decay,
"batch_size": batch_size,
"huber_beta": huber_beta
"huber_beta": huber_beta,
}
......@@ -635,6 +668,7 @@ def main():
parser = argparse.ArgumentParser()
parser.add_argument("--W", type=int, required=True)
parser.add_argument("--B", type=int, required=True)
parser.add_argument("--n-trials", type=int, default=15)
args = parser.parse_args()
w_val = args.W
......@@ -680,7 +714,7 @@ def main():
else:
print("Warning: n_train_case and predict_case not set for W != 2, 3, or 5")
n_trials = 15
n_trials = args.n_trials
max_epachs_tune = 40
patience_tune = 5
max_epachs_final = 200
......@@ -693,15 +727,27 @@ def main():
df = pd.read_csv(data_file)
# Keep only 1 out of every 5 rows within each case.
keep_mask = df.groupby("Case", sort=False).cumcount() % 5 == 0
df = df.loc[keep_mask].reset_index(drop=True)
thickness_cols = [c for c in df.columns if c.startswith("tw")]
feature_cols = ["Displ", "CumDispl", "LoadDir", "CycleNum", "MaxAmpl"] + thickness_cols
feature_cols = [
"Displ",
"CumDispl",
# "LoadDir",
# "CycleNum",
# "MaxAmpl",
] + thickness_cols
target_col = "Force"
all_cases = sorted(df["Case"].unique())
train_pool = [int(c) for c in all_cases if c <= n_train_case]
if int(predict_case) in train_pool:
raise RuntimeError(f"predict_case={predict_case} is in train_pool. This must not happen.")
raise RuntimeError(
f"predict_case={predict_case} is in train_pool. This must not happen."
)
device = "cuda" if torch.cuda.is_available() else "cpu"
......@@ -712,7 +758,10 @@ def main():
print("Train pool cases (for CV):", train_pool)
print("n_cases total:", len(all_cases), "| train_pool:", len(train_pool))
print("torch.compile CV:", "ON" if (device == "cuda" and compile_in_cv) else "OFF")
print("torch.compile FINAL:", "ON" if (device == "cuda" and compile_in_final) else "OFF")
print(
"torch.compile FINAL:",
"ON" if (device == "cuda" and compile_in_final) else "OFF",
)
print("============================================================")
folds, strategy = make_case_folds(train_pool, seed=SEED, n_splits=5)
......@@ -722,10 +771,21 @@ def main():
cases_to_cache_all = sorted(set(train_pool + [int(predict_case)]))
# ---- CV Tuning ----
best = {"mean": np.inf, "std": np.inf, "params": None}
if optuna is None:
raise ImportError(
"Optuna is required for Bayesian CV search. Install it with `pip install optuna`."
)
print(f"Optuna search: TPE sampler | n_trials={n_trials}")
optuna.logging.set_verbosity(optuna.logging.WARNING)
sampler = optuna.samplers.TPESampler(seed=SEED)
pruner = optuna.pruners.MedianPruner(
n_startup_trials=min(5, n_trials), n_warmup_steps=2
)
study = optuna.create_study(direction="minimize", sampler=sampler, pruner=pruner)
for t in range(1, n_trials + 1):
params = sample_params(device=device)
def objective(trial) -> float:
params = suggest_params(trial, device=device)
# Separate window_size from model params (cached funcs must NOT receive window_size)
ws = int(params["window_size"])
......@@ -738,11 +798,9 @@ def main():
cases_to_cache=cases_to_cache_all,
feature_cols=feature_cols,
target_col=target_col,
window_size=ws
window_size=ws,
)
# feature_dim derived from cached windows
# pick a case that has windows; if first has none, find another
feature_dim = None
for c in cases_to_cache_all:
x_c = cache_ws[int(c)][0]
......@@ -750,7 +808,9 @@ def main():
feature_dim = x_c.shape[-1]
break
if feature_dim is None:
raise RuntimeError("All cases have 0 windows for this window_size. Lower window_size.")
raise RuntimeError(
"All cases have 0 windows for this window_size. Lower window_size."
)
mean_rmse, std_rmse, fold_rmses = cv_score_for_params_cached(
cache_ws=cache_ws,
......@@ -762,36 +822,65 @@ def main():
grad_clip=1.0,
device=device,
compile_model=(compile_in_cv and device == "cuda"),
trial=trial,
)
if fold_rmses is None:
print(f"[Trial {t:02d}] OOM -> skipping trial | {params}")
continue
print(f"[Trial {trial.number + 1:02d}] OOM -> pruning trial | {params}")
raise optuna.TrialPruned()
fold_str = ", ".join([f"{v:.3f}" for v in fold_rmses.tolist()])
print(
f"[Trial {t:02d}]"
f" CV mean RMSE={mean_rmse:.4f} | std={std_rmse:.4f} | folds=[{fold_str}]")
f"[Trial {trial.number + 1:02d}]"
f" CV mean RMSE={mean_rmse:.4f} | std={std_rmse:.4f} | folds=[{fold_str}]"
)
print(f" params: {params}")
if (
mean_rmse < best["mean"]) or (
np.isclose(mean_rmse, best["mean"]) and std_rmse < best["std"]):
best.update(mean=mean_rmse, std=std_rmse, params=params)
trial.set_user_attr("std_rmse", float(std_rmse))
trial.set_user_attr("params_full", params)
gc.collect()
if torch.cuda.is_available():
torch.cuda.empty_cache()
return float(mean_rmse)
study.optimize(objective, n_trials=n_trials, show_progress_bar=False)
completed_trials = [
trial
for trial in study.trials
if trial.state == optuna.trial.TrialState.COMPLETE
]
if not completed_trials:
raise RuntimeError(
"No valid Optuna trial found. Try lowering window sizes or check your data."
)
best_trial = min(
completed_trials,
key=lambda trial: (
float(trial.value),
float(trial.user_attrs.get("std_rmse", np.inf)),
),
)
best = {
"mean": float(best_trial.value),
"std": float(best_trial.user_attrs.get("std_rmse", np.inf)),
"params": best_trial.user_attrs.get("params_full"),
}
print("\n====================")
print("BEST (CV TUNING)")
print("BEST (OPTUNA CV TUNING)")
print("CV mean RMSE:", best["mean"])
print("CV std RMSE :", best["std"])
print("params:", best["params"])
print("====================\n")
if best["params"] is None:
raise RuntimeError("No valid trial found. Try lowering window sizes or check your data.")
raise RuntimeError(
"No valid trial found. Try lowering window sizes or check your data."
)
best_params = cast(dict, best["params"])
ws_best = int(best_params["window_size"])
......@@ -804,7 +893,7 @@ def main():
cases_to_cache=cases_to_cache_all,
feature_cols=feature_cols,
target_col=target_col,
window_size=ws_best
window_size=ws_best,
)
# feature_dim again
......@@ -815,7 +904,9 @@ def main():
feature_dim = x_c.shape[-1]
break
if feature_dim is None:
raise RuntimeError("All cases have 0 windows for best window_size. Lower window_size.")
raise RuntimeError(
"All cases have 0 windows for best window_size. Lower window_size."
)
# ---- Final train on 100% train_pool (NO VAL) ----
print("============================================================")
......@@ -832,7 +923,7 @@ def main():
grad_clip=1.0,
device=device,
compile_model=(compile_in_final and device == "cuda"),
**best_params_model
**best_params_model,
)
scaler_x, scaler_y = final_scalers
......@@ -843,7 +934,7 @@ def main():
bundle = {
"framework": "pytorch",
"model_class": "LSTMRegressor",
"state_dict": final_state, # already CPU tensors
"state_dict": final_state, # already CPU tensors
"params": {**best_params_model, "window_size": ws_best},
"feature_cols": feature_cols,
"target_col": target_col,
......@@ -872,15 +963,18 @@ def main():
f"Case {predict_case} has fewer points ({len(df_test)}) than window_size ({ws_best})."
)
x_test_scaled = scaler_x.transform(
x_test.reshape(-1, feature_dim)).reshape(x_test.shape).astype(np.float32, copy=False)
x_test_scaled = (
scaler_x.transform(x_test.reshape(-1, feature_dim))
.reshape(x_test.shape)
.astype(np.float32, copy=False)
)
final_model = LSTMRegressor(
input_dim=feature_dim,
hidden_dim=best_params_model["hidden_dim"],
dense_dim=best_params_model["dense_dim"],
num_layers=best_params_model["num_layers"],
dropout=best_params_model["dropout"]
dropout=best_params_model["dropout"],
).to(device)
final_state = strip_compile_prefix(final_state)
......@@ -890,15 +984,18 @@ def main():
final_model.load_state_dict(final_state)
final_model.eval()
test_ds = WindowDataset(x_test_scaled, np.zeros((x_test_scaled.shape[0],), dtype=np.float32))
test_ds = WindowDataset(
x_test_scaled, np.zeros((x_test_scaled.shape[0],), dtype=np.float32)
)
test_loader = make_loader(
test_ds,
batch_size=best_params_model["batch_size"],
shuffle=False,
device=device,
use_workers=False)
use_workers=False,
)
use_amp = (device == "cuda")
use_amp = device == "cuda"
preds = []
with torch.no_grad():
for xb, _ in test_loader:
......
Code/src/hysteretic_curves/run.sh
#!/bin/bash
python predict_hysteretic_curves.py --W 2 --B 29
python predict_hysteretic_curves.py --W 2 --B 34
python predict_hysteretic_curves.py --W 3 --B 29
python predict_hysteretic_curves.py --W 3 --B 34
python predict_hysteretic_curves.py --W 5 --B 34
# python predict_hysteretic_curves.py --W 2 --B 29 --n-trials 25
python predict_hysteretic_curves.py --W 2 --B 34 --n-trials 25
python predict_hysteretic_curves.py --W 3 --B 29 --n-trials 25
python predict_hysteretic_curves.py --W 3 --B 34 --n-trials 25
python predict_hysteretic_curves.py --W 5 --B 34 --n-trials 25
Manuscript/Manuscript.aux
......@@ -22,20 +22,23 @@
\newlabel{sec1_1}{{1.1}{1}{}{subsection.1.1}{}}
\BKM@entry{id=5,open,dest={73756273656374696F6E2E312E32},srcline={78}}{5C3337365C3337375C3030304D5C303030615C303030695C3030306E5C3030305C3034305C303030635C303030685C303030615C3030306C5C3030306C5C303030655C3030306E5C303030675C303030655C30303073}
\BKM@entry{id=6,open,dest={73756273656374696F6E2E312E33},srcline={84}}{5C3337365C3337375C303030535C303030745C303030615C303030745C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030655C3030305C3034305C303030615C303030725C303030745C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C303030725C303030655C3030306C5C303030615C303030745C303030655C303030645C3030305C3034305C303030775C3030306F5C303030725C3030306B}
\citation{Deng2014a,Deng2015}
\citation{Deng2014,Deng2015a}
\citation{Deng2014b}
\citation{Elgammal2024}
\BKM@entry{id=7,open,dest={73756273656374696F6E2E312E34},srcline={88}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030745C303030725C303030695C303030625C303030755C303030745C303030695C3030306F5C3030306E5C303030735C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030695C303030735C3030305C3034305C303030775C3030306F5C303030725C3030306B}
\citation{Hirt1974}
\BKM@entry{id=8,open,dest={73656374696F6E2E32},srcline={103}}{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}
\BKM@entry{id=7,open,dest={73756273656374696F6E2E312E34},srcline={90}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030745C303030725C303030695C303030625C303030755C303030745C303030695C3030306F5C3030306E5C303030735C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030695C303030735C3030305C3034305C303030775C3030306F5C303030725C3030306B}
\@writefile{toc}{\contentsline {subsection}{\numberline {1.2}Main challenges}{2}{subsection.1.2}\protected@file@percent }
\newlabel{sec1_2}{{1.2}{2}{}{subsection.1.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {1.3}State of the art and related work}{2}{subsection.1.3}\protected@file@percent }
\newlabel{sec1_2}{{1.3}{2}{}{subsection.1.3}{}}
\newlabel{sec1_3}{{1.3}{2}{}{subsection.1.3}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {1.4}Contributions of this work}{2}{subsection.1.4}\protected@file@percent }
\newlabel{sec1_3}{{1.4}{2}{}{subsection.1.4}{}}
\BKM@entry{id=9,open,dest={73756273656374696F6E2E322E31},srcline={107}}{5C3337365C3337375C303030475C303030655C3030306F5C3030306D5C303030655C303030745C303030725C303030795C3030305C3034305C3030306F5C303030665C3030305C3034305C303030535C3030304C5C303030425C3030305C3034305C303030645C303030615C3030306D5C303030705C303030655C303030725C30303073}
\BKM@entry{id=10,open,dest={73756273656374696F6E2E322E32},srcline={113}}{5C3337365C3337375C303030435C303030795C303030635C3030306C5C303030695C303030635C3030305C3034305C3030306C5C3030306F5C303030615C303030645C303030695C3030306E5C303030675C3030305C3034305C303030705C303030725C3030306F5C303030745C3030306F5C303030635C3030306F5C3030306C5C30303073}
\BKM@entry{id=11,open,dest={73756273656374696F6E2E322E33},srcline={119}}{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}
\BKM@entry{id=12,open,dest={73756273656374696F6E2E322E34},srcline={125}}{5C3337365C3337375C303030445C303030655C303030735C303030695C303030675C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030655C3030305C3034305C303030735C303030695C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030645C303030615C303030745C303030615C303030735C303030655C30303074}
\newlabel{sec1_4}{{1.4}{2}{}{subsection.1.4}{}}
\citation{Hirt1974}
\BKM@entry{id=8,open,dest={73656374696F6E2E32},srcline={105}}{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}
\BKM@entry{id=9,open,dest={73756273656374696F6E2E322E31},srcline={109}}{5C3337365C3337375C303030475C303030655C3030306F5C3030306D5C303030655C303030745C303030725C303030795C3030305C3034305C3030306F5C303030665C3030305C3034305C303030535C3030304C5C303030425C3030305C3034305C303030645C303030615C3030306D5C303030705C303030655C303030725C30303073}
\BKM@entry{id=10,open,dest={73756273656374696F6E2E322E32},srcline={115}}{5C3337365C3337375C303030435C303030795C303030635C3030306C5C303030695C303030635C3030305C3034305C3030306C5C3030306F5C303030615C303030645C303030695C3030306E5C303030675C3030305C3034305C303030705C303030725C3030306F5C303030745C3030306F5C303030635C3030306F5C3030306C5C30303073}
\BKM@entry{id=11,open,dest={73756273656374696F6E2E322E33},srcline={121}}{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}
\BKM@entry{id=12,open,dest={73756273656374696F6E2E322E34},srcline={127}}{5C3337365C3337375C303030445C303030655C303030735C303030695C303030675C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030655C3030305C3034305C303030735C303030695C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030645C303030615C303030745C303030615C303030735C303030655C30303074}
\@writefile{toc}{\contentsline {section}{\numberline {2}Numerical simulation and ground truth generation}{3}{section.2}\protected@file@percent }
\newlabel{sec2}{{2}{3}{}{section.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Geometry of SLB dampers}{3}{subsection.2.1}\protected@file@percent }
......@@ -44,51 +47,50 @@
\newlabel{sec2_2}{{2.2}{3}{}{subsection.2.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Finite element outputs and quantities of interest}{3}{subsection.2.3}\protected@file@percent }
\newlabel{sec2_3}{{2.3}{3}{}{subsection.2.3}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Design of the simulation dataset}{3}{subsection.2.4}\protected@file@percent }
\newlabel{sec2_4}{{2.4}{3}{}{subsection.2.4}{}}
\BKM@entry{id=13,open,dest={73656374696F6E2E33},srcline={148}}{5C3337365C3337375C303030485C303030795C303030735C303030745C303030655C303030725C303030655C303030735C303030695C303030735C3030305C3034305C303030705C303030725C303030655C303030645C303030695C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030755C303030735C303030695C3030306E5C303030675C3030305C3034305C3030304C5C303030535C303030545C3030304D5C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\BKM@entry{id=14,open,dest={73756273656374696F6E2E332E31},srcline={152}}{5C3337365C3337375C303030505C303030725C3030306F5C303030625C3030306C5C303030655C3030306D5C3030305C3034305C303030665C3030306F5C303030725C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030775C303030695C303030745C303030685C3030305C3034305C3030306D5C303030655C3030306D5C3030306F5C303030725C303030795C3030305C3034305C303030655C303030665C303030665C303030655C303030635C303030745C30303073}
\BKM@entry{id=13,open,dest={73656374696F6E2E33},srcline={150}}{5C3337365C3337375C303030485C303030795C303030735C303030745C303030655C303030725C303030655C303030735C303030695C303030735C3030305C3034305C303030705C303030725C303030655C303030645C303030695C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030755C303030735C303030695C3030306E5C303030675C3030305C3034305C3030304C5C303030535C303030545C3030304D5C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\BKM@entry{id=14,open,dest={73756273656374696F6E2E332E31},srcline={154}}{5C3337365C3337375C303030505C303030725C3030306F5C303030625C3030306C5C303030655C3030306D5C3030305C3034305C303030665C3030306F5C303030725C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030775C303030695C303030745C303030685C3030305C3034305C3030306D5C303030655C3030306D5C3030306F5C303030725C303030795C3030305C3034305C303030655C303030665C303030665C303030655C303030635C303030745C30303073}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces This is the sample figure caption.}}{4}{figure.caption.1}\protected@file@percent }
\providecommand*\caption@xref[2]{\@setref\relax\@undefined{#1}}
\newlabel{fig1}{{1}{4}{This is the sample figure caption}{figure.caption.1}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces This is the sample figure caption.}}{4}{figure.caption.2}\protected@file@percent }
\newlabel{fig2}{{2}{4}{This is the sample figure caption}{figure.caption.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Design of the simulation dataset}{4}{subsection.2.4}\protected@file@percent }
\newlabel{sec2_4}{{2.4}{4}{}{subsection.2.4}{}}
\@writefile{toc}{\contentsline {section}{\numberline {3}Hysteresis prediction using LSTM models}{4}{section.3}\protected@file@percent }
\newlabel{sec3}{{3}{4}{}{section.3}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Problem formulation with memory effects}{4}{subsection.3.1}\protected@file@percent }
\newlabel{sec3_1}{{3.1}{4}{}{subsection.3.1}{}}
\BKM@entry{id=15,open,dest={73756273656374696F6E2E332E32},srcline={160}}{5C3337365C3337375C303030535C303030655C303030715C303030755C303030655C3030306E5C303030745C303030695C303030615C3030306C5C3030305C3034305C303030725C303030655C303030705C303030725C303030655C303030735C303030655C3030306E5C303030745C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030655C3030305C3034305C303030695C3030306E5C303030705C303030755C303030745C3030305C3034305C303030735C303030695C303030675C3030306E5C303030615C3030306C}
\BKM@entry{id=16,open,dest={73756273656374696F6E2E332E33},srcline={166}}{5C3337365C3337375C3030304C5C303030535C303030545C3030304D5C3030305C3034305C303030615C303030725C303030635C303030685C303030695C303030745C303030655C303030635C303030745C303030755C303030725C303030655C303030735C3030305C3034305C303030635C3030306F5C3030306E5C303030735C303030695C303030645C303030655C303030725C303030655C30303064}
\BKM@entry{id=17,open,dest={73756273656374696F6E2E332E34},srcline={174}}{5C3337365C3337375C303030545C303030725C303030615C303030695C3030306E5C303030695C3030306E5C303030675C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030735C303030745C303030725C303030615C303030745C303030655C303030675C30303079}
\BKM@entry{id=18,open,dest={73756273656374696F6E2E332E35},srcline={180}}{5C3337365C3337375C303030415C303030645C303030765C303030615C3030306E5C303030745C303030615C303030675C303030655C303030735C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C3030306C5C303030695C3030306D5C303030695C303030745C303030615C303030745C303030695C3030306F5C3030306E5C30303073}
\citation{Burton2013,Berndt2011,Kucharik2012}
\citation{Breil2015}
\citation{Barth1997}
\BKM@entry{id=15,open,dest={73756273656374696F6E2E332E32},srcline={162}}{5C3337365C3337375C303030535C303030655C303030715C303030755C303030655C3030306E5C303030745C303030695C303030615C3030306C5C3030305C3034305C303030725C303030655C303030705C303030725C303030655C303030735C303030655C3030306E5C303030745C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C303030745C303030685C303030655C3030305C3034305C303030695C3030306E5C303030705C303030755C303030745C3030305C3034305C303030735C303030695C303030675C3030306E5C303030615C3030306C}
\BKM@entry{id=16,open,dest={73756273656374696F6E2E332E33},srcline={168}}{5C3337365C3337375C3030304C5C303030535C303030545C3030304D5C3030305C3034305C303030615C303030725C303030635C303030685C303030695C303030745C303030655C303030635C303030745C303030755C303030725C303030655C303030735C3030305C3034305C303030635C3030306F5C3030306E5C303030735C303030695C303030645C303030655C303030725C303030655C30303064}
\BKM@entry{id=17,open,dest={73756273656374696F6E2E332E34},srcline={176}}{5C3337365C3337375C303030545C303030725C303030615C303030695C3030306E5C303030695C3030306E5C303030675C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030735C303030745C303030725C303030615C303030745C303030655C303030675C30303079}
\BKM@entry{id=18,open,dest={73756273656374696F6E2E332E35},srcline={182}}{5C3337365C3337375C303030415C303030645C303030765C303030615C3030306E5C303030745C303030615C303030675C303030655C303030735C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C3030306C5C303030695C3030306D5C303030695C303030745C303030615C303030745C303030695C3030306F5C3030306E5C30303073}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Problem formulation with memory effects}{5}{subsection.3.1}\protected@file@percent }
\newlabel{sec3_1}{{3.1}{5}{}{subsection.3.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Sequential representation of the input signal}{5}{subsection.3.2}\protected@file@percent }
\newlabel{sec3_2}{{3.2}{5}{}{subsection.3.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}LSTM architectures considered}{5}{subsection.3.3}\protected@file@percent }
\newlabel{sec3_3}{{3.3}{5}{}{subsection.3.3}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.4}Training and validation strategy}{5}{subsection.3.4}\protected@file@percent }
\newlabel{sec3_4}{{3.4}{5}{}{subsection.3.4}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.5}Advantages and limitations}{5}{subsection.3.5}\protected@file@percent }
\newlabel{sec3_5}{{3.5}{5}{}{subsection.3.5}{}}
\BKM@entry{id=19,open,dest={73656374696F6E2E34},srcline={190}}{5C3337365C3337375C303030475C303030655C3030306F5C3030306D5C303030655C303030745C303030725C303030695C303030635C3030305C3034305C3030306F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030755C303030735C303030695C3030306E5C303030675C3030305C3034305C303030735C303030755C303030725C303030725C3030306F5C303030675C303030615C303030745C303030655C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\BKM@entry{id=20,open,dest={73756273656374696F6E2E342E31},srcline={194}}{5C3337365C3337375C303030505C303030725C3030306F5C303030625C3030306C5C303030655C3030306D5C3030305C3034305C303030665C3030306F5C303030725C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=21,open,dest={73756273656374696F6E2E342E32},srcline={203}}{5C3337365C3337375C303030535C303030755C303030725C303030725C3030306F5C303030675C303030615C303030745C303030655C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\BKM@entry{id=22,open,dest={73756273656374696F6E2E342E33},srcline={211}}{5C3337365C3337375C3030304F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030615C3030306C5C303030675C3030306F5C303030725C303030695C303030745C303030685C3030306D}
\citation{Burton2013,Berndt2011,Kucharik2012}
\citation{Breil2015}
\citation{Barth1997}
\BKM@entry{id=19,open,dest={73656374696F6E2E34},srcline={192}}{5C3337365C3337375C303030475C303030655C3030306F5C3030306D5C303030655C303030745C303030725C303030695C303030635C3030305C3034305C3030306F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030755C303030735C303030695C3030306E5C303030675C3030305C3034305C303030735C303030755C303030725C303030725C3030306F5C303030675C303030615C303030745C303030655C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\BKM@entry{id=20,open,dest={73756273656374696F6E2E342E31},srcline={196}}{5C3337365C3337375C303030505C303030725C3030306F5C303030625C3030306C5C303030655C3030306D5C3030305C3034305C303030665C3030306F5C303030725C3030306D5C303030755C3030306C5C303030615C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=21,open,dest={73756273656374696F6E2E342E32},srcline={205}}{5C3337365C3337375C303030535C303030755C303030725C303030725C3030306F5C303030675C303030615C303030745C303030655C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C30303073}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.5}Advantages and limitations}{6}{subsection.3.5}\protected@file@percent }
\newlabel{sec3_5}{{3.5}{6}{}{subsection.3.5}{}}
\@writefile{toc}{\contentsline {section}{\numberline {4}Geometric optimization using surrogate models}{6}{section.4}\protected@file@percent }
\newlabel{sec4}{{4}{6}{}{section.4}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Problem formulation}{6}{subsection.4.1}\protected@file@percent }
\newlabel{sec4_1}{{4.1}{6}{}{subsection.4.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Surrogate models}{6}{subsection.4.2}\protected@file@percent }
\newlabel{sec4_2}{{4.2}{6}{}{subsection.4.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.3}Optimization algorithm}{6}{subsection.4.3}\protected@file@percent }
\newlabel{sec4_3}{{4.3}{6}{}{subsection.4.3}{}}
\BKM@entry{id=23,open,dest={73656374696F6E2E35},srcline={217}}{5C3337365C3337375C3030304E5C303030755C3030306D5C303030655C303030725C303030695C303030635C303030615C3030306C5C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C303030615C303030645C303030615C303030705C303030745C303030695C303030765C303030655C3030305C3034305C303030665C303030655C303030655C303030645C303030625C303030615C303030635C3030306B}
\BKM@entry{id=24,open,dest={73756273656374696F6E2E352E31},srcline={221}}{5C3337365C3337375C303030465C303030455C3030304D5C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C3030306F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030655C303030645C3030305C3034305C303030645C303030655C303030735C303030695C303030675C3030306E5C30303073}
\BKM@entry{id=25,open,dest={73756273656374696F6E2E352E32},srcline={229}}{5C3337365C3337375C303030415C303030645C303030615C303030705C303030745C303030695C303030765C303030655C3030305C3034305C303030725C303030655C303030745C303030725C303030615C303030695C3030306E5C303030695C3030306E5C303030675C3030305C3034305C303030735C303030745C303030725C303030615C303030745C303030655C303030675C30303079}
\BKM@entry{id=26,open,dest={73656374696F6E2E36},srcline={236}}{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}
\BKM@entry{id=27,open,dest={73756273656374696F6E2E362E31},srcline={240}}{5C3337365C3337375C303030505C303030725C303030655C303030645C303030695C303030635C303030745C303030695C303030765C303030655C3030305C3034305C303030615C303030635C303030635C303030755C303030725C303030615C303030635C30303079}
\BKM@entry{id=22,open,dest={73756273656374696F6E2E342E33},srcline={213}}{5C3337365C3337375C3030304F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030615C3030306C5C303030675C3030306F5C303030725C303030695C303030745C303030685C3030306D}
\BKM@entry{id=23,open,dest={73656374696F6E2E35},srcline={219}}{5C3337365C3337375C3030304E5C303030755C3030306D5C303030655C303030725C303030695C303030635C303030615C3030306C5C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C303030615C303030645C303030615C303030705C303030745C303030695C303030765C303030655C3030305C3034305C303030665C303030655C303030655C303030645C303030625C303030615C303030635C3030306B}
\BKM@entry{id=24,open,dest={73756273656374696F6E2E352E31},srcline={223}}{5C3337365C3337375C303030465C303030455C3030304D5C3030305C3034305C303030765C303030615C3030306C5C303030695C303030645C303030615C303030745C303030695C3030306F5C3030306E5C3030305C3034305C3030306F5C303030665C3030305C3034305C3030306F5C303030705C303030745C303030695C3030306D5C303030695C3030307A5C303030655C303030645C3030305C3034305C303030645C303030655C303030735C303030695C303030675C3030306E5C30303073}
\BKM@entry{id=25,open,dest={73756273656374696F6E2E352E32},srcline={231}}{5C3337365C3337375C303030415C303030645C303030615C303030705C303030745C303030695C303030765C303030655C3030305C3034305C303030725C303030655C303030745C303030725C303030615C303030695C3030306E5C303030695C3030306E5C303030675C3030305C3034305C303030735C303030745C303030725C303030615C303030745C303030655C303030675C30303079}
\BKM@entry{id=26,open,dest={73656374696F6E2E36},srcline={238}}{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}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.3}Optimization algorithm}{7}{subsection.4.3}\protected@file@percent }
\newlabel{sec4_3}{{4.3}{7}{}{subsection.4.3}{}}
\@writefile{toc}{\contentsline {section}{\numberline {5}Numerical validation and adaptive feedback}{7}{section.5}\protected@file@percent }
\newlabel{sec5}{{5}{7}{}{section.5}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}FEM validation of optimized designs}{7}{subsection.5.1}\protected@file@percent }
......@@ -97,38 +99,39 @@
\newlabel{sec5_2}{{5.2}{7}{}{subsection.5.2}{}}
\@writefile{toc}{\contentsline {section}{\numberline {6}Comparative assessment of supervised surrogate models and RBF approaches}{7}{section.6}\protected@file@percent }
\newlabel{sec6}{{6}{7}{}{section.6}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.1}Predictive accuracy}{7}{subsection.6.1}\protected@file@percent }
\newlabel{sec6_1}{{6.1}{7}{}{subsection.6.1}{}}
\BKM@entry{id=28,open,dest={73756273656374696F6E2E362E32},srcline={246}}{5C3337365C3337375C303030435C3030306F5C3030306D5C303030705C303030755C303030745C303030615C303030745C303030695C3030306F5C3030306E5C303030615C3030306C5C3030305C3034305C303030635C3030306F5C303030735C30303074}
\BKM@entry{id=29,open,dest={73756273656374696F6E2E362E33},srcline={252}}{5C3337365C3337375C303030505C303030725C303030615C303030635C303030745C303030695C303030635C303030615C3030306C5C3030305C3034305C303030695C3030306D5C303030705C3030306C5C303030695C303030635C303030615C303030745C303030695C3030306F5C3030306E5C303030735C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C3030305C3034305C303030735C303030655C3030306C5C303030655C303030635C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=30,open,dest={73656374696F6E2E37},srcline={259}}{5C3337365C3337375C303030445C303030695C303030735C303030635C303030755C303030735C303030735C303030695C3030306F5C3030306E}
\BKM@entry{id=27,open,dest={73756273656374696F6E2E362E31},srcline={242}}{5C3337365C3337375C303030505C303030725C303030655C303030645C303030695C303030635C303030745C303030695C303030765C303030655C3030305C3034305C303030615C303030635C303030635C303030755C303030725C303030615C303030635C30303079}
\BKM@entry{id=28,open,dest={73756273656374696F6E2E362E32},srcline={248}}{5C3337365C3337375C303030435C3030306F5C3030306D5C303030705C303030755C303030745C303030615C303030745C303030695C3030306F5C3030306E5C303030615C3030306C5C3030305C3034305C303030635C3030306F5C303030735C30303074}
\BKM@entry{id=29,open,dest={73756273656374696F6E2E362E33},srcline={254}}{5C3337365C3337375C303030505C303030725C303030615C303030635C303030745C303030695C303030635C303030615C3030306C5C3030305C3034305C303030695C3030306D5C303030705C3030306C5C303030695C303030635C303030615C303030745C303030695C3030306F5C3030306E5C303030735C3030305C3034305C303030615C3030306E5C303030645C3030305C3034305C3030306D5C3030306F5C303030645C303030655C3030306C5C3030305C3034305C303030735C303030655C3030306C5C303030655C303030635C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=30,open,dest={73656374696F6E2E37},srcline={261}}{5C3337365C3337375C303030445C303030695C303030735C303030635C303030755C303030735C303030735C303030695C3030306F5C3030306E}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.1}Predictive accuracy}{8}{subsection.6.1}\protected@file@percent }
\newlabel{sec6_1}{{6.1}{8}{}{subsection.6.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.2}Computational cost}{8}{subsection.6.2}\protected@file@percent }
\newlabel{sec6_2}{{6.2}{8}{}{subsection.6.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.3}Practical implications and model selection}{8}{subsection.6.3}\protected@file@percent }
\newlabel{sec6_3}{{6.3}{8}{}{subsection.6.3}{}}
\@writefile{toc}{\contentsline {section}{\numberline {7}Discussion}{8}{section.7}\protected@file@percent }
\newlabel{sec7}{{7}{8}{}{section.7}{}}
\BKM@entry{id=31,open,dest={73656374696F6E2E38},srcline={272}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030635C3030306C5C303030755C303030735C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=31,open,dest={73656374696F6E2E38},srcline={274}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030635C3030306C5C303030755C303030735C303030695C3030306F5C3030306E5C30303073}
\@writefile{toc}{\contentsline {section}{\numberline {8}Conclusions}{9}{section.8}\protected@file@percent }
\newlabel{sec8}{{8}{9}{}{section.8}{}}
\@writefile{toc}{\contentsline {paragraph}{\numberline {\rm 8.0.0.1}Fourth level head}{9}{paragraph.8.0.0.1}\protected@file@percent }
\citation{Liska2010,Kucharik2003,Blanchard2015}
\citation{Lauritzen2011}
\citation{Klima2017}
\citation{Dukowicz2000}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces This is sample table caption.}}{11}{table.caption.3}\protected@file@percent }
\newlabel{tab1}{{1}{11}{This is sample table caption}{table.caption.3}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces This is sample table caption.}}{11}{table.caption.4}\protected@file@percent }
\newlabel{tab2}{{2}{11}{This is sample table caption}{table.caption.4}{}}
\citation{Klima2017}
\citation{Dukowicz2000}
\citation{Kucharik2011,Kucharik2014,Loubere2005}
\citation{Caramana1998}
\citation{Hoch2009}
\citation{Shashkov1996,Knupp1999,Knupp1999}
\citation{Kamm2000}
\citation{Taylor1937}
\BKM@entry{id=32,open,dest={73656374696F6E2E39},srcline={482}}{5C3337365C3337375C303030455C303030785C303030615C3030306D5C303030705C3030306C5C303030655C303030735C3030305C3034305C303030665C3030306F5C303030725C3030305C3034305C303030655C3030306E5C303030755C3030306E5C303030635C303030695C303030615C303030745C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=32,open,dest={73656374696F6E2E39},srcline={484}}{5C3337365C3337375C303030455C303030785C303030615C3030306D5C303030705C3030306C5C303030655C303030735C3030305C3034305C303030665C3030306F5C303030725C3030305C3034305C303030655C3030306E5C303030755C3030306E5C303030635C303030695C303030615C303030745C303030695C3030306F5C3030306E5C30303073}
\@writefile{toc}{\contentsline {section}{\numberline {9}Examples for enunciations}{13}{section.9}\protected@file@percent }
\newlabel{sec4}{{9}{13}{}{section.9}{}}
\newlabel{sec15}{{9}{13}{}{section.9}{}}
\newlabel{thm1}{{1}{13}{}{theorem.1}{}}
\citation{Kucharik2012}
\citation{Hirt1974}
......@@ -145,57 +148,62 @@
\@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces \hskip .5em\relax Pseudocode for our algorithm}}{17}{algorithm.1}\protected@file@percent }
\newlabel{alg1}{{1}{17}{\enskip Pseudocode for our algorithm}{algorithm.1}{}}
\newlabel{eq23}{{1}{17}{}{equation.9.1}{}}
\BKM@entry{id=33,open,dest={73656374696F6E2E3130},srcline={702}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030635C3030306C5C303030755C303030735C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=34,open,dest={73656374696F6E2E3130},srcline={721}}{5C3337365C3337375C303030415C303030755C303030745C303030685C3030306F5C303030725C3030305C3034305C303030635C3030306F5C3030306E5C303030745C303030725C303030695C303030625C303030755C303030745C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=35,open,dest={73656374696F6E2E3130},srcline={725}}{5C3337365C3337375C303030415C303030635C3030306B5C3030306E5C3030306F5C303030775C3030306C5C303030655C303030645C303030675C3030306D5C303030655C3030306E5C303030745C30303073}
\BKM@entry{id=33,open,dest={73656374696F6E2E3130},srcline={704}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030635C3030306C5C303030755C303030735C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=34,open,dest={73656374696F6E2E3130},srcline={723}}{5C3337365C3337375C303030415C303030755C303030745C303030685C3030306F5C303030725C3030305C3034305C303030635C3030306F5C3030306E5C303030745C303030725C303030695C303030625C303030755C303030745C303030695C3030306F5C3030306E5C30303073}
\BKM@entry{id=35,open,dest={73656374696F6E2E3130},srcline={727}}{5C3337365C3337375C303030415C303030635C3030306B5C3030306E5C3030306F5C303030775C3030306C5C303030655C303030645C303030675C3030306D5C303030655C3030306E5C303030745C30303073}
\citation{Kenamond2013}
\BKM@entry{id=36,open,dest={73656374696F6E2E3130},srcline={729}}{5C3337365C3337375C303030465C303030695C3030306E5C303030615C3030306E5C303030635C303030695C303030615C3030306C5C3030305C3034305C303030645C303030695C303030735C303030635C3030306C5C3030306F5C303030735C303030755C303030725C30303065}
\BKM@entry{id=37,open,dest={73656374696F6E2E3130},srcline={733}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030665C3030306C5C303030695C303030635C303030745C3030305C3034305C3030306F5C303030665C3030305C3034305C303030695C3030306E5C303030745C303030655C303030725C303030655C303030735C30303074}
\BKM@entry{id=36,open,dest={73656374696F6E2E3130},srcline={731}}{5C3337365C3337375C303030465C303030695C3030306E5C303030615C3030306E5C303030635C303030695C303030615C3030306C5C3030305C3034305C303030645C303030695C303030735C303030635C3030306C5C3030306F5C303030735C303030755C303030725C30303065}
\BKM@entry{id=37,open,dest={73656374696F6E2E3130},srcline={735}}{5C3337365C3337375C303030435C3030306F5C3030306E5C303030665C3030306C5C303030695C303030635C303030745C3030305C3034305C3030306F5C303030665C3030305C3034305C303030695C3030306E5C303030745C303030655C303030725C303030655C303030735C30303074}
\bibdata{wileyNJD-AMA}
\BKM@entry{id=38,open,dest={73656374696F6E2E3130},srcline={1}}{5C3337365C3337375C303030525C303030455C303030465C303030455C303030525C303030455C3030304E5C303030435C303030455C30303053}
\bibcite{Elgammal2024}{{1}{}{{}}{{}}}
\bibcite{Deng2014a}{{1}{}{{}}{{}}}
\newlabel{eq24}{{2}{18}{}{equation.9.2}{}}
\@writefile{toc}{\contentsline {section}{\numberline {10}Conclusions}{18}{section.10}\protected@file@percent }
\newlabel{sec5}{{10}{18}{}{section.10}{}}
\newlabel{sec16}{{10}{18}{}{section.10}{}}
\@writefile{toc}{\contentsline {section}{Author contributions}{18}{section.10}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{Acknowledgments}{18}{section.10}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{Financial disclosure}{18}{section.10}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{Conflict of interest}{18}{section.10}\protected@file@percent }
\bibcite{Hirt1974}{{2}{}{{}}{{}}}
\bibcite{Burton2013}{{3}{}{{}}{{}}}
\bibcite{Berndt2011}{{4}{}{{}}{{}}}
\bibcite{Kucharik2012}{{5}{}{{}}{{}}}
\bibcite{Breil2015}{{6}{}{{}}{{}}}
\bibcite{Barth1997}{{7}{}{{}}{{}}}
\bibcite{Liska2010}{{8}{}{{}}{{}}}
\bibcite{Kucharik2003}{{9}{}{{}}{{}}}
\bibcite{Blanchard2015}{{10}{}{{}}{{}}}
\bibcite{Lauritzen2011}{{11}{}{{}}{{}}}
\bibcite{Klima2017}{{12}{}{{}}{{}}}
\bibcite{Dukowicz2000}{{13}{}{{}}{{}}}
\bibcite{Kucharik2011}{{14}{}{{}}{{}}}
\bibcite{Kucharik2014}{{15}{}{{}}{{}}}
\bibcite{Loubere2005}{{16}{}{{}}{{}}}
\bibcite{Caramana1998}{{17}{}{{}}{{}}}
\bibcite{Hoch2009}{{18}{}{{}}{{}}}
\bibcite{Shashkov1996}{{19}{}{{}}{{}}}
\bibcite{Knupp1999}{{20}{}{{}}{{}}}
\bibcite{Kamm2000}{{21}{}{{}}{{}}}
\bibcite{Taylor1937}{{22}{}{{}}{{}}}
\bibcite{Benson1992}{{23}{}{{}}{{}}}
\bibcite{Margolin2003}{{24}{}{{}}{{}}}
\bibcite{Kenamond2013}{{25}{}{{}}{{}}}
\bibcite{Dukowicz1984}{{26}{}{{}}{{}}}
\bibcite{Margolin2002}{{27}{}{{}}{{}}}
\bibcite{Mavriplis2003}{{28}{}{{}}{{}}}
\bibcite{Scovazzi2008}{{29}{}{{}}{{}}}
\BKM@entry{id=39,open,dest={73656374696F6E2E3130},srcline={740}}{5C3337365C3337375C303030535C303030755C303030705C303030705C3030306F5C303030725C303030745C303030695C3030306E5C303030675C3030305C3034305C303030695C3030306E5C303030665C3030306F5C303030725C3030306D5C303030615C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=40,open,dest={73656374696F6E2E3130},srcline={748}}{5C3337365C3337375C303030415C303030505C303030505C303030455C3030304E5C303030445C303030495C30303058}
\BKM@entry{id=41,open,dest={417070656E6469782E312E41},srcline={750}}{5C3337365C3337375C303030505C303030725C3030306F5C303030675C303030725C303030615C3030306D5C3030305C3034305C303030635C3030306F5C303030645C303030655C303030735C3030305C3034305C303030615C303030705C303030705C303030655C303030615C303030725C3030305C3034305C303030695C3030306E5C3030305C3034305C303030415C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\bibcite{Deng2015}{{2}{}{{}}{{}}}
\bibcite{Deng2014}{{3}{}{{}}{{}}}
\bibcite{Deng2015a}{{4}{}{{}}{{}}}
\bibcite{Deng2014b}{{5}{}{{}}{{}}}
\bibcite{Elgammal2024}{{6}{}{{}}{{}}}
\bibcite{Hirt1974}{{7}{}{{}}{{}}}
\bibcite{Burton2013}{{8}{}{{}}{{}}}
\bibcite{Berndt2011}{{9}{}{{}}{{}}}
\bibcite{Kucharik2012}{{10}{}{{}}{{}}}
\bibcite{Breil2015}{{11}{}{{}}{{}}}
\bibcite{Barth1997}{{12}{}{{}}{{}}}
\bibcite{Liska2010}{{13}{}{{}}{{}}}
\bibcite{Kucharik2003}{{14}{}{{}}{{}}}
\bibcite{Blanchard2015}{{15}{}{{}}{{}}}
\bibcite{Lauritzen2011}{{16}{}{{}}{{}}}
\bibcite{Klima2017}{{17}{}{{}}{{}}}
\bibcite{Dukowicz2000}{{18}{}{{}}{{}}}
\bibcite{Kucharik2011}{{19}{}{{}}{{}}}
\bibcite{Kucharik2014}{{20}{}{{}}{{}}}
\bibcite{Loubere2005}{{21}{}{{}}{{}}}
\bibcite{Caramana1998}{{22}{}{{}}{{}}}
\bibcite{Hoch2009}{{23}{}{{}}{{}}}
\bibcite{Shashkov1996}{{24}{}{{}}{{}}}
\bibcite{Knupp1999}{{25}{}{{}}{{}}}
\bibcite{Kamm2000}{{26}{}{{}}{{}}}
\bibcite{Taylor1937}{{27}{}{{}}{{}}}
\bibcite{Benson1992}{{28}{}{{}}{{}}}
\bibcite{Margolin2003}{{29}{}{{}}{{}}}
\bibcite{Kenamond2013}{{30}{}{{}}{{}}}
\bibcite{Dukowicz1984}{{31}{}{{}}{{}}}
\bibcite{Margolin2002}{{32}{}{{}}{{}}}
\bibcite{Mavriplis2003}{{33}{}{{}}{{}}}
\bibcite{Scovazzi2008}{{34}{}{{}}{{}}}
\@writefile{toc}{\contentsline {section}{\fontsize {10}{13}\selectfont \bfseries {{REFERENCES}}\markboth {\MakeUppercase []{References}}{\MakeUppercase []{References}}}{19}{section.10}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{Supporting information}{19}{section.10}\protected@file@percent }
\BKM@entry{id=42,open,dest={73756273656374696F6E2E312E412E31},srcline={768}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030665C303030695C303030725C303030735C303030745C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=43,open,dest={73756273756273656374696F6E2E312E412E312E31},srcline={791}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030665C303030695C303030725C303030735C303030745C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=39,open,dest={73656374696F6E2E3130},srcline={742}}{5C3337365C3337375C303030535C303030755C303030705C303030705C3030306F5C303030725C303030745C303030695C3030306E5C303030675C3030305C3034305C303030695C3030306E5C303030665C3030306F5C303030725C3030306D5C303030615C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=40,open,dest={73656374696F6E2E3130},srcline={750}}{5C3337365C3337375C303030415C303030505C303030505C303030455C3030304E5C303030445C303030495C30303058}
\BKM@entry{id=41,open,dest={417070656E6469782E312E41},srcline={752}}{5C3337365C3337375C303030505C303030725C3030306F5C303030675C303030725C303030615C3030306D5C3030305C3034305C303030635C3030306F5C303030645C303030655C303030735C3030305C3034305C303030615C303030705C303030705C303030655C303030615C303030725C3030305C3034305C303030695C3030306E5C3030305C3034305C303030415C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=42,open,dest={73756273656374696F6E2E312E412E31},srcline={770}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030665C303030695C303030725C303030735C303030745C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=43,open,dest={73756273756273656374696F6E2E312E412E312E31},srcline={793}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030665C303030695C303030725C303030735C303030745C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\@writefile{toc}{\contentsline {section}{Supporting information}{20}{section.10}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{APPENDIX}{20}{section.10}\protected@file@percent }
\newlabel{APP1}{{A}{20}{}{Appendix.1.A}{}}
\@writefile{toc}{\contentsline {section}{\numberline {A}Program codes appear in Appendix}{20}{Appendix.1.A}\protected@file@percent }
......@@ -205,27 +213,27 @@
\@writefile{toc}{\contentsline {subsection}{\numberline {A.1}Subsection title of first appendix}{20}{subsection.1.A.1}\protected@file@percent }
\newlabel{app1.1.1a}{{A.1.1}{20}{}{subsubsection.1.A.1.1}{}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {A.1.1}Subsection title of first appendix}{20}{subsubsection.1.A.1.1}\protected@file@percent }
\BKM@entry{id=44,open,dest={417070656E6469782E312E42},srcline={814}}{5C3337365C3337375C303030535C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=45,open,dest={73756273656374696F6E2E312E422E31},srcline={836}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=46,open,dest={73756273756273656374696F6E2E312E422E312E31},srcline={852}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=44,open,dest={417070656E6469782E312E42},srcline={816}}{5C3337365C3337375C303030535C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=45,open,dest={73756273656374696F6E2E312E422E31},srcline={838}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\newlabel{APP2}{{B}{21}{}{Appendix.1.B}{}}
\@writefile{toc}{\contentsline {section}{\numberline {B}Section title of second appendix}{21}{Appendix.1.B}\protected@file@percent }
\newlabel{app2.1a}{{B.1}{21}{}{subsection.1.B.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {B.1}Subsection title of second appendix}{21}{subsection.1.B.1}\protected@file@percent }
\newlabel{app2.1.1a}{{B.1.1}{21}{}{subsubsection.1.B.1.1}{}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {B.1.1}Subsection title of second appendix}{21}{subsubsection.1.B.1.1}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {B1}{\ignorespaces This is an example for appendix figure.}}{21}{figure.caption.7}\protected@file@percent }
\newlabel{fig5}{{B1}{21}{This is an example for appendix figure}{figure.caption.7}{}}
\BKM@entry{id=47,open,dest={417070656E6469782E312E43},srcline={889}}{5C3337365C3337375C303030455C303030785C303030615C3030306D5C303030705C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030615C3030306E5C3030306F5C303030745C303030685C303030655C303030725C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C303030785C3030305C3034305C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E}
\BKM@entry{id=46,open,dest={73756273756273656374696F6E2E312E422E312E31},srcline={854}}{5C3337365C3337375C303030535C303030755C303030625C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E5C3030305C3034305C303030745C303030695C303030745C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030735C303030655C303030635C3030306F5C3030306E5C303030645C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C30303078}
\BKM@entry{id=47,open,dest={417070656E6469782E312E43},srcline={891}}{5C3337365C3337375C303030455C303030785C303030615C3030306D5C303030705C3030306C5C303030655C3030305C3034305C3030306F5C303030665C3030305C3034305C303030615C3030306E5C3030306F5C303030745C303030685C303030655C303030725C3030305C3034305C303030615C303030705C303030705C303030655C3030306E5C303030645C303030695C303030785C3030305C3034305C303030735C303030655C303030635C303030745C303030695C3030306F5C3030306E}
\@writefile{lot}{\contentsline {table}{\numberline {B1}{\ignorespaces This is an example of Appendix table showing food requirements of army, navy and airforce.}}{22}{table.caption.8}\protected@file@percent }
\newlabel{tab4}{{B1}{22}{This is an example of Appendix table showing food requirements of army, navy and airforce}{table.caption.8}{}}
\newlabel{app2.1.1a}{{B.1.1}{22}{}{subsubsection.1.B.1.1}{}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {B.1.1}Subsection title of second appendix}{22}{subsubsection.1.B.1.1}\protected@file@percent }
\newlabel{eq25}{{B1}{22}{}{equation.1.B.1}{}}
\newlabel{APP3}{{C}{22}{}{Appendix.1.C}{}}
\@writefile{toc}{\contentsline {section}{\numberline {C}Example of another appendix section}{22}{Appendix.1.C}\protected@file@percent }
\newlabel{eq26}{{C2}{22}{}{equation.1.C.2}{}}
\citation{*}
\BKM@entry{id=48,open,dest={6571756174696F6E2E312E432E32},srcline={964}}{5C3337365C3337375C303030415C303030755C303030745C303030685C3030306F5C303030725C3030305C3034305C303030425C303030695C3030306F5C303030675C303030725C303030615C303030705C303030685C30303079}
\BKM@entry{id=48,open,dest={6571756174696F6E2E312E432E32},srcline={966}}{5C3337365C3337375C303030415C303030755C303030745C303030685C3030306F5C303030725C3030305C3034305C303030425C303030695C3030306F5C303030675C303030725C303030615C303030705C303030685C30303079}
\FirstPg{1}\LastPg{23}
\providecommand\NAT@force@numbers{}\NAT@force@numbers
\newlabel{eq26}{{C2}{23}{}{equation.1.C.2}{}}
\@writefile{toc}{\contentsline {section}{Author Biography}{23}{equation.1.C.2}\protected@file@percent }
\gdef \@abspage@last{23}
Manuscript/Manuscript.bbl
\begin{thebibliography}{10}
\providecommand \doibase [0]{http://dx.doi.org/}%
\bibitem{Deng2014a}
Deng K, Pan P, Su Y, Ran T, Xue Y. Development of an energy dissipation restrainer for bridges using a steel shear panel. {\it Journal of Constructional Steel Research.} 2014\string;101\string:83--95.
\newblock \href {\doibase 10.1016/j.jcsr.2014.03.009} {doi: 10.1016/j.jcsr.2014.03.009}
\bibitem{Deng2015}
Deng K, Pan P, Li W, Xue Y. Development of a buckling restrained shear panel damper. {\it Journal of Constructional Steel Research.} 2015\string;106\string:311--321.
\newblock \href {\doibase 10.1016/j.jcsr.2015.01.004} {doi: 10.1016/j.jcsr.2015.01.004}
\bibitem{Deng2014}
Deng K, Pan P, Sun J, Liu J, Xue Y. Shape optimization design of steel shear panel dampers. {\it Journal of Constructional Steel Research.} 2014\string;99\string:187--193.
\newblock \href {\doibase 10.1016/j.jcsr.2014.03.001} {doi: 10.1016/j.jcsr.2014.03.001}
\bibitem{Deng2015a}
Deng K, Pan P, Su Y, Xue Y. Shape optimization of {U}-shaped damper for improving its bi-directional performance under cyclic loading. {\it Engineering Structures.} 2015\string;93\string:27--35.
\newblock \href {\doibase 10.1016/j.engstruct.2015.03.006} {doi: 10.1016/j.engstruct.2015.03.006}
\bibitem{Deng2014b}
Deng K, Pan P, Lam A, Xue Y. A simplified model for analysis of high-rise buildings equipped with hysteresis damped outriggers. {\it The Structural Design of Tall and Special Buildings.} 2014\string;23(15)\string:1158--1170.
\newblock \_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/tal.1113\href {\doibase 10.1002/tal.1113} {doi: 10.1002/tal.1113}
\bibitem{Elgammal2024}
Elgammal A, Ali Y. A novel hysteretic restoring force model for shear link dampers: {A} machine learning approach. {\it Structures.} 2024\string;70\string:107848.
\newblock \href {\doibase 10.1016/j.istruc.2024.107848} {doi: 10.1016/j.istruc.2024.107848}
......
Manuscript/Manuscript.blg
......@@ -3,44 +3,44 @@ Capacity: max_strings=200000, hash_size=200000, hash_prime=170003
The top-level auxiliary file: Manuscript.aux
The style file: WileyNJD-AMA.bst
Database file #1: wileyNJD-AMA.bib
You've used 29 entries,
You've used 34 entries,
2086 wiz_defined-function locations,
740 strings with 9720 characters,
and the built_in function-call counts, 5464 in all, are:
= -- 498
> -- 239
783 strings with 11196 characters,
and the built_in function-call counts, 6526 in all, are:
= -- 575
> -- 298
< -- 3
+ -- 102
- -- 73
* -- 580
:= -- 985
add.period$ -- 49
call.type$ -- 29
+ -- 129
- -- 95
* -- 718
:= -- 1173
add.period$ -- 54
call.type$ -- 34
change.case$ -- 2
chr.to.int$ -- 0
cite$ -- 29
duplicate$ -- 285
empty$ -- 557
format.name$ -- 73
if$ -- 1251
cite$ -- 34
duplicate$ -- 340
empty$ -- 657
format.name$ -- 95
if$ -- 1470
int.to.chr$ -- 0
int.to.str$ -- 29
missing$ -- 26
newline$ -- 99
num.names$ -- 33
pop$ -- 67
int.to.str$ -- 34
missing$ -- 31
newline$ -- 119
num.names$ -- 38
pop$ -- 75
preamble$ -- 1
purify$ -- 0
quote$ -- 0
skip$ -- 35
skip$ -- 40
stack$ -- 0
substring$ -- 0
swap$ -- 28
swap$ -- 48
text.length$ -- 3
text.prefix$ -- 0
top$ -- 0
type$ -- 0
warning$ -- 0
while$ -- 31
width$ -- 31
write$ -- 326
while$ -- 36
width$ -- 36
write$ -- 388
Manuscript/Manuscript.fdb_latexmk
# Fdb version 4
["bibtex Manuscript"] 1775808645.83164 "Manuscript.aux" "Manuscript.bbl" "Manuscript" 1775808647.36868 0
"./wileyNJD-AMA.bib" 1775661423.01154 12481 d3c1ec04186781edf5cae85ded22a40b ""
["bibtex Manuscript"] 1776327267.214 "Manuscript.aux" "Manuscript.bbl" "Manuscript" 1776327268.4116 0
"./wileyNJD-AMA.bib" 1776327033.62821 22635 ac78711a00932a09d59c9d66618441ea ""
"./wileyNJD-AMA.bst" 1768403161.04645 19155 8fd474a7161c22bb6a795bd57510d2e1 ""
"Manuscript.aux" 1775808646.88201 32894 d0c0c56b060dcd4df4e506d7feccb7d5 "pdflatex"
"Manuscript.aux" 1776327268.15206 33155 f2589dad76cdbdd1a8af76c8e4700460 "pdflatex"
(generated)
"Manuscript.bbl"
"Manuscript.blg"
(rewritten before read)
["pdflatex"] 1775808645.93506 "/home/cimne/Articles_in_process/2026_Article_RESILINK_ML/Manuscript/Manuscript.tex" "Manuscript.pdf" "Manuscript" 1775808647.36888 0
["pdflatex"] 1776327267.34583 "/home/cimne/Articles_in_process/2026_Article_RESILINK_ML/Manuscript/Manuscript.tex" "Manuscript.pdf" "Manuscript" 1776327268.4118 0
"/etc/texmf/web2c/texmf.cnf" 1727440723.11971 475 c0e671620eb5563b2130f56340a5fde8 ""
"/home/cimne/Articles_in_process/2026_Article_RESILINK_ML/Manuscript/Manuscript.tex" 1775808627.80383 86636 d406710a534778a383839dd0108cefcf ""
"/home/cimne/Articles_in_process/2026_Article_RESILINK_ML/Manuscript/Manuscript.tex" 1776327265.87996 87744 49a228ccac70c171aff96da1aaba9077 ""
"/usr/share/texlive/texmf-dist/fonts/enc/dvips/base/8r.enc" 1165713224 4850 80dc9bab7f31fb78a000ccfed0e27cab ""
"/usr/share/texlive/texmf-dist/fonts/map/fontname/texfonts.map" 1577235249 3524 cb3e574dea2d1052e39280babc910dc8 ""
"/usr/share/texlive/texmf-dist/fonts/tfm/adobe/courier/pcrb8r.tfm" 1136768653 1292 3059476c50a24578715759f22652f3d0 ""
......@@ -190,9 +190,9 @@
"/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map" 1727447066.11376 5472669 54eaf61a88b6b7896ebd0dac973cb29c ""
"/var/lib/texmf/web2c/pdftex/pdflatex.fmt" 1727447091 8213230 bd25039be121841657767565aabcb4cb ""
"LETTERSP.STY" 1768403161.04145 12163 b6de1fa5e93e58dc68ba3c77a1af2e61 ""
"Manuscript.aux" 1775808646.88201 32894 d0c0c56b060dcd4df4e506d7feccb7d5 "pdflatex"
"Manuscript.bbl" 1775808645.93001 7163 ba7aff43d6fd11d7017ffd22ea0caf5d "bibtex Manuscript"
"Manuscript.tex" 1775808627.80383 86636 d406710a534778a383839dd0108cefcf ""
"Manuscript.aux" 1776327268.15206 33155 f2589dad76cdbdd1a8af76c8e4700460 "pdflatex"
"Manuscript.bbl" 1776327267.34103 8721 83e33752cfa17df61036e774d1ae9768 "bibtex Manuscript"
"Manuscript.tex" 1776327265.87996 87744 49a228ccac70c171aff96da1aaba9077 ""
"NJDnatbib.sty" 1768403161.04145 45877 277c41da70878866aa377a8f5b8b53d8 ""
"WileyNJDv5.cls" 1768403161.04545 229209 b00f44318e3c54456bb10ed4e19ec0c4 ""
"algorithm.sty" 1768403161.04545 3249 15763257e50278eef5db1952ccde229c ""
......
Manuscript/Manuscript.log
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023/Debian) (preloaded format=pdflatex 2024.9.27) 10 APR 2026 10:10
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023/Debian) (preloaded format=pdflatex 2024.9.27) 16 APR 2026 10:14
entering extended mode
restricted \write18 enabled.
file:line:error style messages enabled.
......@@ -917,17 +917,7 @@ File: l3backend-pdftex.def 2024-01-04 L3 backend support: PDF output (pdfTeX)
LaTeX Warning: Unused global option(s):
[AMA,Times1COL].
(./Manuscript.aux
LaTeX Warning: Label `sec1_2' multiply defined.
LaTeX Warning: Label `sec4' multiply defined.
LaTeX Warning: Label `sec5' multiply defined.
)
(./Manuscript.aux)
\openout1 = `Manuscript.aux'.
LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 18.
......@@ -1070,8 +1060,13 @@ File: ts1ptm.fd 2001/06/04 font definitions for TS1/ptm.
\openout3 = `Manuscript.pag'.
] [2]
<empty.pdf, id=27, 114.43155pt x 86.162pt>
LaTeX Font Info: Trying to load font information for T1+pcr on input line 134.
Overfull \hbox (91.15167pt too wide) has occurred while \output is active
\T1/ptm/m/n/7 FAST DESIGN OPTIMIZATION OF SLB DAMPERS USING FEM-CALIBRATED SURROGATES: HYSTERESIS PREDICTION WITH LSTM AND DAMAGE-CONSTRAINED OPTIMIZATION []| [][]
[]
[3]
<empty.pdf, id=45, 114.43155pt x 86.162pt>
LaTeX Font Info: Trying to load font information for T1+pcr on input line 136.
(/usr/share/texlive/texmf-dist/tex/latex/psnfss/t1pcr.fd
File: t1pcr.fd 2001/06/04 font definitions for T1/pcr.
)
......@@ -1080,17 +1075,12 @@ Package microtype Info: Loading generic protrusion settings for font family
(microtype) For optimal results, create family-specific settings.
(microtype) See the microtype manual for details.
Underfull \hbox (badness 10000) detected at line 135
Underfull \hbox (badness 10000) detected at line 137
[]
[]
Overfull \hbox (91.15167pt too wide) has occurred while \output is active
\T1/ptm/m/n/7 FAST DESIGN OPTIMIZATION OF SLB DAMPERS USING FEM-CALIBRATED SURROGATES: HYSTERESIS PREDICTION WITH LSTM AND DAMAGE-CONSTRAINED OPTIMIZATION []| [][]
[]
[3]
Underfull \hbox (badness 10000) detected at line 145
Underfull \hbox (badness 10000) detected at line 147
[]
[]
......@@ -1110,15 +1100,12 @@ Overfull \hbox (91.15167pt too wide) has occurred while \output is active
[]
[9]
Underfull \hbox (badness 10000) detected at line 345
Underfull \hbox (badness 10000) detected at line 347
[]
[]
LaTeX Warning: `!h' float specifier changed to `!ht'.
[10]
Underfull \hbox (badness 10000) detected at line 395
Underfull \hbox (badness 10000) detected at line 397
[]
[]
......@@ -1130,7 +1117,7 @@ Overfull \hbox (91.15167pt too wide) has occurred while \output is active
[11]
LaTeX Warning: The counter will not be printed.
The label is: on input line 475.
The label is: on input line 477.
[12]
Overfull \hbox (91.15167pt too wide) has occurred while \output is active
......@@ -1138,16 +1125,16 @@ Overfull \hbox (91.15167pt too wide) has occurred while \output is active
[]
[13]
Underfull \hbox (badness 10000) detected at line 561
Underfull \hbox (badness 10000) detected at line 563
[]
[]
Underfull \hbox (badness 10000) detected at line 601
Underfull \hbox (badness 10000) detected at line 603
[]
[]
Package hyperref Info: bookmark level for unknown algorithm defaults to 0 on input line 609.
Package hyperref Info: bookmark level for unknown algorithm defaults to 0 on input line 611.
[14]
Overfull \hbox (91.15167pt too wide) has occurred while \output is active
\T1/ptm/m/n/7 FAST DESIGN OPTIMIZATION OF SLB DAMPERS USING FEM-CALIBRATED SURROGATES: HYSTERESIS PREDICTION WITH LSTM AND DAMAGE-CONSTRAINED OPTIMIZATION []| [][]
......@@ -1159,51 +1146,50 @@ Overfull \hbox (91.15167pt too wide) has occurred while \output is active
[]
[17] (./Manuscript.bbl [18]
LaTeX Font Info: Calculating math sizes for size <8.5> on input line 36.
LaTeX Font Info: Calculating math sizes for size <8.5> on input line 56.
LaTeX Font Warning: Font shape `OT1/cmr/m/n' in size <8.5> not available
(Font) size <8> substituted on input line 36.
(Font) size <8> substituted on input line 56.
LaTeX Font Warning: Font shape `OT1/cmr/m/n' in size <4.25> not available
(Font) size <5> substituted on input line 36.
(Font) size <5> substituted on input line 56.
LaTeX Font Warning: Font shape `OML/cmm/m/it' in size <8.5> not available
(Font) size <8> substituted on input line 36.
(Font) size <8> substituted on input line 56.
LaTeX Font Warning: Font shape `OML/cmm/m/it' in size <4.25> not available
(Font) size <5> substituted on input line 36.
(Font) size <5> substituted on input line 56.
LaTeX Font Warning: Font shape `OMS/cmsy/m/n' in size <8.5> not available
(Font) size <8> substituted on input line 36.
(Font) size <8> substituted on input line 56.
LaTeX Font Warning: Font shape `OMS/cmsy/m/n' in size <4.25> not available
(Font) size <5> substituted on input line 36.
(Font) size <5> substituted on input line 56.
)
Overfull \hbox (9.0pt too wide) in paragraph at lines 748--748
[] []
[]
Overfull \hbox (91.15167pt too wide) has occurred while \output is active
\T1/ptm/m/n/7 FAST DESIGN OPTIMIZATION OF SLB DAMPERS USING FEM-CALIBRATED SURROGATES: HYSTERESIS PREDICTION WITH LSTM AND DAMAGE-CONSTRAINED OPTIMIZATION []| [][]
[]
[19]
Package hyperref Info: bookmark level for unknown lstlisting defaults to 0 on input line 757.
Overfull \hbox (9.0pt too wide) in paragraph at lines 750--750
[] []
[]
Underfull \hbox (badness 10000) detected at line 757
Package hyperref Info: bookmark level for unknown lstlisting defaults to 0 on input line 759.
Underfull \hbox (badness 10000) detected at line 759
[]
[]
[20]
Underfull \hbox (badness 10000) detected at line 833
Underfull \hbox (badness 10000) detected at line 835
[]
[]
......@@ -1213,7 +1199,7 @@ Overfull \hbox (91.15167pt too wide) has occurred while \output is active
[]
[21]
Underfull \hbox (badness 10000) detected at line 871
Underfull \hbox (badness 10000) detected at line 873
[]
[]
......@@ -1232,9 +1218,6 @@ L3 programming layer <2024-01-22>
LaTeX Font Warning: Size substitutions with differences
(Font) up to 0.75pt have occurred.
LaTeX Warning: There were multiply-defined labels.
)
(\end occurred when \iftrue on line 4824 was incomplete)
(\end occurred when \iftrue on line 4812 was incomplete)
......@@ -1246,18 +1229,18 @@ LaTeX Warning: There were multiply-defined labels.
(\end occurred when \iftrue on line 4740 was incomplete)
(\end occurred when \ifx on line 2 was incomplete)
Here is how much of TeX's memory you used:
23079 strings out of 474222
356659 string characters out of 5748733
1948975 words of memory out of 5000000
44387 multiletter control sequences out of 15000+600000
677483 words of font info for 391 fonts, out of 8000000 for 9000
23108 strings out of 474222
357055 string characters out of 5748733
1949975 words of memory out of 5000000
44405 multiletter control sequences out of 15000+600000
677838 words of font info for 395 fonts, out of 8000000 for 9000
1167 hyphenation exceptions out of 8191
90i,18n,93p,2671b,1065s stack positions out of 10000i,1000n,20000p,200000b,200000s
</usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmex10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmmi10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmmi5.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmmi7.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmr10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmr7.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmsy10.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmsy5.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmsy6.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmsy7.pfb></usr/share/texlive/texmf-dist/fonts/type1/public/amsfonts/cm/cmsy8.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/courier/ucrb8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/courier/ucrr8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/times/utmb8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/times/utmr8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/times/utmri8a.pfb>
Output written on Manuscript.pdf (23 pages, 254526 bytes).
Output written on Manuscript.pdf (23 pages, 258213 bytes).
PDF statistics:
519 PDF objects out of 1000 (max. 8388607)
456 compressed objects within 5 object streams
131 named destinations out of 1000 (max. 500000)
536 PDF objects out of 1000 (max. 8388607)
473 compressed objects within 5 object streams
136 named destinations out of 1000 (max. 500000)
125830 words of extra memory for PDF output out of 128383 (max. 10000000)
Manuscript/Manuscript.tex
......@@ -81,13 +81,13 @@ Despite their advantages, the direct use of FEM models within optimization loops
Furthermore, purely data-driven approaches face intrinsic limitations when applied to this class of problems. Models trained on limited datasets often exhibit poor extrapolation capabilities when queried outside the domain covered by the training data, which is particularly critical in design optimization scenarios. As a consequence, there is a clear need for surrogate modeling techniques that are both computationally efficient and sufficiently reliable to approximate complex nonlinear responses, while remaining consistent with the underlying physics captured by FEM simulations.
\subsection{State of the art and related work}\label{sec1_2}
\subsection{State of the art and related work}\label{sec1_3}
Over the past years, the finite element method (FEM) has been widely employed to investigate the behavior of energy dissipation devices subjected to seismic loading, providing detailed insight into their nonlinear cyclic response, stiffness degradation, and local inelastic mechanisms \cite{Deng2014a, Deng2015}. FEM has also been used as a tool for the optimization of such devices, enabling the systematic exploration of geometric configurations and performance criteria under prescribed loading conditions \cite{Deng2014, Deng2015a}. In parallel, simplified models have been proposed to estimate the structural response of systems equipped with this type of dissipative devices, with the aim of reducing computational cost and facilitating their use in engineering practice \cite{Deng2014b}. Although these approaches have contributed significantly to the analysis and design of seismic energy dissipation systems, computational efficiency and predictive fidelity remain competing requirements, particularly when complex hysteretic behavior and local damage phenomena must be simultaneously captured.
Elgammal and Ali \cite{Elgammal2024} present an enhanced hysteretic restoring force model for shear link dampers and introduces a machine learning approach to predict its hardening parameters without requiring prior experimental hysteretic curves. The study followed a three-phase methodology: first, a numerical investigation of 350 specimens was conducted to derive analytical formulas for key parameters like shear yield strength and buckling rotation. In the second phase, a genetic algorithm was employed to determine optimal hardening parameters by aligning analytical curves with numerical data. Finally, an Artificial Neural Network (ANN) was trained using these parameters and the dampers' geometric properties to enable the prediction of hysteretic response for any new specimen based solely on its dimensions. The model was successfully validated through blind testing against independent experimental data and has been integrated into a graphical user interface tool called SL-Analyser for practical engineering applications.
\subsection{Contributions of this work}\label{sec1_3}
\subsection{Contributions of this work}\label{sec1_4}
This paper proposes a surrogate-assisted optimization framework for SLB dampers subjected to cyclic loading, combining FEM-calibrated datasets with advanced machine learning techniques. The main contributions of the work can be summarized as follows:
......@@ -343,7 +343,7 @@ Vivamus eu dolor.
\begin{center}
\begin{table*}[!h]%
\begin{table*}[!ht]%
\caption{This is sample table caption.\label{tab1}}
\begin{tabular*}{\textwidth}{@{\extracolsep\fill}lllll@{}}
\toprule
......@@ -481,7 +481,7 @@ et quam. Below is the example for description list. Below is the example for des
\item Sample unnumberd list text.
\end{enumerate}
\section{Examples for enunciations}\label{sec4}
\section{Examples for enunciations}\label{sec15}
\begin{theorem}\label{thm1}
Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text. Example theorem text.
......@@ -701,7 +701,7 @@ Vivamus eu dolor.
\section{Conclusions}\label{sec5}
\section{Conclusions}\label{sec16}
Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Ut purus elit, vestibulum ut, placerat ac, adipiscing vitae,
felis. Curabitur dictum gravida mauris. Nam arcu libero, nonummy eget, consectetuer id, vulputate a, magna. Donec
......
Manuscript/wileyNJD-AMA.bib
......@@ -318,4 +318,87 @@ organization = "The organization",
urldate = {2026-04-08},
}
@Article{Deng2014,
author = {Deng, Kailai and Pan, Peng and Sun, Jiangbo and Liu, Jixin and Xue, Yantao},
journal = {Journal of Constructional Steel Research},
title = {Shape optimization design of steel shear panel dampers},
year = {2014},
issn = {0143-974X},
month = aug,
pages = {187--193},
volume = {99},
abstract = {Steel shear panel dampers (SSPDs) have a reasonably good and stable energy dissipation capacity, and are widely used in engineering to enhance the structural safety of buildings in large earthquakes. Efforts to improve the low cycle fatigue performance of SSPDs have focused mostly on the arrangement of the stiffeners or on the effects of the material properties. The shape of the SSPD plate has not been well investigated. This paper presents a shape optimization method for improving the low cycle fatigue performance of SSPDs. The shear plate shape of the SSPD is taken as the variable in the optimization process. The low cycle fatigue performance of the SSPD is assumed to have a negative relationship to the maximum equivalent plastic strain in the cyclic loading process. The equivalent plastic strains are obtained using the finite element software ABAQUS. The simulated annealing method is adopted for the optimization, which is capable of solving optimization problems involving strong nonlinear systems. In the optimization, four types of SSPDs with different aspect were modeled and the optimal shape of the SSPD for each case was derived. It can be found that the low cycle fatigue performance of the SSPD was significantly improved and the global optimal solution showed better performance compared to the local optimal solution.},
doi = {10.1016/j.jcsr.2014.03.001},
keywords = {Finite element analysis, Low cycle fatigue performance, Shape optimization, Simulating annealing, Steel shear panel damper},
url = {https://www.sciencedirect.com/science/article/pii/S0143974X14000650},
urldate = {2026-04-15},
}
@Article{Deng2014a,
author = {Deng, Kailai and Pan, Peng and Su, Yukun and Ran, Tianran and Xue, Yantao},
journal = {Journal of Constructional Steel Research},
title = {Development of an energy dissipation restrainer for bridges using a steel shear panel},
year = {2014},
issn = {0143-974X},
month = oct,
pages = {83--95},
volume = {101},
abstract = {Restrainers, along with isolation bearings, are often installed in bridges to avoid upper girders falling off their piers during large earthquakes. In this study, a novel energy dissipation restrainer was developed. The energy dissipation restrainer remains elastic and provides a reaction force to restrain the displacement of the girder during small earthquakes, maintaining the functionality of the bridges. When large earthquakes occur, the restrainer can yield and dissipate energy, thus reducing the deformation between the superstructures and piers, and protecting the piers from server damages. To verify the performance of the restrainer, five specimens were designed and subjected to physical loading tests. The test results suggest that when appropriately designed, the restrainer has satisfactory deformation and energy dissipation capacities. The thickness of the side flange and width of the energy dissipation plate have significant effects on its performance. Because the number of physical tests was limited, finite element models were built using the general finite element program ABAQUS to supplement the results, and a parametric study focusing on the effects of the side flange thickness and restrainer width was conducted. Based on the test and analysis results, a formula for estimating the restrainer strength was derived.},
doi = {10.1016/j.jcsr.2014.03.009},
keywords = {Bridge, Energy dissipation capacity, Finite element model, Parameter fitting, Restrainer},
url = {https://www.sciencedirect.com/science/article/pii/S0143974X14000819},
urldate = {2026-04-15},
}
@Article{Deng2015,
author = {Deng, Kailai and Pan, Peng and Li, Wei and Xue, Yantao},
journal = {Journal of Constructional Steel Research},
title = {Development of a buckling restrained shear panel damper},
year = {2015},
issn = {0143-974X},
month = mar,
pages = {311--321},
volume = {106},
abstract = {Steel shear panel dampers (SPDs) have been widely used in structural seismic design. The low cycle fatigue damage for SPD often occurs close to the welded stiffener, significantly weakening the fatigue performance of the damper. A novel steel shear panel damper called a buckling restrained shear panel damper (BRSPD) is proposed in this paper. A BRSPD has two main parts, an energy dissipation plate and two restraining plates. No stiffener is welded to the energy dissipation plate. The two restraining plates clamp the energy dissipation plate with bolts on both sides to prevent out-of-plane buckling. Quasi-static tests of five specimens were carried out to investigate the performance of the BRSPDs. The test focused on the stiffness and strength of the restraining plates and the gaps between them and the energy dissipation plate. The tests showed that the restraining plates with adequate stiffness and strength can effectively restrain the out-of-plane buckling of the energy dissipation plate. Numerical analysis of the BRSPD was conducted using the general finite element program, ABAQUS, to supplement the test results. A design method for the restraining plates and the bolts is suggested based on the test and analysis results.},
doi = {10.1016/j.jcsr.2015.01.004},
keywords = {Buckling restrained shear panel damper, Design method, Low cycle fatigue, Numerical analyses, Quasi-static test},
url = {https://www.sciencedirect.com/science/article/pii/S0143974X15000061},
urldate = {2026-04-15},
}
@Article{Deng2015a,
author = {Deng, Kailai and Pan, Peng and Su, Yukun and Xue, Yantao},
journal = {Engineering Structures},
title = {Shape optimization of {U}-shaped damper for improving its bi-directional performance under cyclic loading},
year = {2015},
issn = {0141-0296},
month = jun,
pages = {27--35},
volume = {93},
abstract = {A U-shaped damper typically has a stable and saturated hysteretic performance along the in-plane direction and is usually installed in the isolation layer. However experimental study shows that the conventional U-shaped damper presents an unstable hysteretic performance when it sustains bi-directional deformations. Therefore, shape optimization is needed to improve the hysteretic performance of the U-shaped damper. To obtain an optimal shape for the U-shaped damper, a finite element (FE) model was built using a general FE analysis software called ABAQUS. Comparisons of results obtained from FE models with those obtained from experimental studies demonstrated the effectiveness of the FE models. Optimization of a U-shaped damper was carried out using the FE model. The length and shape of the straight part of the U-shaped damper were treated as optimization parameters and the enlarging the end of the straight part was adopted as the improved approach. The formula for the ratio of the energy dissipated by rate-independent and rate-dependent plastic deformation (ALLPD) to the maximum cumulative equivalent plastic strain (PEEQ) was derived though regression analysis. After four levels of optimization processes the optimal shape of the improved U-shaped damper was obtained, and the bi-directional performance was significantly improved compared to that of a conventional U-shaped damper.},
doi = {10.1016/j.engstruct.2015.03.006},
keywords = {Bi-directional performance, Response surface method, Shape optimization, U-shaped damper},
url = {https://www.sciencedirect.com/science/article/pii/S014102961500142X},
urldate = {2026-04-15},
}
@Article{Deng2014b,
author = {Deng, Kailai and Pan, Peng and Lam, Alexandre and Xue, Yantao},
journal = {The Structural Design of Tall and Special Buildings},
title = {A simplified model for analysis of high-rise buildings equipped with hysteresis damped outriggers},
year = {2014},
issn = {1541-7808},
note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/tal.1113},
number = {15},
pages = {1158--1170},
volume = {23},
abstract = {A simplified model is developed to estimate the seismic response of high-rise buildings equipped with hysteresis damped outriggers. In the simplified model, the core tube is considered as a cantilever beam, and the effects of outriggers on the core tube are considered as concentrated moments. Modal decomposition method is adopted to obtain the seismic response of the simplified model. To investigate the accuracy and effectiveness of the simplified model, a high-rise building with a height of 160 m was adopted as the example structure, and its response subjected to a ground motion was analyzed using the simplified model. A corresponding finite element model was built and analyzed by a finite element program called SAP2000 (Computers and Structures, Inc. Berkeley, California, United States). The analysis results obtained from the two models were compared. To consider the randomness of the ground motion, comparisons between the two models were further conducted using another 22 ground motions. It is found that the analysis results obtained from the simplified model agree well with those obtained from the finite element model, and the computation time used for the simplified model is almost negligible compared to that used for the finite element model. Such observations demonstrate that the simplified model is accurate and effective. Copyright © 2013 John Wiley \& Sons, Ltd.},
copyright = {Copyright © 2013 John Wiley \& Sons, Ltd.},
doi = {10.1002/tal.1113},
keywords = {distribute parameter system, high-rise building, hysteresis damper, outrigger, simplified model},
language = {en},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/tal.1113},
urldate = {2026-04-15},
}
@Comment{jabref-meta: databaseType:bibtex;}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment