Revise abstract and methodology sections for clarity; update design variables and geometry families in manuscript

- Updated cross-validation results for models in B29 and B34, including new performance metrics and model parameters.
- Added new model outputs for Gradient Boosting and SVR in the cv_summary_per_output_B29_H45.csv file.
- Introduced new figures and updated manuscript sections to reflect changes in model selection and optimization strategies.
- Included new binary files for model outputs and results in both B29 and B34 directories.
- Enhanced the Bayesian optimization process description in the manuscript to clarify the methodology and results.

- Added new CSV files for optimization results of 2W and 3W configurations.
- Updated the `ml_surrogate_train.py` to change cross-validation strategy for sample sizes between 21 and 80.
- Modified `run_rbf.sh` to execute training scripts for iteration 1 instead of 0.
- Updated manuscript to reflect changes in design variables and optimization methodology.
- Added new references to the bibliography for Bayesian optimization.
- Included new PDF of the manuscript in the repository.

Enhance manuscript content by refining design of experiments section and adding new references for Latin Hypercube Sampling methodologies

- Revised the text to clarify the damage-aware surrogate-assisted optimization methodology, emphasizing the balance between dissipative performance and damage indicators.
- Changed the figure reference from "illustrates" to "summarizes" for improved clarity.
- Adjusted the figure size for better presentation in the manuscript.
- Updated the figure caption to accurately reflect the content of the flowchart.

- Introduced a new flow chart image (MethodologyFlowChart.png) to visually represent the adaptive surrogate-assisted optimization framework.
- Expanded the manuscript to include detailed descriptions of the proposed methodology, emphasizing the balance between energy dissipation and damage control.
- Added systematic comparisons of surrogate techniques and outlined the adaptive FEM validation and retraining strategy.

- Added new figure: EspecificacionesML_Final_eng.png.
- Updated author name from J. Gonzalez to J. M. Gonzalez in the manuscript.
- Modified WileyNJDv5.cls to conditionally load packages and provide commands if not found, improving compatibility and avoiding errors related to missing packages.

- Introduced a comprehensive manuscript detailing the optimization framework for buckling-delayed shear-link dampers.
- Included sections on introduction, device description, FEM calibration, surrogate modeling, optimization algorithm, and adaptive validation.
- Implemented a damage-aware objective function and outlined the methodology for generating high-fidelity FEM datasets.
- Discussed the predictive performance of supervised ML models and RBF surrogates, along with planned numerical assessments.
- Added author contributions, acknowledgments, financial disclosures, and conflict of interest statements.

- Reorganized import statements in `ml_surrogate_train.py`, `rbf_model.py`, `rbf_optimization_de.py`, `rbf_surrogate_train.py` for clarity.
- Simplified dictionary and list comprehensions for better readability.
- Updated print statements for consistent formatting.
- Enhanced function definitions with clearer parameter formatting.
- Added a new `pyproject.toml` file for Ruff configuration to enforce code style.
- Removed unnecessary comments and improved inline documentation.

Update .gitignore to include additional manuscript auxiliary files and refine abstract in manuscript

- Removed DOI from the Khatibinia2019 entry in the bibliography.
- Added a .gitignore file to exclude manuscript auxiliary files, byte-compiled files, plot outputs, and GiD results from version control.

- Updated bibliography references in Manuscript.fdb_latexmk to reflect new timestamps.
- Adjusted log file timestamps and fixed warnings related to document class naming.
- Removed an unnumbered list section from Manuscript.tex for clarity.
- Corrected the document class name in WileyNJDv5.cls to ensure consistency.
- Updated binary files: Manuscript.pdf and Manuscript.synctex.gz to reflect recent changes.

- Added a new function `load_tfdmap` to load TFDMap data from files, ensuring proper error handling for missing or malformed data.
- Updated the hysteretic curves processing script to include TFDMap data in the point-level DataFrame, maintaining alignment with case folders.
- Enhanced the prediction script to handle multiple target columns dynamically, improving flexibility for model training and evaluation.
- Modified caching mechanism for window sizes to use a tuple key for better organization and retrieval.
- Improved logging and error messages for better debugging and user feedback.
- Updated the run script to ensure consistent execution of prediction tasks with specified parameters.

- 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.

- Added a new article by Elgammal and Ali (2024) on hysteretic restoring force models for shear link dampers to the bibliography.
- Updated the bibliography file (Manuscript.bbl) to reflect the new entry and adjusted the entry count in the log file (Manuscript.blg).
- Modified the manuscript text to include a new subsection discussing the added reference.
- Updated the .fdb_latexmk and .fls files to reflect changes in the bibliography and manuscript.
- Adjusted the log file to correct line numbers and warnings related to the new content.

refactor(predict): Enhance stability and performance in LSTM training with improved DataLoader settings and caching mechanisms

- Reduced hyperparameter optimization trials
- Lowered max epochs for tuning and final training
- Decreased early stopping patience
- Enabled parallel data loading with num_workers
- Refined hyperparameter search space for models
- Simplified batch size logic for CUDA

- Introduced a new thickness data file `widthsH60_B34.txt` for hysteretic curves.
- Updated the path for thickness data in `hysteretic_curves.py` to include the base and width parameters.
- Modified the loop structure in `hysteretic_curves.py` to ensure thickness data aligns with case folders.
- Enhanced the prediction script `predict_hysteretic_curves.py` with cross-validation strategies and improved training logic.
- Implemented Leave-One-Out and K-Fold cross-validation based on the number of training cases.
- Adjusted model training to handle full training pool without validation and added detailed logging for trials.
- Improved memory management and error handling during training and validation processes.

- Implemented LSTM model with enhanced training features including mixed precision, early stopping, and validation via DataLoader.
- Introduced a new 1D Temporal Convolutional Network (TCN) model for predicting hysteretic curves.
- Added functionality for creating sliding windows from the dataset for both training and testing.
- Integrated scaling for features and targets using StandardScaler.
- Enhanced data handling with explicit cleanup and memory management for GPU.
- Updated main function to include model training and prediction for both LSTM and TCN.
- Saved predictions to CSV files for further analysis.

- Introduced `plot_data_hysteretic_curves.py` for visualizing envelope curves, energy degradation, and stiffness degradation from cycle-level data.
- Implemented `predict_hysteretic_curves.py` to create a sliding window dataset for training an LSTM model to predict hysteretic force-displacement curves.
- Enhanced the manuscript with updated references to force-displacement relationships and clarified the role of LSTM models in the optimization framework.
- Updated manuscript files to reflect changes in the document structure and content.

feat: Generate and store new machine learning and RBF models, cross-validation results, and optimization reports for width optimization, and remove outdated model and report files.