Physics-Informed Machine Learning for Seismic Response Prediction OF Nonlinear Steel Moment Resisting Frame Structures
This work addresses the problem of high computational costs and data dependency in structural engineering for seismic prediction, offering an incremental improvement by combining physics with machine learning.
The paper tackled the challenge of predicting seismic responses for nonlinear steel structures by introducing a physics-informed machine learning method that integrates physical laws into neural networks, resulting in a metamodel that outperforms existing physics-guided and non-physics data-driven networks in handling complex data.
There is growing interest in using machine learning (ML) methods for structural metamodeling due to the substantial computational cost of traditional simulations. Purely data-driven strategies often face limitations in model robustness, interpretability, and dependency on extensive data. To address these challenges, this paper introduces a novel physics-informed machine learning (PiML) method that integrates scientific principles and physical laws into deep neural networks to model seismic responses of nonlinear structures. The approach constrains the ML model's solution space within known physical bounds through three main features: dimensionality reduction via combined model order reduction and wavelet analysis, long short-term memory (LSTM) networks, and Newton's second law. Dimensionality reduction addresses structural systems' redundancy and boosts efficiency while extracting essential features through wavelet analysis. LSTM networks capture temporal dependencies for accurate time-series predictions. Manipulating the equation of motion helps learn system nonlinearities and confines solutions within physically interpretable results. These attributes allow for model training with sparse data, enhancing accuracy, interpretability, and robustness. Furthermore, a dataset of archetype steel moment resistant frames under seismic loading, available in the DesignSafe-CI Database [1], is considered for evaluation. The resulting metamodel handles complex data better than existing physics-guided LSTM models and outperforms other non-physics data-driven networks.