A composition of simplified physics-based model with neural operator for trajectory-level seismic response predictions of structural systems

2025-06-12

AI Summary

High-fidelity nonlinear time-history analysis (NTHA) for seismic risk assessment incurs prohibitive computational costs. Method: This paper proposes a physics-informed Fourier Neural Operator (FNO) compositional learning framework to efficiently and accurately predict trajectory-level nonlinear structural responses. It first generates coarse-grained initial response estimates using a simplified physics-based model—incorporating modal reduction and solver relaxation—and then employs FNO to learn the residual correction, mitigating hysteresis and path-dependency errors. A linear post-processing module quantifies prediction uncertainty. Contribution/Results: We introduce the first three-stage paradigm integrating physics modeling, data-driven residual correction, and uncertainty quantification. Validation across three representative structural types demonstrates substantial improvements over baseline models: notably enhanced accuracy under limited training data and two orders-of-magnitude reduction in computational cost.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Structured Learning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate prediction of nonlinear structural responses is essential for earthquake risk assessment and management. While high-fidelity nonlinear time history analysis provides the most comprehensive and accurate representation of the responses, it becomes computationally prohibitive for complex structural system models and repeated simulations under varying ground motions. To address this challenge, we propose a composite learning framework that integrates simplified physics-based models with a Fourier neural operator to enable efficient and accurate trajectory-level seismic response prediction. In the proposed architecture, a simplified physics-based model, obtained from techniques such as linearization, modal reduction, or solver relaxation, serves as a preprocessing operator to generate structural response trajectories that capture coarse dynamic characteristics. A neural operator is then trained to correct the discrepancy between these initial approximations and the true nonlinear responses, allowing the composite model to capture hysteretic and path-dependent behaviors. Additionally, a linear regression-based postprocessing scheme is introduced to further refine predictions and quantify associated uncertainty with negligible additional computational effort. The proposed approach is validated on three representative structural systems subjected to synthetic or recorded ground motions. Results show that the proposed approach consistently improves prediction accuracy over baseline models, particularly in data-scarce regimes. These findings demonstrate the potential of physics-guided operator learning for reliable and data-efficient modeling of nonlinear structural seismic responses.

Problem

• Predict nonlinear seismic structural responses efficiently
• Combine physics models with neural operators for accuracy
• Improve prediction in data-scarce earthquake scenarios

Innovation

• Combines physics-based models with neural operators
• Uses Fourier neural operator for response correction
• Introduces linear regression for uncertainty quantification