A physics and data co-driven surrogate modeling method for high-dimensional rare event simulation

Abstract

This paper presents a physics and data co-driven surrogate modeling method for efficient rare event simulation of civil and mechanical systems with high-dimensional input uncertainties. The method fuses interpretable low-fidelity physical models with data-driven error corrections. The hypothesis is that a well-designed and well-trained simplified physical model can preserve salient features of the original model, while data-fitting techniques can fill the remaining gaps between the surrogate and original model predictions. The coupled physics-data-driven surrogate model is adaptively trained using active learning, aiming to achieve a high correlation and small bias between the surrogate and original model responses in the critical parametric region of a rare event. A final importance sampling step is introduced to correct the surrogate model-based probability estimations. Static and dynamic problems with input uncertainties modeled by random field and stochastic process are studied to demonstrate the proposed method.

References in corpus (17)

• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Reliability-based design optimization using kriging surrogates and subset simulation
• An active-learning algorithm that combines sparse polynomial chaos expansions and bootstrap for structural reliability analysis
• Active learning for structural reliability: survey, general framework and benchmark
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• Data-driven polynomial chaos expansion for machine learning regression
• Nonlinear Model Order Reduction via Lifting Transformations and Proper Orthogonal Decomposition
• Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold
• Active Learning with Multifidelity Modeling for Efficient Rare Event Simulation
• Surrogate assisted active subspace and active subspace assisted surrogate -- A new paradigm for high dimensional structural reliability analysis
• Adaptive active subspace-based metamodeling for high-dimensional reliability analysis
• Relaxation-based importance sampling for structural reliability analysis
• Multifidelity probability estimation via fusion of estimators
• Optimized Equivalent Linearization for Random Vibration
• Uncertainty quantification for complex systems with very high dimensional response using Grassmann manifold variations
• Mutual Information for Explainable Deep Learning of Multiscale Systems
• Nonlinear input feature reduction for data-based physical modeling

Cited by in corpus (2)

• Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification
• A composition of simplified physics-based model with neural operator for trajectory-level seismic response predictions of structural systems