Bayesian Model Updating of Multiscale Simulations Informing Corrosion Prognostics Using Conditional Invertible Neural Networks

Abstract

Physics-based multiscale corrosion simulation plays a vital role in predicting the evolution of pitting corrosion on large civil infrastructure, contributing to a model-informed structural health monitoring strategy for risk-based asset health management. The physics-based analysis, however, may not accurately reflect the underlying true physics due to various uncertainty sources and needs to be updated using Bayesian inference methods based on observations to make the prediction closer to field observations. However, traditional Bayesian inference requires the evaluation of a likelihood function, which is often unavailable due to the complex model architecture and various surrogate models used in the analysis. Therefore, likelihood-free inference approaches are required for the updating of the multiscale corrosion simulation models. This paper meets this need by proposing a conditional invertible neural network (cINN)-based Bayesian model updating method for an existing corrosion simulation model. We first train a cINN model based on simulated observations generated from a high-fidelity forward corrosion analysis model. A convolutional neural network-based feature extraction algorithm is then employed to extract key features from corrosion images. After that, the extracted corrosion features are used as inputs of the cINN model to directly obtain posterior distributions of uncertain corrosion model parameters without evaluating the likelihood function. A case study of a miter gate structure is used to demonstrate the proposed approach. The results show that the proposed cINN-based model updating approach can provide more accurate inference results with a reduced computational cost in comparison to the classical approximate Bayesian computation (ABC) approach.