Latent Space-based Stochastic Model Updating

TL;DR

This paper introduces a latent space-based stochastic model updating method that uses variational autoencoders to efficiently quantify uncertainties in engineering systems with limited data, outperforming existing approaches.

Contribution

The paper presents a novel latent space approach for stochastic model updating that reduces data needs and computational costs using a variational autoencoder framework.

Findings

Demonstrated superior accuracy and efficiency over existing methods in numerical experiments.

Validated applicability to time-series data with NASA UQ Challenge 2019.

Effective uncertainty quantification with fewer data and high-dimensional data handling.

Abstract

Model updating of engineering systems inevitably involves handling both aleatory or inherent randomness and epistemic uncertainties or uncertainities arising from a lack of knowledge or information about the system. Addressing these uncertainties poses significant challenges, particularly when data and simulations are limited. This study proposes a novel latent space-based method for stochastic model updating that leverages limited data to effectively quantify uncertainties in engineering applications. By extending the latent space-based approach to multiobservation and multisimulation frameworks, the proposed method circumvents the need for probability estimations at each iteration of MCMC, relying instead on an amortized probabilistic model trained using a variational autoencoder (VAE). This method was validated through numerical experiments on a two-degree-of-freedom shear spring model, demonstrating superior efficiency and accuracy compared to existing methods in terms of uncertainty quantification (UQ) metrics, such as Bhattacharyya and Euclidean distances. Moreover, the applicability of the method to time-series data was verified using the model calibration problem of the NASA UQ Challenge 2019. The results underscore the potential of the latent space-based method in practical engineering applications, providing a robust framework for uncertainty quantification with fewer data requirements, and demonstrating its effectiveness in handling high-dimensional data.