Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applications
This work addresses the need for efficient and uncertainty-aware models in Structural Health Monitoring, representing an incremental improvement by applying existing conditional variational autoencoders to this domain.
The paper tackled the problem of high computational cost in Structural Health Monitoring by proposing a conditional deep generative model as a surrogate for reconstructing spatial field solutions with quantified uncertainty, achieving high reconstruction accuracy compared to reference Finite Element solutions.
In recent years, increasingly complex computational models are being built to describe physical systems which has led to increased use of surrogate models to reduce computational cost. In problems related to Structural Health Monitoring (SHM), models capable of both handling high-dimensional data and quantifying uncertainty are required. In this work, our goal is to propose a conditional deep generative model as a surrogate aimed at such applications and high-dimensional stochastic structural simulations in general. To that end, a conditional variational autoencoder (CVAE) utilizing convolutional neural networks (CNNs) is employed to obtain reconstructions of spatially ordered structural response quantities for structural elements that are subjected to stochastic loading. Two numerical examples, inspired by potential SHM applications, are utilized to demonstrate the performance of the surrogate. The model is able to achieve high reconstruction accuracy compared to the reference Finite Element (FE) solutions, while at the same time successfully encoding the load uncertainty.