Uncertainty-assisted deep vision structural health monitoring

Computer vision leveraging deep learning has achieved significant success in the last decade. Despite the promising performance of the existing deep vision inspection models, the extent of models' reliability remains unknown. Structural health monitoring (SHM) is a crucial task for the safety and sustainability of structures, and thus, prediction mistakes can have fatal outcomes. In this paper, we use Bayesian inference for deep vision SHM models where uncertainty can be quantified using the Monte Carlo dropout sampling. Three independent case studies for cracks, local damage identification, and bridge component detection are investigated using Bayesian inference. Aside from better prediction results, the two uncertainty metrics, variations in softmax probability and entropy, are shown to have good correlations with misclassifications. However, modifying the decision or triggering human intervention can be challenging based on raw uncertainty outputs. Therefore, the concept of surrogate models is proposed to develop the models for uncertainty-assisted segmentation and prediction quality tagging. The former refines the segmentation mask and the latter is used to trigger human interventions. The proposed framework can be applied to future deep vision SHM frameworks to incorporate model uncertainty in the inspection processes.

Automated summary

This paper explores the use of deep learning and Bayesian inference in structural health monitoring, addressing prediction uncertainty and conducting three case studies. The uncertainty metrics show correlations with misclassifications, and a surrogate model is proposed to trigger human interventions.