Domain Adaptation for Structural Fault Detection under Model Uncertainty

Abstract

In the last decade, the interest in machine learning (ML) has grown significantly within the structural health monitoring (SHM) community. Traditional supervised ML approaches for detecting faults assume that the training and test data come from similar distributions. However, in real-world applications, the statistical properties of these datasets may diverge from each other in time, leading to a deterioration in the prediction performance of the ML. This paper proposes a domain adaptation approach for ML-based damage detection and localization problems to treat such issues where the classifier has access to the labeled training (source) and unlabeled test (target) data, but the source and target domains are statistically different. The proposed domain adaptation method seeks to form a feature space that minimizes the discrepancy between the source and target domain implementing a domain-adversarial neural network. To evaluate the performance, we present two case studies where we design a neural network model for classifying the health condition of a variety of systems. The effectiveness of the domain adaptation is shown by computing the classification accuracy of the unlabeled target data with and without domain adaptation. Furthermore, the performance gain of the domain adaptation over well-known transfer knowledge approaches such as Transfer Component Analysis and Joint Distribution Adaptation is also demonstrated. Overall, the results demonstrate that domain adaption is a valid approach for damage detection applications where access to labeled experimental data is limited.