Robust and Explainable Fault Diagnosis With Power-Perturbation-Based Decision Boundary Analysis of Deep Learning Models

Robustness of neural network models is important in fault diagnosis (FD) because uncertainty in operating conditions varies the power spectral densities of vibration data; however, it is unknown to users due to the limited explainability of the models. This article proposes an FD framework with a power-perturbation-based decision boundary analysis (POBA) to explain the decision boundaries of vibration classification models. In the POBA, perturbed data are obtained from training data by power perturbation on frequency bands centering on dominant class-discriminative frequencies. The decision boundary of a model is then evaluated and visualized to users by testing the model on the perturbed data. Furthermore, the decision boundary information can be used to define a robustness score per class, and a robust model can be obtained by ensembling trained models using their robustness score per class. Demonstration using two vibration datasets verifies the explainability and robustness of the proposed FD framework.