Interpretability of deep convolutional neural networks on rolling bearing fault diagnosis

Abstract

Abstract Despite the rapid development of deep learning-based intelligent fault diagnosis methods on rotating machinery, the data-driven approach generally remains a ‘black box’ to researchers, and its internal mechanism has not been sufficiently understood. The weak interpretability significantly impedes further development and application of the effective deep neural network-based methods. This paper contributes to understanding the mechanical signal processing of deep learning on the fault diagnosis problems. The diagnostic knowledge learned by the deep neural network is visualized using the neuron activation maximization and the saliency map methods. The discriminative features of different machine health conditions are intuitively observed. The relationship between the data-driven methods and the well-established conventional fault diagnosis knowledge is confirmed by the experimental investigations on two datasets. The results of this study can benefit researchers on understanding the complex neural networks, and increase the reliability of the data-driven fault diagnosis model in real engineering cases.