Deep Learning-Based Explainable Fault Diagnosis Model With an Individually Grouped 1-D Convolution for Three-Axis Vibration Signals

• Published in: IEEE transactions on industrial informatics 2022-12, Vol.18 (12), p.8807-8817
• Main Authors: Kim, Min Su, Yun, Jong Pil, Park, PooGyeon
• Format: Article
• Language: English
• Subjects: Convolution; Convolutional neural network (CNN); Criteria; Data models; Data visualization; Deep learning; end-to-end model; Fault diagnosis; Feature extraction; Feature maps; Frequency domain analysis; Model accuracy; Rotary machines; Termites; Three axis; Vibration measurement; Vibrations; Visualization
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2022.3147828

This article proposes a new end-to-end deep learning model for fault diagnosis using three-axis vibration signals measured from facilities. The three-axis vibration signals measured in the time domain are used without domain transformations to train the end-to-end model. The proposed model is designed to effectively extract feature maps of each X -, Y -, and Z -axis individually from the three-axis vibration signals using a grouped 1-D convolution. The feature maps extracted from each axis are composed of specific frequencies of each axis. Accordingly, the proposed model classifies faults based on the frequency characteristics of each axis. In addition, this article proposes a method to visualize the decision criteria of the proposed model in the frequency domain. Using the proposed model and the proposed visualization method, it is possible to grasp the degree to which specific frequencies of each X -, Y -, and Z -axis affect the decision criteria of the proposed model. The experiment is conducted by applying the proposed model to an open dataset with three-axis vibration signals measured from a rotary machine. Experimental results demonstrate that the proposed model achieves high accuracy and provides the explainability in each X -, Y -, and Z -axis using the visualized decision criteria in the frequency domain.