Multi-Channel Deep Pulse-Coupled Net: A Novel Bearing Fault Diagnosis Framework

Abstract

Bearings are a critical part of various industrial equipment. Existing bearing fault detection methods face challenges such as complicated data preprocessing, difficulty in analysing time series data, and inability to learn multi-dimensional features, resulting in insufficient accuracy. To address these issues, this study proposes a novel bearing fault diagnosis model called multi-channel deep pulse-coupled net (MC-DPCN) inspired by the mechanisms of image processing in the primary visual cortex of the brain. Initially, the data are transformed into greyscale spectrograms, allowing the model to handle time series data effectively. The method introduces a convolutional coupling mechanism between multiple channels, enabling the framework can learn the features on all channels well. This study conducted experiments using the bearing fault dataset from Case Western Reserve University. On this dataset, a 6-channel (adjustable to specific tasks) MC-DPCN was utilized to analyse one normal class and three fault classes. Compared to state-of-the-art bearing fault diagnosis methods, our model demonstrates one of the highest diagnostic accuracies. This method achieved an accuracy of 99.96% in normal vs. fault discrimination and 99.89% in fault type diagnosis (average result of ten-fold cross-validation).