Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network

Abstract

To address the problems of poor model diagnosis and poor noise immunity caused by inconsistent distribution of bearing fault features and difficulty in feature extraction in multi-condition environments, a multi-condition bearing fault diagnosis method based on a channel segmentation improved residual network is proposed. A channel segmentation mechanism is designed for channel information highlighting, by selecting one channel of the three-channel feature image as the main operation channel, stacking it with the secondary operation channel after convolution, and then inputting the stacked feature map into the convolutional neural network to realize the extraction and classification of bearing fault features. Four different network models were selected to verify the diagnostic performance of the channel segmentation mechanism on the Case Western Reserve University bearing dataset and the Jiangnan University bearing dataset, and noise immunity experiments were conducted on the Jiangnan University bearing dataset. The experiments show that the proposed diagnostic model on the Case Western Reserve bearing dataset has a minimum improvement of 6.8% compared to the comparison method for multi-case bearing fault diagnosis experiments. In terms of noise immunity, the diagnostic accuracy of the fault diagnosis model with the addition of the channel cut-off mechanism improves the diagnostic accuracy of the noisy data by an average of 4.3% compared to that without the addition. The proposed model still has excellent diagnostic performance when diagnosing variable speed bearing faults.