A Bearing Fault Diagnosis Model Based on a Simplified Wide Convolutional Neural Network and Random Forrest

Bearings play a crucial role in the complex mechanical systems of ships, and their operational status is closely related to vibration signals. Therefore, analyzing bearing signals plays an important role in the field of fault diagnosis. In order to solve the problems of low accuracy and slow response speed in fault diagnosis through vibration signals at mixed speeds, this paper introduces an improved Simple Window Deep Convolutional Neural Network with Random Forest (SWDCNN-RF) model on traditional Wide Convolutional Neural Network (WDCNN). It was verified through the publicly available dataset of ball bearings from Western Reserve University in the United States. It was found that the improved model increased speed by 38.51% and accuracy from 97.5% to 99.6% at epoch = 50, and also achieved faster convergence and smaller fluctuations during training. This study is of great significance for determining the occurrence time and type of bearing faults, and provides criteria for reliability evaluation and fault diagnosis of equipment using bearings.