An intelligent rolling bearing fault diagnosis method of cnn based on mnist database of handwritten digits

Abstract

An intelligent rolling bearing fault diagnosis method of convolutional neural network (CNN) based on MNIST database of handwritten digits was proposed. The equal length interception of the vibration signal of the rolling bearing was performed, and the intercepted signal was reconstructed into two-dimensional pictures in sequence. In order to ensure the authentic and effective restoration of the fault characteristics of the vibration signal, no preprocessing was performed on the vibration signal, and direct interception was performed to reconstruct the two-dimensional pictures. To realize intelligent fault diagnosis of rolling bearings, the failure pictures were input as feature maps, and a CNN classifier model based on MNIST database of handwritten digits was established. In order to verify the validity of the rolling bearing fault diagnosis method proposed in this paper, the open-end rolling bearing data from Case Western Reserve University and the rolling bearing data collected under laboratory conditions were experimentally verified respectively. The experimental results were then compared with the traditional BP neural network, BP neural network optimized by particle swarm optimization, wavelet energy entropy support vector machine optimized by particle swarm optimization, support vector machine based on variational mode decomposition mutual approximation entropy and BP neural network optimized by genetic algorithm on the effectiveness of fault pattern recognition. The results show that this method can identify effectively the fault type of the rolling bearing, and the diagnosis efficiency is higher. The method has strong feature extraction and recognition capabilities.