Fault diagnosis of rolling bearing based on back propagation neural network optimized by cuckoo search algorithm

• Published in: Multimedia tools and applications Vol. 81; no. 2; pp. 1567 - 1587
• Main Authors: Xiao, Maohua, Liao, Yabing, Bartos, Petr, Filip, Martin, Geng, Guosheng, Jiang, Ziwei
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2022; Springer Nature B.V
• Subjects: Algorithms; Back propagation; Back propagation networks; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Decomposition; Energy value; Fault diagnosis; Fault location; Feature extraction; Frequencies; Multimedia Information Systems; Neural networks; Propagation; Roller bearings; Search algorithms; Special Purpose and Application-Based Systems; Wave propagation; Fault diagnosis; BP neural network; Cuckoo search algorithm; Wavelet packet decomposition; Rolling bearing
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-021-11556-x

In order to improve the accuracy of rolling bearing fault diagnosis in mechanical equipment, a new fault diagnosis method based on back propagation neural network optimized by cuckoo search algorithm is proposed. This method use the global search ability of the cuckoo search algorithm to constantly search for the best weights and thresholds, and then give it to the back propagation neural network. In this paper, wavelet packet decomposition is used for feature extraction of vibration signals. The energy values of different frequency bands are obtained through wavelet packet decomposition, and they are input as feature vectors into optimized back propagation neural network to identify different fault types of rolling bearings. Through the three sets of simulation comparison experiments of Matlab, the experimental results show that, Under the same conditions, compared with the other five models, the proposed back propagation neural network optimized by cuckoo search algorithm has the least number of training iterations and the highest diagnostic accuracy rate. And in the complex classification experiment with the same fault location but different bearing diameters, the fault recognition correct rate of the back propagation neural network optimized by cuckoo search algorithm is 96.25%.