Aero-engine Bearing Fault Diagnosis Based on MGA-BP Neural Network

被引：0
|
作者：
Pi J. [1 ]
Liu P. [2 ]
Ma S. [2 ]
Liang C. [2 ]
Meng L. [1 ]
Wang L. [3 ]
机构：
[1] General Aviation College, Civil Aviation University of China, Tianjin
[2] College of Aeronautical Engineering, Civil Aviation University of China, Tianjin
[3] Motoren-und Turbinen-Union(MTU) Maintenance Zhuhai Co., Ltd., Zhuhai
来源：
Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis | 2020年 / 40卷 / 02期
关键词：
Aero-engine; Bearing fault diagnosis; BP neural network; Genetic algorithm; Output mode; Sample proportion;
D O I：
10.16450/j.cnki.issn.1004-6801.2020.02.024
中图分类号：
学科分类号：
摘要：
The back propagation(BP)neural network optimized by modified genetic algorithm(MGA-BP) is proposed to improve accuracy of aero-engine bearing fault diagnosis. The traditional genetic algorithm optimized by using the fixed individual selection probability, trigonometric function and Gauss mutation operation to solve defect problem of genetic algorithm. The BP neural network weight and threshold is optimized by MGA-BP. Four cases of rolling bearing normal, inner ring fault, out ring fault and ball fault are diagnosed by using the optimized BP neural network. The influence of network output mode and diagnostic sample proportion on the accuracy of diagnosis is fully considered. In order to verify the effectiveness of MGA-BP in the bearing fault diagnosis, the BP neural network is optimized by other improve genetic algorithm as a contrast algorithm. The comprehensive comparison results show that MGA-BP can better adapt to different output modes and different sample proportions than other algorithms in this paper. And its noise immunity, diagnosis accuracy, convergence speed and error convergence value are all better than other improved genetic algorithm. In consequence, MGA-BP is more suitable for bearing fault diagnosis. © 2020, Editorial Department of JVMD. All right reserved.
引用
收藏
页码：381 / 388
页数：7
相关论文
共 22 条
  • [1] Roller bearing fault diagnosis method based on LMD-CM-PCA, Journal of Vibration, Measurement & Diagnosis, 37, 2, pp. 249-255, (2017)
  • [2] Pi J., Huang J., Aero-engine fault diagnosis based on IPSO-Elman neural network, Journal of Aerospace Power, 32, 12, pp. 3031-3038, (2017)
  • [3] Desavale R.G., Kanai R.A., Chavan S.P., Et al., Vibration characteristics diagnosis of roller bearing using the new empirical model, Journal of Tribology, 138, 1, (2016)
  • [4] Zhao Z., Yang S., Sample entropy-base roller bearing fault diagnosis method, Journal of Vibration and Shock, 31, 6, pp. 136-140, (2012)
  • [5] Xiang D., Cen J., Method of roller bearing fault diagnosis based on feature fusion of EMD entropy, Journal of Aerospace Power, 30, 5, pp. 1149-1155, (2015)
  • [6] Wan S., Tong H., Dong B., Bearing fault diagnosis using wavelet packet transform and least square support vector machines, Journal of Vibration, Measurement & Diagnosis, 30, 2, pp. 149-152, (2010)
  • [7] Zheng H., Zhou L., Yang H., Rolling bearing fault diagnosis based on wavelet packet analysis and multi kernel learning, Journal of Aerospace Power, 30, 12, pp. 3035-3042, (2015)
  • [8] Li B., Chow M.Y., Tipsuwan Y., Et al., Neural-network-based motor rolling bearing fault diagnosis, IEEE Transactions on Industrial Electronics, 47, 5, pp. 1060-1069, (2000)
  • [9] Kanai R.A., Desavale R.G., Chavan S.P., Experimental-based fault diagnosis of rolling bearings using artificial neural network, Journal of Tribology, 138, 3, (2016)
  • [10] Pi J., Huang J.B., Ma L., Aero-engine fault diagnosis using optimized Elman neural network, Mathematical Problems in Engineering, 2017, 9, pp. 1-8, (2017)
123