Motor bearing fault prediction based on grasshopper optimized Bi-LSTM network

被引：0
|
作者：
Yu F. [1 ]
Fan Q.-C. [1 ]
Xuan M. [1 ]
机构：
[1] School of Electrical Engineering, Naval University of Engineering, Wuhan
来源：
Dianji yu Kongzhi Xuebao/Electric Machines and Control | 2022年 / 26卷 / 06期
关键词：
bidirectional long short-term memory; complementary ensemble empirical mode decomposition; failure prediction; grasshopper optimization algorithm; motor bearings; singular value energy;
D O I：
10.15938/j.emc.2022.06.002
中图分类号：
学科分类号：
摘要：
In order to effectively predict motor bearing faults under complex operating conditions, a motor bearing fault prediction method using a grasshopper optimization algorithm ( GOA) optimized bidirectional long short-term memory ( Bi-LSTM ) network is proposed. Firstly, the vibration signal of the motor bearing was decomposed by the complementary ensemble empirical mode decomposition ( CEEMD) algorithm to obtain multiple sets of intrinsic mode functions (IMF) that can characterize the vibration, calculate the singular value energy of each IMF component, and form the singular value energy spectrum as the performance degradation index of the motor bearing. Secondly, GOA was used to iteratively seek the optimization of multiple hyperparameters of the Bi-LSTM network to improve the prediction accuracy and convergence speed of the model, so as to obtain an optimal set of hyperparameter combinations. Finally, the optimized Bi-LSTM network was used to realize the fault prediction of motor bearings. The experimental results show that compared with other prediction models, the model established in this paper has higher prediction accuracy and stronger robustness, which can provide theoretical support for maintenance work in time and has certain research value and engineering significance. © 2022 Editorial Department of Electric Machines and Control. All rights reserved.
引用
收藏
页码：9 / 17
页数：8
相关论文
共 18 条
  • [1] AN Guoqing, QIN Cheng, GUO Liwei, Et al., Kurtosis filter is used to extraet early fault feature of motor bearing, Electric Machines and Control, 18, 6, (2014)
  • [2] ZHANG R, FANG Y, ZHOU Z., Fault diagnosis of rolling bearing based on K-SVD dictionary learning algorithm and BP neural net-work, The 2019 International Conference, pp. 341-345, (2019)
  • [3] QIAN Y, HU S, YAN R., Bearing performance degradation evaluation using recurrence quantification analysis and auto-regression model, 2013 IEEE International Instrumentation and Measurement Technology Conference, pp. 1713-1716, (2013)
  • [4] DONG W, TSUI K U., Two novel mixed effects models for prognostics of rolling element bearings, Mechanical Systems and Signal Processing, 34, 99, (2018)
  • [5] NIU Qiming, UIU Feng, ZHANG Yihuang, PHM based health prediction of rolling bearing of high-speed railway traction motor : J], Journal of the China Railway Society, 42, 7, (2020)
  • [6] XU Jiya, WANG Yan, YAN Dahu, Et al., SVM prediction of rolling bearing performance degradation based on KPCA and information granulation, Journal of System Simulation, 30, 6, (2018)
  • [7] ZHAO Jianpeng, ZHOU Jun, Research on state prediction of rotating machinery based on long and short time memory network, Noise and Vibration Control, 37, 4, (2017)
  • [8] ZHANG B, ZHANG S, LI W., Bearing performance degradation assessment using long short-term memory recurrent network, Computers in Industry, 106, (2019)
  • [9] YEH J R, SHIEH J S, HUANG N E., Complementary ensemble empirical mode decomposition : a novel noise enhanced data analysis method [J], Advances in Adaptive Data Analysis, 2, 2, (2010)
  • [10] LI Zhijun, ZHANG Hongpeng, WANG Yanan, Et al., A novel wavelet threshold de-noising harmonic detection method based on permutation entropy-CEEMD decomposition, Electric Machines and Control, 24, 12, (2020)
12