Fault Detection Method for Rolling Bearings of Rotating Electrical Machines Based on CEEMDAN⁃SPSO⁃ELM

doi:10.3969/j.issn.1672-6952.2022.01.015

Abstract

Abstract:

In view of the unstable and nonlinear characteristics of the rolling bearing vibration signal of rotating electrical machines, the traditional time?frequency analysis method and wavelet packet decomposition method have energy leakage and poor adaptive ability in the signal decomposition process, and the EMD decomposition method has modal aliasing and other problems. In order to improve the fault diagnosis accuracy of rolling bearings, CEEMDAN combined with energy moment method is proposed to extract the original vibration signal features. The weight and offset of ELM hidden layer are optimized by SPSO algorithm, and the CEEMDAN?SPSO?ELM method is used to analyze and diagnose single and multiple damage faults of rolling bearings.The effectiveness of the algorithm and the improvement of diagnosis accuracy are verified by comparative experiments.

Key words: Rotating electric machine rolling bearing, Fault diagnosis, CEMMDAN, ELM, SPSO

摘要：

由于旋转电机滚动轴承振动信号存在不平稳、非线性的特征，传统时频分析法、小波分解法存在在信号分解过程中能量泄露、自适应能力差的问题，经验模态分解（EMD）法存在模态混叠等问题。提出一种基于噪声自适应完备总体平均经验模态分解方法（CEEMDAN），利用具有麻雀捕食预警机制的粒子群算法（SPSO）优化极限学习机神经网络（ELM）的CEEMDAN?SPSO?ELM算法。利用所提方法对滚动轴承单一与多种损伤故障进行分析诊断，结果表明，所提算法具有有效性及诊断准确性。

关键词: 旋转电机滚动轴承, 故障诊断, CEMMDAN, ELM, SPSO

CLC Number:

TH17

Shaolou Song, Lü Liang, Xinming Liu. Fault Detection Method for Rolling Bearings of Rotating Electrical Machines Based on CEEMDAN⁃SPSO⁃ELM[J]. Journal of Liaoning Petrochemical University, 2022, 42(1): 86-91.

宋绍楼, 吕亮, 刘昕明. 基于CEEMDAN⁃SPSO⁃ELM的旋转电机滚动轴承故障检测方法[J]. 辽宁石油化工大学学报, 2022, 42(1): 86-91.

Figures/Tables 7

References 14

1	Wang H， Chen J， Zhou Y， et al. Early fault diagnosis of rolling bearing based on noise⁃assisted signal feature enhancement and stochastic resonance for intelligent manufacturing［J］. The International Journal of Advanced Manufacturing Technology， 2020，107：1017⁃1023．
2	Li C， Zheng J， Pan H， et al. Refined composite multivariate multiscale dispersion entropy and its application to fault diagnosis of rolling bearing［J］. IEEE Access，2019，7：47663⁃47673．
3	Zhang L P，Liu H M，Lu C. Fault diagnosis technology of rolling bearing based on LMD and BP neural network［C］// 2016 12th World Congress on Intelligent Control and Automation （WCICA）. Guilin ：IEEE，2016.
4	Gunerkar R S， Jalan A K， Belgamwar S U. Fault diagnosis of rolling element bearing based on artificial neural network［J］. Journal of Mechanical Science and Technology， 2019， 33（2）：505⁃511.
5	Li Y， Zhang W， Xiong Q， et al. A rolling bearing fault diagnosis strategy based on improved multiscale permutation entropy and least squares SVM［J］. Journal of Mechanical Science and Technology， 2017， 31（6）：2711⁃2722.
6	Ma J， Wu J D， Fan Y G， et al. Fault diagnosis of rolling bearing based on the PSO⁃SVM of the mixed⁃feature［J］. Applied Mechanics & Materials， 2013， 380⁃384：895⁃901.
7	谢国民，王灿祥，佟莹.采煤机电动机故障诊断专家系统的研究与应用［J］.信息与控制，2013，42（3）：358⁃363.
8	吕维宗，王海瑞，舒捷.基于谐波小波包和IAGA⁃SVM的滚动轴承故障诊断［J］.计算机应用与软件，2019，36（10）：30⁃38.
9	张旭.基于加权排列熵和ELM的通风机轴承故障诊断研究［D］.徐州：中国矿业大学，2020.
10	皮骏，马圣，杜旭博，等.基于BQGA⁃ELM网络在滚动轴承故障诊断中的应用研究［J］.振动与冲击，2019，38（18）：192⁃
200
11	卓仁雄.基于CEEMDAN和GWO⁃SVM的电机滚动轴承故障诊断［D］. 衡阳：南华大学，2018.
12	尤田，张威，葛琳琳.基于GA⁃PSO算法焊接机器人路径规划研究［J］.辽宁石油化工大学学报，2018，38（2）：85⁃89.
13	唐玲玲，缪希仁，庄胜斌.PSO⁃ELM在低压系统短路电流峰值预测中的应用［J］.福州大学学报（自然科学版），2020，48（4）：471⁃478.
14	杨博雯，钱伟懿.粒子群优化算法中惯性权重改进策略综述［J］.渤海大学学报（自然科学版），2019，40（3）：274⁃288.

工作状态	Q₁	Q₂	Q₃	Q₄	Q₅	Q₆	Q₇
正常运行	0.032 4	0.002 2	0.218 7	0.087 9	0.031 2	0.127 7	0.364 8
正常运行	0.027 8	0.002 9	0.199 3	0.053 3	0.037 5	0.150 9	0.411 1
滚动体故障	0.867 9	0.012 7	0.022 5	0.040 5	0.033 7	0.014 3	0.002 0
滚动体故障	0.753 6	0.013 2	0.041 4	0.081 6	0.051 6	0.043 3	0.001 9
内圈故障	0.855 9	0.003 5	0.010 0	0.105 0	0.017 0	0.005 8	0.002 1
内圈故障	0.866 1	0.003 6	0.008 7	0.100 6	0.015 0	0.004 1	0.000 7
外圈故障	0.797 1	0.018 9	0.029 4	0.126 5	0.008 9	0.003 8	0.003 7
外圈故障	0.814 2	0.025 7	0.015 4	0.124 6	0.008 5	0.003 8	0.001 2

工作状态	Q₁	Q₂	Q₃	Q₄	Q₅	Q₆	Q₇
正常运行	0.032 4	0.002 2	0.218 7	0.087 9	0.031 2	0.127 7	0.364 8
正常运行	0.027 8	0.002 9	0.199 3	0.053 3	0.037 5	0.150 9	0.411 1
滚动体故障	0.867 9	0.012 7	0.022 5	0.040 5	0.033 7	0.014 3	0.002 0
滚动体故障	0.753 6	0.013 2	0.041 4	0.081 6	0.051 6	0.043 3	0.001 9
内圈故障	0.855 9	0.003 5	0.010 0	0.105 0	0.017 0	0.005 8	0.002 1
内圈故障	0.866 1	0.003 6	0.008 7	0.100 6	0.015 0	0.004 1	0.000 7
外圈故障	0.797 1	0.018 9	0.029 4	0.126 5	0.008 9	0.003 8	0.003 7
外圈故障	0.814 2	0.025 7	0.015 4	0.124 6	0.008 5	0.003 8	0.001 2

工作状态	Q₁	Q₂	Q₃	Q₄	Q₅	Q₆	Q₇
正常运行	0.026 0	0.001 6	0.168 1	0.059 0	0.053 7	0.207 9	0.303 0
正常运行	0.024 6	0.001 7	0.164 4	0.059 5	0.061 7	0.226 0	0.322 6
滚动体故障	0.672 4	0.003 9	0.031 2	0.130 6	0.074 3	0.063 1	0.006 4
滚动体故障	0.654 2	0.003 8	0.063 6	0.128 3	0.072 3	0.042 3	0.006 7
内圈故障	0.888 3	0.004 5	0.008 7	0.073 6	0.020 1	0.002 5	0.001 3
内圈故障	0.865 2	0.004 0	0.012 9	0.092 5	0.014 9	0.005 6	0.002 6
外圈故障	0.819 6	0.033 5	0.040 1	0.096 5	0.004 3	0.002 4	0.000 9
外圈故障	0.774 1	0.029 7	0.044 4	0.120 7	0.010 5	0.004 3	0.002 5

工作状态	Q₁	Q₂	Q₃	Q₄	Q₅	Q₆	Q₇
正常运行	0.026 0	0.001 6	0.168 1	0.059 0	0.053 7	0.207 9	0.303 0
正常运行	0.024 6	0.001 7	0.164 4	0.059 5	0.061 7	0.226 0	0.322 6
滚动体故障	0.672 4	0.003 9	0.031 2	0.130 6	0.074 3	0.063 1	0.006 4
滚动体故障	0.654 2	0.003 8	0.063 6	0.128 3	0.072 3	0.042 3	0.006 7
内圈故障	0.888 3	0.004 5	0.008 7	0.073 6	0.020 1	0.002 5	0.001 3
内圈故障	0.865 2	0.004 0	0.012 9	0.092 5	0.014 9	0.005 6	0.002 6
外圈故障	0.819 6	0.033 5	0.040 1	0.096 5	0.004 3	0.002 4	0.000 9
外圈故障	0.774 1	0.029 7	0.044 4	0.120 7	0.010 5	0.004 3	0.002 5

[1]	Qilei XIA, Lin LUO, Yao ZHANG. Fault Diagnosis of Chemical Processes Based on Attention⁃Enhanced Encoder⁃Decoder Network [J]. Journal of Liaoning Petrochemical University, 2024, 44(2): 63-70.
[2]	Xun ZHAO, Shuai CHEN, Haiyang QIU. Research on Transformer Fault Diagnosis Model Based on Improved Bidirectional Recurrent Neural Network [J]. Journal of Liaoning Petrochemical University, 2023, 43(5): 75-83.
[3]	Nan Jiang, Lin Luo, Qiao Wang, Wei Hou. Structural Optimization Deep Network for Mechanical Fault Diagnosis of High Voltage Circuit Breakers [J]. Journal of Liaoning Petrochemical University, 2023, 43(3): 91-96.
[4]	Xuejun Zhou, Xiaoqiang Chen, Lei Xie. Location of Plant⁃Level Oscillation Source Based on Improved Convergent Cross Mapping [J]. Journal of Liaoning Petrochemical University, 2021, 41(5): 85-90.
[5]	Liu Xiaoqin， Wang Chenxu， Sun Haijun， Wang Qian. Research on Fault Diagnosis of Power Supply and Distribution System in Intelligent Building Based on Wavelet and Bayesian Networks [J]. Journal of Liaoning Petrochemical University, 2020, 40(6): 78-84.
[6]	Pei Xiaodeng， Luo Lin， Chen Shuai， Wang Qiao. A Convolutional Neural Network Diagnosis Method for Dissolved Gas in Power Transformer Oil [J]. Journal of Liaoning Petrochemical University, 2020, 40(5): 79-85.
[7]	Chen Xiaolong，Zhou Junpeng，Zhang Ying，Fan Ruixiao. Fault Test and Diagnosis of Rolling Bearing Based on Acoustic Emission Waveform Streaming Signals [J]. Journal of Liaoning Petrochemical University, 2018, 38(03): 89-92.
[8]	Chang Jiaming,Li Weijun,Shi Chengjiang. Aluminum Foil Sealing Seal Detection Based on Gabor Transformation and Extreme Learning Machine [J]. Journal of Liaoning Petrochemical University, 2017, 37(3): 64-69.
[9]	Liu Shuai, Zhao Qiang. Research and Design of Power Transmission Stability Optimizationfor Wireless Power Supply System with Endoscope [J]. Journal of Liaoning Petrochemical University, 2016, 36(4): 64-68.
[10]	Wang Xiaolei, Kan Zhe, Zhang Leilei. The Fault Diagnosis Principle for Mine Hydraulic System Based  on Wavelet Principle and Fluid Electrostatic Signals [J]. Journal of Liaoning Petrochemical University, 2015, 35(3): 65-68.
[11]	Zhou Weiqiang， Hou Ligang，Su Chengli. Feature Extraction of the Rolling Bearing Based on  TimeWavelet Power Envelope Spectrum [J]. Journal of Liaoning Petrochemical University, 2014, 34(3): 75-78.
[12]	LIU Da, ZHAI Chunyan, LI Shuchen, SU Chengli. Application of Algorithm for Turbine Rotor Fault Diagnosis [J]. Journal of Liaoning Petrochemical University, 2013, 33(3): 67-69.
[13]	TANG Yu, SHI Chengjiang, YANG Jing, CUI Qing. Simulation and Analysis on Typical Rotor Fault Based on DASP [J]. Journal of Liaoning Petrochemical University, 2013, 33(2): 80-84.
[14]	SHAN Hai-ou. Improved Wavelet Neural Network’s Application in Pipelines Leakage Fault Diagnosis [J]. Journal of Liaoning Petrochemical University, 2008, 28(1): 74-77.
[15]	LIU Xiao -qin,SHEN Do ng -ri,SU Cheng -li. Fault Diagnosis of T ennessee -Eastman Process Based on the Improved Wavelet Network [J]. Journal of Liaoning Petrochemical University, 2007, 27(4): 64-67.