Life condition recognition of slewing bearing based on kernel extreme learning machine based auto-encoder

doi:10.3785/j.issn.1008-973X.2022.09.019

Journal of ZheJiang University (Engineering Science)

2022, Vol. 56

Issue (9): 1856-1866 DOI: 10.3785/j.issn.1008-973X.2022.09.019

Life condition recognition of slewing bearing based on kernel extreme learning machine based auto-encoder

Yu-bin PAN1(

),Hua WANG1,2,*(

),Jie CHEN1,2,Rong-jing HONG1,2

1. School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211816, China
2. Jiangsu Key Laboratory of Digital Manufacturing for Industrial Equipment and Control Technology, Nanjing 211816, China

Download:

HTML

PDF(2091KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A life condition recognition method based on multi-layer kernel extreme learning machine based auto-encoder optimized by moth-flame optimization (MFO-MLKELM-AE) was proposed to solve the problem of low-speed heavy-load slewing bearing, such as poor working condition and weak fault feature. Firstly, multiple feature vectors were extracted from time domain and time-frequency domain of vibration signal to make a high dimension feature set which can characterize the operation condition of slewing bearing. Secondly, multi-layer kernel extreme learning machine based auto-encoder (MLKELM-AE) was utilized to extract the vectors which best reflect the slewing bearing life condition information from the high dimension feature set. Thirdly, the vectors were inputted into the kernel extreme learning machine (KELM) for the life condition recognition. Finally, a new moth-flame optimization (MFO) was proposed to optimize the penalty coefficient and kernel parameter for the improvement of MLKELM-AE feature recognition ability in the training process. The accelerated life test of slewing bearing shows that the recognition accuracy of MLKELM-AE is better than multi-layer extreme learning machine based auto-encoder (MLELM-AE), single layer extreme learning machine (ELM) and KELM. The multi-sensor and multi-domain features can reflect the life condition of slewing bearing more comprehensively.

Key words： low-speed heavy-load slewing bearing multi-layer kernel extreme learning machine based auto-encoder (MLKELM-AE) moth-flame optimization (MFO) life condition recognition multi-domain features

Received: 27 October 2021 Published: 28 September 2022

CLC:

TH 17

Fund: 国家自然科学基金资助项目（51875273）；中国博士后科学基金资助项目（2021M691558）；江苏省自然科学基金资助项目（BK20210547）；江苏省高等学校自然科学研究项目资助（21KJB460036）；江苏省博士后科研资助计划项目（2021K297B）

Corresponding Authors: Hua WANG E-mail: panyb@njtech.edu.cn;njtechwh@yeah.net

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yu-bin PAN
	Hua WANG
	Jie CHEN
	Rong-jing HONG

Cite this article:

Yu-bin PAN,Hua WANG,Jie CHEN,Rong-jing HONG. Life condition recognition of slewing bearing based on kernel extreme learning machine based auto-encoder. Journal of ZheJiang University (Engineering Science), 2022, 56(9): 1856-1866.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2022.09.019 OR https://www.zjujournals.com/eng/Y2022/V56/I9/1856

基于核极限学习机自编码器的转盘轴承寿命状态识别

针对低速重载转盘轴承运行工况恶劣、故障特征微弱的特点，提出基于飞蛾扑火算法优化多层核极限学习机自编码器（MFO-MLKELM-AE）的转盘轴承寿命状态识别方法. 该方法从振动信号的时域和时频域中提取出多个能够表征转盘轴承运行状态的特征向量，并将其组成高维特征集. 采用堆叠多层核极限学习机自编码器（MLKELM-AE），从高维特征集中提取最能反映转盘轴承的寿命状态信息，输入核极限学习机（KELM）模型进行寿命状态识别. 在MLKELM-AE学习训练中，采用新的飞蛾扑火算法（MFO）优化惩罚系数和核参数，提高MLKELM-AE的特征识别能力. 转盘轴承加速寿命实验表明，MLKELM-AE比多层极限学习机自编码器（MLELM-AE）、单层极限学习机（ELM）、KELM的识别精度高，多传感器、多领域特征能够全面反映转盘轴承的寿命状态.

关键词： 低速重载转盘轴承, 多层核极限学习机自编码器（MLKELM-AE）, 飞蛾扑火算法（MFO）, 寿命状态识别, 多领域特征

Fig.1 Structure diagram of kernel extreme learning machine based auto-encoder

Fig.2 Structure diagram of multi-layer kernel extreme learning machine based auto-encoder

Fig.3 Flowchart of slewing bearing life condition recognition

Fig.4 Schematic diagram of slewing bearing test rig

Tab.1 Performance parameters of slewing bearing test rig

Fig.5 Structure and sensor installation of slewing bearing

Fig.6 Physical map of slewing bearing test rig

Fig.7 Damage components of slewing bearing

Fig.8 Vibration signals of different life periods

Fig.9 Life cycle temperature and driving torque signals

Fig.10 Feature trend curve of life cycle vibration signals

Fig.11 Recognition result of different layers of kernel extreme learning machine based auto-encoder

Fig.12 Feature output after learning of multi-layer kernel extreme learning machine based auto-encoder

Fig.13 Confusion matrix of life condition recognition result under different domain features

Tab.2 Life condition recognition result of different optimization algorithm under multi-domain features

Tab.3 Life condition recognition accuracy of parameter optimization and non optimization under different domain features

Tab.4 Life condition recognition result of different recognition models under multi-domain features

Tab.5 Life condition recognition accuracy of different recognition models under different domain features

Tab.6 Life condition recognition accuracy of different recognition models under multi-sensor feature fusion


[1]	CERRADA M, SÁNCHEZ R V, LI C, et al A review on data-driven fault severity assessment in rolling bearings[J]. Mechanical Systems and Signal Processing, 2018, 99: 169- 196 doi: 10.1016/j.ymssp.2017.06.012

[2]	赵祥龙, 陈捷, 洪荣晶, 等基于Wavelet leader和优化的等距映射算法的回转支承自适应特征提取[J]. 浙江大学学报:工学版, 2019, 53 (11): 2092- 2101 ZHAO Xiang-long, CHEN Jie, HONG Rong-jing, et al Adaptive feature extraction method for slewing bearing based on Wavelet leader and optimized isometric mapping method[J]. Journal of Zhejiang University: Engineering Science, 2019, 53 (11): 2092- 2101

[3]	封杨, 黄筱调, 洪荣晶, 等基于数据驱动的回转支承性能退化评估方法[J]. 中南大学学报:自然科学版, 2017, 48 (3): 684- 693 FENG Yang, HUANG Xiao-diao, HONG Rong-jing, et al A multi-dimensional data-driven method for large-size slewing bearings performance degradation assessment[J]. Journal of Central South University: Science and Technology, 2017, 48 (3): 684- 693

[4]	NAYANA B R GEETHANJALI P. Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal[J]. IEEE Sensors Journal, 2017, 17 (17): 5618- 5625 doi: 10.1109/JSEN.2017.2727638

[5]	CAESARENDRA W, KOSASIH P B, TIEU A K, et al Condition monitoring of naturally damaged slow speed slewing bearing based on ensemble empirical mode decomposition[J]. Journal of Mechanical Science and Technology, 2013, 27: 2253- 2262 doi: 10.1007/s12206-013-0608-7

[6]	LIU Z, ZHANG L, CARRASCO J Vibration analysis for large-scale wind turbine blade bearing fault detection with an empirical wavelet thresholding method[J]. Renewable Energy, 2020, 146: 99- 110 doi: 10.1016/j.renene.2019.06.094

[7]	LU C, CHEN J, HONG R, et al Degradation trend estimation of slewing bearing based on LSSVM model[J]. Mechanical Systems and Signal Processing, 2016, 76-77: 353- 366 doi: 10.1016/j.ymssp.2016.02.031

[8]	李媛媛, 陈捷, 黄筱调, 等基于改进模糊C均值的回转支承寿命状态识别[J]. 计算机集成制造系统, 2018, 24 (11): 2751- 2758 LI Yuan-yuan, CHEN Jie, HUANG Xiao-diao, et al Life state recognition of slewing bearing based on improved fuzzy C-means[J]. Computer Integrated Manufacturing Systems, 2018, 24 (11): 2751- 2758 doi: 10.13196/j.cims.2018.11.010

[9]	付文博, 孙涛, 梁藉, 等深度学习原理及应用综述[J]. 计算机科学, 2018, 45 (6A): 11- 15 FU Wen-bo, SUN Tao, LIANG Ji, at al Review of principle and application of deep learning[J]. Computer Science, 2018, 45 (6A): 11- 15 doi: 10.11896/j.issn.1002-137X.2018.Z6.002

[10]	KASUN L L C, ZHOU H, HUANG G B Representational learning with ELMs for big data[J]. IEEE Intelligent Systems, 2013, 28 (6): 31- 34

[11]	YU W, ZHUANG F, HE Q, et al Learning deep representations via extreme learning machines[J]. Neurocomputing, 2015, 149: 308- 315 doi: 10.1016/j.neucom.2014.03.077

[12]	ZHANG N, DING S, SHI Z Denoising Laplacian multi-layer extreme learning machine[J]. Neurocomputing, 2016, 171: 1066- 1074 doi: 10.1016/j.neucom.2015.07.058

[13]	SUN K, ZHANG J, ZHANG C, et al Generalized extreme learning machine autoencoder and a new deep neural network[J]. Neurocomputing, 2017, 230: 374- 381 doi: 10.1016/j.neucom.2016.12.027

[14]	桑发文. 深度核极限学习机和相似性LSSVM时间序列预测模型研究[D]. 兰州: 兰州大学, 2019: 18. Sang Fa-wen. Research on time series prediction model of deep kernel extreme learning machine and LSSVM based on similarity [D]. Lanzhou: Lanzhou University, 2019: 18.

[15]	邓万宇, 郑庆华, 陈琳, 等神经网络极速学习方法研究[J]. 计算机学报, 2010, 33 (2): 279- 287 DENG Wan-yu, ZHENG Qing-hua, CHEN Lin, et al Research on extreme learning of neural networks[J]. Chinese Journal of Computers, 2010, 33 (2): 279- 287 doi: 10.3724/SP.J.1016.2010.00279

[16]	HUANG G B An insight into extreme learning machines: Random neurons, random features and kernels[J]. Cognitive Computation, 2014, 6: 376- 390 doi: 10.1007/s12559-014-9255-2

[17]	商强, 林赐云, 杨兆升, 等基于变量选择和核极限学习机的交通事件检测[J]. 浙江大学学报:工学版, 2017, 51 (7): 1339- 1346 SHANG Qiang, LIN Ci-yun, YANG Zhao-sheng, et al Traffic incident detection based on variable selection and kernel extreme learning machine[J]. Journal of Zhejiang University:Engineering Science, 2017, 51 (7): 1339- 1346

[18]	胡爱军, 张军华, 刘随贤, 等滚动轴承多工况故障的特征自动选择核极限学习机智能识别方法[J]. 振动与冲击, 2020, 39 (23): 182- 189 HU Ai-jun, ZHANG Jun-hua, LIU Sui-xian, et al Intelligent identification method using kernel extreme learning machine for rolling bearing multi-working condition multi-feature automatic selection[J]. Journal of Vibration and Shock, 2020, 39 (23): 182- 189

[19]	SCHÖLKOPF B, SMOLA A J. Learning with kernels: support vector machines, regularization and beyond [M]. Cambridge: MIT Press, 2002.

[20]	MIRJALILI S Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm[J]. Knowledge-Based Systems, 2015, 89: 228- 249 doi: 10.1016/j.knosys.2015.07.006

[21]	李志明, 莫愿斌, 张森一种新颖的群智能算法: 飞蛾扑火优化算法[J]. 电脑知识与技术, 2016, 12 (31): 172- 176 LI Zhi-ming, MO Yuan-bin, ZHANG Sen A novel swarm intelligence optimization algorithm: moth-flame optimization algorithm[J]. Computer Knowledge and Technology, 2016, 12 (31): 172- 176

[22]	CHENG Y, ZHAO D, WANG Y, et al Multi-label learning with kernel extreme learning machine autoencoder[J]. Knowledge-Based Systems, 2019, 178: 1- 10 doi: 10.1016/j.knosys.2019.04.002

[23]	郭建华, 杨海东基于支持向量免疫集成预测的电信网络性能监控[J]. 中南大学学报:自然科学版, 2012, 43 (3): 1020- 1026 GUO Jian-hua, YANG Hai-dong Telecom networks performance monitoring based on artificial immune support vector regression[J]. Journal of Central South University: Science and Technology, 2012, 43 (3): 1020- 1026

[1]	Yu-hui XU,Jun-qing SHU,Ya SONG,Yu ZHENG,Tang-bin XIA. Remaining useful life prediction of turbofan engine based on similarity in multiple time scales[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(10): 1937-1947.

[2]	Xiu-fen ZHANG,Yun-fei GAO. Multi-dimensional hierarchical remanufacturability evaluation method for end-of-life mechanical parts[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(5): 954-962.

[3]	Hai-jin WANG,Zong-yu YIN,Zhen-zheng KE,Ying-jie GUO,Hui-yue DONG. Wear monitoring of helical milling tool based on one-dimensional convolutional neural network[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(5): 931-939.

[4]	YUAN Xing, ZHANG You-yun, ZHU Yong-sheng, HONG Jun，QI Wen-chang. Fault degree evaluation for rolling bearing combining backward inference with forward inference[J]. Journal of ZheJiang University (Engineering Science), 2012, 46(11): 1960-1967.

[5]	YANG Xian-Yong, ZHOU Xiao-Jun, LIN Yong, ZHANG Wen-Bin, CHEN Lu. Fault diagnosis approach for rolling bearing based on V-detector algorithm[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(9): 1805-1810.

[6]	YANG Xian-Yong, ZHOU Xiao-Jun, ZHANG Wen-Bin, YANG Fu-Chun. Rolling bearing fault diagnosis based on local wave method and KPCA-LSSVM[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(8): 1519-1524.

Viewed

Full text

Abstract

Cited

Shared

Discussed