基于蜣螂算法优化深度极限学习机的中介轴承故障诊断方法

PDF(3705 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (21) : 96-106.

论文

基于蜣螂算法优化深度极限学习机的中介轴承故障诊断方法

栾孝驰，汤捷中，沙云东

作者信息 +

Inter-shaft fault diagnosis method based on deep extreme learning machine optimized with dung beetle optimizer

LUAN Xiaochi, TANG Jiezhong, SHA Yundong

Author information +

文章历史 +

摘要

针对中介轴承故障信号传递路径复杂、受背景噪声干扰大、故障特征提取难，且传统诊断模型准确率受限于测点位置的问题，提出了一种基于自适应噪声完全经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)与蜣螂算法(dung beetle optimizer, DBO)优化深度极限学习机(deep extreme learning machine,DELM)结合的中介轴承故障诊断方法。首先，使用CEEMDAN和由能量比-相关系数-峭度值组成的固有模态分量筛选准则对原始信号进行分解、筛选、重构，在重构信号的时域与频域中提取特征组成特征矩阵；其次，将诊断准确率作为DBO的适应度值，对DELM模型的初始权重进行优化构建出全新的DELM；最后，将特征矩阵输入DELM完成故障诊断。以中介轴承故障数据为例，经DBO优化后的DELM诊断准确率取得了较大提升，在诊断较为困难的45°方向上诊断准确率仍达到了98.75%。结果表明：该诊断方法有效识别了中介轴承故障类型，展现了较强的鲁棒性与泛化能力。

Abstract

For the problems that the fault signal transmission path of inter-shaft bearing is complex, interfered by background noise, fault features extraction are difficult, and the accuracy of traditional diagnosis model is limited by the location of measuring points, an inter-shaft bearing fault diagnosis method based on a combination of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Deep Extreme Learning Machine (DELM) optimized by Dung Beetle Optimizer (DBO) was proposed. Firstly, the original signal was decomposed,screened and reconstructed by CEEMDAN and the intrinsic mode function screening criteria composed of energy ratio-correlation coefficient-kurtosis value,and features were extracted from the time domain and frequency domain of the reconstructed signal to form the feature matrix. Secondly, reconstruct the DELM after optimizing the initial weight of DELM model using the diagnostic accuracy as the fitness value of DBO. Finally, the feature matrix was input into DELM to complete fault diagnosis. Taking the inter-shaft bearing fault data as an example, the DELM diagnosis accuracy after DBO optimization has been greatly improved, and the diagnosis accuracy was still up to 98.75% in the 45° direction which was difficult to diagnose. The results show that the diagnostic method can effectively identify the inter-shaft bearing fault type and shows strong robustness and generalization ability.

导出引用

栾孝驰, 汤捷中, 沙云东. 基于蜣螂算法优化深度极限学习机的中介轴承故障诊断方法[J]. 振动与冲击, 2024, 43(21): 96-106

LUAN Xiaochi, TANG Jiezhong, SHA Yundong. Inter-shaft fault diagnosis method based on deep extreme learning machine optimized with dung beetle optimizer[J]. Journal of Vibration and Shock, 2024, 43(21): 96-106

参考文献

[1] 田博文.基于信息熵的中介轴承故障诊断[D].沈阳航空航天大学,2020.
TIAN Bowen. Fault diagnosis of inter-shaft bearingbased on information entropy[D]. Shenyang Aerospace University, 2020.
[2] 司伟伟,岑健,伍银波,等.小样本轴承故障诊断研究综述[J].计算机工程与应用,2023,59(06):45-56.
SI Weiwei, CEN Jian, WU Yinbo, et al. Review of Research on Bearing Fault Diagnosis with Small Samples[J]. Computer Engineering and Applications, 2023, 59(06):45-46.
[3] 李一平,叶海天,曹立,等.基于K-L散度和TEO的滚动轴承故障频率识别方法[J].中国计量大学学报,2021,32(03):310-317.
LI Yiping, YE Hitian, CAO Li, et al. Fault frequency identification method of rolling bearing based on K-L divergence and TEO[J]. Journal of China University of Metrology, 2021, 32(03):310-317.
[4] 季俊伟.小波分析技术在汽轮机振动信号消噪与检测中的应用[J].东北电力技术,2006(02):9-11.
JI Junwei. The Application of Wavelet Analysis Technology to De-noising and Detection of Steam Turbine Vibration Signal[J]. NORTHEAST ELECTRIC POWER TECHNOLOGY, 2006(02):9-11.
[5] 李志农,刘跃凡,胡志峰,等.经验小波变换-同步提取及其在滚动轴承故障诊断中的应用[J].振动工程学报,2021,34(06):1284-1292.
LI Zhinong, LIU Yuefan, HU Zhifeng.et al.Empirical wavelet transform-synchronous extraction application in rolling bearing fault diagnosis[J]. Journal of Vibration Engineering, 2021, 34(06):1284-1292.
[6] Wang Yi,Xu Chuannuo, Wang Yu, et al. A Comprehensive Diagnosis Method of Rolling Bearing Fault Based on CEEMDAN-DFA-Improved Wavelet Threshold Function and QPSO-MPE-SVM[J]. Entropy, 2021, 23(9):1142-1142.
[7] 王丹,金光灿,邱志,等.滚动轴承故障的卷积神经网络诊断研究[J].软件导刊,2021,20(08):44-48.
WANG Dan, JIN Guangcan, QIU Zhi, et al.Research on the Diagnosis of Rolling Bearing Fault by Convolutional Neural Network[J]. Software Guide, 2021, 20(08):44-48.
[8] 金岩磊,何茂慧,郭涛等.改进VMD融合深度学习在滚动轴承故障诊断中的应用[J].热能动力工程,2023,38(02):144-152.
JIN Yanlei, HE Maohui, GUO Tao, et al. Application of Improved VMD Combined with Deep Learning in Ｒolling Bearing Fault Diagnosis[J]. Journal of Engineering for Thermal Energy and Power, 2023, 38(02):144-152.
[9] 鲍怀谦,魏永长,王金瑞等.EMD-CSF在滚动轴承早期微弱故障诊断中应用[J].噪声与振动控制,2022,42(06):105-110.
BAO Huiqian, WEI Yongchang, WANG Jinrui, et al. Early Weak Bearing Fault Diagnosis Method Based on EMD-CSF[J]. Noise and Vibration Control, 2022, 42(06):105-110.
[10] Torres Maria E, Colominas Mar-celoA, Schlotthauer Gaston, et al. A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise[C]. Prague: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing, 2011.
[11] 栾孝驰,张席,沙云东等.基于灰狼算法优化极限学习机的中介轴承故障诊断方法[J/OL].推进技术:1-12[2023-04-02].
LUAN Xiaochi, ZHANG Xi, SHA Yundong,et al. Method on Inter-shaft Bearing Fault Diagnosis Based on Extreme Learning Machine optimized by Gray Wolf Optimizer[J/OL]. Journal of Propulsion Technology:1-12[2023-04-02].
[12] WANG Fei, ZHANG Wenjin, DING Yu, et al. Bearing fault diagnosis based on intrinsic time-scale decomposition and extreme learning machine[J]. Vibroengineering PROCEDIA, 2017, 14:97-101.
[13] YUAN Liying, WANG Hongqi. Application of hierarchical symbolic fuzzy entropy and sparse Bayesian ELM to bearing fault diagnosis[J]. Journal of Mechanical Science and Technology, 2023, 37(5).
[14] 郑小霞,蒋海生,刘静,等.基于变分模态分解与灰狼算法优化极限学习机的滚动轴承故障诊断[J].轴承,2021(09):48-53.
ZHENG Xiaoxia, JIANG Haisheng, LIU Jing,et al.Fault Diagnosis for Rolling Bearings Based on Variational Mode Decomposition and GWO-ELM[J] .Bearing, 2021(09):48-53.
[15] 何葵东,陈伽,金艳,等.EEMD多尺度熵和ELM在水电机组振动信号特征提取中的应用[J].中国农村水利水电,2021(05):176-182+187.
HE Kuidong, CHEN Jia, JIN Yan, et al. Application of EEMD Multi-scale Entropy and ELM in Feature Extraction of Vibration Signal of Hydropower Unit[J]. China Rural Water and Hydropower, 2021(05):176-182+187.
[16] Xue Jiankai, Shen Bo, Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2022, 79(7):7305-7336.
[17] 陈万圣,王珍,赵洪健,等.基于压缩感知与改进的深度极限学习机的轴承故障诊断方法[J].机械强度,2021,43(04):779-785.
CHEN Wansheng, WANG Zhen, ZHAO Hongjian, et al. New Method for Bearing Intelligent Diagnosis based on Compressed Sensing and Multilayer Extreme Learning Machine[J]. Journal of Mechanical Strength, 2021, 43(04):779-785.
[18] 兰杰,李志宁,吕建刚.基于深度极限学习机的轴承故障诊断方法研究[J/OL].[2022-06-16]（2023-10-26）.https://kns.cnki.net/kcms/detail/61.1224.TN.20220616.1316.002.html.
[19] Case Western Reserve University Bearing Data Center［EB/OL］. 2018. https:// cse groups. case. edu/ bearing data center/ pages/ download-data-file.
[20] 田晶,艾辛平,刘丽丽,等.中介轴承复合故障动力学建模与振动特征分析[J].振动与冲击,2022,41(22):144-151.
TIAN Jing, AI Xinping, LIU Lili, et al. Dynamic modeling and vibration characteristic analysis of the inter-shaft bearing multiple point fault[J]. Journal of Vibration and Shock, 2022, 41(22):144-151.
[21] 田晶,周杰,王术光等.基于自适应双稳态随机共振的中介轴承故障诊断方法[J].航空动力学报,2019(10):2237-2245[2023-04-02].
TIAN Jing, ZHOU Jie, WANG Shuguang, et al. Fault diagnosis method of inter-shaft bearing based on adaptive bistable stochastic resonance[J/OL]. Journal of Aerospace Power, 2019(10):2237-2245[2023-04-02].