一种基于概率盒&mdash;HGWO优化SVM的滚动轴承故障诊断方法

PDF(1597 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (22) : 234-241.

论文

一种基于概率盒—HGWO优化SVM的滚动轴承故障诊断方法

路小娟，石成基

作者信息 +

Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings

LU Xiaojuan, SHI Chengji

Author information +

文章历史 +

摘要

针对滚动轴承故障振动信号在特征提取时出现的信息丢失、误动等不确定性问题以及故障诊断准确性不理想的问题，提出了一种基于概率盒理论和改进灰狼算法优化支持向量机的混合智能机械故障诊断方法。首先，利用直接建模的方法得到概率盒，再采用累积不确定性测量方法提取其特征，构建出用于故障诊断的特征向量集；其次，利用改进的灰狼算法对支持向量机进行优化；最后，利用优化后的支持向量机实现对特征集的分类诊断。所提方法充分利用了概率盒在处理不确定性问题的优势和支持向量机在解决小样本、非线性模式识别中优秀的分类性能，可对不同故障类型的振动信号进行更加精准的辨识。通过对滚动轴承振动信号的实验验证与对比实验分析表明，该方法在滚动轴承故障诊断方面具有一定的有效性。

Abstract

A hybrid intelligent mechanical fault diagnosis method based on probability box theory and improved Grey Wolf algorithm to optimize support vector machine was proposed to solve the problem of information loss, misoperation and other uncertainties in feature extraction of rolling bearing fault vibration signal and the problem of poor accuracy of fault diagnosis.Firstly, the probability box is obtained by direct modeling method, and then its features are extracted by cumulative uncertainty measurement method to construct the feature vector set for fault diagnosis.Secondly, the improved Grey Wolf algorithm is used to optimize the support vector machine.Finally, the feature set is classified and diagnosed by using the optimized support vector machine.The proposed method makes full use of the advantages of probability box in dealing with uncertain problems and the excellent classification performance of support vector machine in solving small sample and nonlinear pattern recognition, so that vibration signals of different fault types can be more accurately identified.Experimental verification and comparative analysis of rolling bearing vibration signal show that this method is effective in fault diagnosis of rolling bearing.

导出引用

路小娟，石成基. 一种基于概率盒—HGWO优化SVM的滚动轴承故障诊断方法[J]. 振动与冲击, 2021, 40(22): 234-241

LU Xiaojuan, SHI Chengji. Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2021, 40(22): 234-241

参考文献

[1] XIA M, LIT, SHU T X. et al. A two-stage approach for the remaining useful life prediction of bearings using deep neural networks [J]. IEEE Transactions onIndustrial Informatics, 2019, 15(6); 3703-3711.
[2] 金棋,王友仁,王俊.基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法[J].中国机械工程,2019,30(02):196-204.
JIN Qi, WANG Youren, WANG Jun, et al. Planetarygearbox fault diagnosis based on multiple feature extraction and information fusion combined with deep learning [J]. China Mechanical Engineering, 2019, 30 (2): 196-204.
[3] 赵志宏,杨绍普,刘永强.多小波系数特征提取方法在故障诊断中的应用[J].振动.测试与诊断,2015,35(02):276-280+398.
ZHAO Zhihong, YANG Shaopu, LIU Yongqiang. Multiwavelet coefficient feature extraction method in fault diagnosis[J]. Journal of Vibration, Measurement & Diagnosis, 2015,35(02):276-280+398.
[4] 陈保家,刘浩涛,徐超,等.深度置信网络在齿轮故障诊断中的应用[J].中国机械工程,2019,30(02):205-211.
CHEN Baojia, LIU Haotao, XU Chao, et al. Gear fault diagnosis based on DBNS [J]. China Mechanical Engineering, 2019, 30(2): 205-211.
[5] 唐贵基,王晓龙.基于局部均值分解和切片双谱的滚动轴承故障诊断研究[J].振动与冲击,2013,32(24):83-88+95.
TANG Guijli, WANG Xiaolong. Fault diagnosis of rollerbearings based on local mean decomposition and slice bispectrun [J]. Journal of Vibration and Shock, 2013,32(24):83-88+95.
[6] 王波,刘树林,张宏利.基于QGA优化广义S变换的滚动轴承故障特征提取[J].振动与冲击,2017,36(05):108-113+119.
WANG Bo, LIU Shulin, ZHANG Hongli. Fault feature extraction for rolling bearings based on generalized s transformation optimized with Quantum genetic algorithm [J]. ournal of Vibration and Shock, 2017,36(05):108-113+119.
[7] 孙鲜明,刘欢,赵新光,等.基于瞬时包络尺度谱熵的滚动轴承早期故障奇异点识别及特征提取[J].机械工程学报,2017,53(03):73-80.
Sun XianMing, Liu Huan, Zhao XinGuang, et al. Identification and feature extraction of early fault singularity of rolling bearing based on instantaneous envelope scale spectrum entropy. Journal of Mechanical Engineering, 2017, 53(03): 73-80.
[8] Liu R N, Yang B Y, Zhang X L,Wang S B, Chen X F. Timefrequency atoms-driven support vector machine method for bearings incipient fault diagnosis. Mechanical Systems and Signal Processing, 2016, 75: 345-370.
[9] 杨蕊,李宏坤,贺长波,等.利用最优小波尺度循环谱的滚动轴承早期故障特征提取[J].机械工程学报,2018,54(17):208-217.
Yang Rui. Li HongKun. He ChangBo, et al. Early fault feature extraction of rolling bearing by using optimal wavelet scale cyclic spectrum. Journal of Mechanical Engineering, 2018,54(17):208-217.
[10] Dhamande L S, Chaudhari M B. Compound gear-bearingault feature extraction using statistical features based on time-frequency method. Measurement, 2018, 125: 63-77.
[11] SHAFER G. TheCombination of Evidence [J]. International Journal of Intelligent Systems, 1986 (3) : 155-179.
[12] 杜奕,丁家满,刘力强.基于概率盒理论的滚动轴承故障信号建模方法[J].振动与冲击,2016,35(19):31-37.
Duyi, DING Jiaman,LIU Liqiang. Modeling method of rolling bearing fault signal based on probability box theory [J]. Journal of Vibration and Shock,2016,35(19):31-37.
[13] MIRJALILI S, MIRJALILI S M. LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software,2014, 69: 46-61.
[14] RODRIGUEZ L, CASTILLO O, SORIA J, et al. A fuzzy hierarchical operator in the grey wolf optimizer algorithm [J]. Applied Soft Computing, 2017, 57: 315-328.
[15] MIRJALILI S, MIRJALILI S M. LEWIS A. Grey wolf optimizer approach for optimal weight design problem of the spur gear [J]. Engineering Optimization, 2019,51(6): 1013-1027.
[16] ZHANG X. MIAO Q, LIU z w, et al. An adaptive stochastic resonance method based on grey wolf optimizer algorithm and its application to machinery fault diagnosis [J]. ISA Transactions, 2019, 71: 206-214.
[17] 李阳,李维刚,赵云涛,等.基于莱维飞行和随机游动策略的灰狼算法[J].计算机科学,2020,47(08):291-296.
Li Yang, Li Weigang, Zhao Yuntao, ,et al. Grey wolf algorithm based on Levy flight and random walk strategy [J]. Computer science,2020,47(08):291-296.
[18] 汪泓,韩文秀.关于Rastrigin函数的注记[J].青岛大学学报(自然科学版),1999(03):3-5.
Wang Hong, Han Wenxiu.Notes on the Rastrigin function [J]. Journal of Qingdao University (Natural Science edition),1999(03):3-5.