[1]吕明珠,苏晓明,陈长征,等.Fisher准则下的粒子群支持向量机在轴承故障诊断中的应用[J].机械与电子,2018,(07):49-54.
　LYU Mingzhu,SU xiaoming,CHEN Changzheng,et al.Application of Particle Swarm Support Vector Machine Based on Fisher Criterion in Bearing Fault Diagnosis[J].Machinery & Electronics,2018,(07):49-54.
点击复制

Fisher准则下的粒子群支持向量机在轴承故障诊断中的应用
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2018年07期
页码:
49-54
栏目:
自动控制与检测
出版日期:
2018-07-25

文章信息/Info

Title:
Application of Particle Swarm Support Vector Machine Based on Fisher Criterion in Bearing Fault Diagnosis
文章编号:
1001-2257(2018)07-0049-06
作者:
吕明珠1; 2; 苏晓明1; 陈长征1; 刘世勋3
(1.沈阳工业大学机械工程学院,辽宁 沈阳 110870; 2.辽宁装备制造职业技术学院自控学院,辽宁 沈阳 110161; 3.中认(沈阳)北方实验室有限公司,辽宁 沈阳 110164)
Author(s):
LYU Mingzhu1; 2;  SU xiaoming1;  CHEN Changzheng1;  LIU Shixun3
(1.School of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, China; 2.Department of Automatic Control, Liaoning Equipment Manufacturing Professional Technology Institute,Shenyang 110161, China; 3.CQC(Shenyang)North Laboratory, Shenyang 110164, China)
关键词:
Fisher准则;  粒子群算法;  支持向量机;  滚动轴承;  故障诊断
Keywords:
Fisher criterion;  particle swarm optimization;  support vector machine;  rolling bearing;  fault diagnosis
分类号:
TH13
文献标志码:
A
摘要:
针对粒子群算法对支持向量机参数进行优化时存在的收敛速度慢、分类准确率不高的问题,通过引入Fisher准则评估每个特征向量粒子的适应度得到最优特征子集,提出了一种基于Fisher准则下粒子群算法优化支持向量机(FIPSO-SVM)的新分类方法,该方法的目标是尽可能地加大类间间隔和减小类内间隔。采用滚动轴承数据集在时域和频域上得到32组特征向量,测试该方法在4种工作状态下的分类效果,最后,使用不同核函数和2种不同算法将全样本特征向量与最优特征向量子集的SVM分类结果进行对比。结果表明,FIPSO-SVM分类器不仅能够识别故障产生的位置,还能区别故障损伤的程度,FIPSO-SVM分类器具有更高的分类精度和更快的收敛速度,值得进一步在工程领域内推广。
Abstract:
In order to solve the problem of slow convergence rate and low classification accuracy for the optimization of SVM parameters in particle swarm optimization algorithm, this paper proposes a new classification method that uses the improved particle swarm optimization(IPSO)based on the Fisher criterion to optimize the parameters of SVM(FIPSO-SVM). In this method, the Fisher criterion is applied to assess the fitness of each feature vector particle in order to get the best feature vector subset. The purpose of this method is to increase the between-class intervals and reduce the within-class intervals as much as possible. The effectiveness of the method was tested by using the rolling bearing data set to obtain 32 sets of eigenvector in the time domain and frequency domain in 4 working conditions, and the whole sample eigenvectors and the SVM classification results were compared by using different kernel functions and two different algorithms.The results show that the FIPSO-SVM classifier can not only identify the location of the fault, but also distinguish the degree of fault damage. It has higher classification accuracy and faster convergence speed which is worthy of further promotion in the engineering field.

参考文献/References:

[1] 王亚萍,许迪,葛江华,等.基于SPWVD时频图纹理特征的滚动轴承故障诊断[J].振动、测试与诊断,2017,37(1):115-119.
[2] 刘长良,闫萧.基于工况辨识和变分模态分解的风电机组滚动轴承故障诊断[J].动力工程学报,2017,37(4):273-278.
[3] 秦波,孙国栋,张利强,等.基于Hilbert包络谱奇异值和IPSO-SVM的滚动轴承故障诊断研究[J].机械传动,2017,41(3):166-171.
[4] Samanta B,Nataraj C.Use of particle swarm optimization for machinery fault detection[J]. Engineering Applications of Artificial Intelligence, 2009,22(2):308-316.
[5] Yuan S F, Chu F L.Fault diagnosis based on particleoptimization and support vector machines[J]. Mechanical Systems and Signal Processing, 2007,21(4):1787–1798.
[6] Li R, Sopon P, He D. Fault features extraction for bearing prognostics[J].Journal of Intelligent Manufacturing,2012,23(2):313–321.
[7] 付大鹏,翟勇,于青民.基于EMD和支持向量机的滚动轴承故障诊断研究[J].机床与液压,2017,45(11):184-187.
[8] 梅恒荣,殷礼胜,刘冬梅,等.改进粒子群算法优化的SVM模拟电路故障诊断[J].电子测量与仪器学报,2017, 31(8):1239-1246.
[9] 王刚,万敏,刘虎,等.粒子群优化模糊系统的铣削力建模方法[J].机械工程学报,2011,47(13):123-130.
[10] 郝伟,刘忠宝.基于Fisher准则的半监督特征提取方法[J].计算机工程与设计,2017,38(1):238-241.
[11] 杨青青,马训鸣,李海海,等.基于LabVIEW的冲击振动信号监测系统的设计[J].机械制造与自动化,2017,46(6):210-212.
[12] 胡智勇,胡杰鑫,谢里阳,等.滚动轴承振动信号处理方法综述[J].中国工程机械学报,2016,14(6):525-531.

备注/Memo

备注/Memo:
收稿日期:2018-02-11
基金项目:国家自然科学基金资助项目(51675350); 高校重点课题(2018XB01-4)
作者简介:吕明珠(1980-),女, 辽宁沈阳人,博士研究生,讲师,主要从事故障诊断和自动控制领域的教学和研究; 苏晓明(1964-),男, 辽宁沈阳人,博士研究生导师,教授,主要从事工业工程控制领域的教学和研究; 陈长征(1965-),男,辽宁沈阳人,博士研究生导师,教授,主要从事振动与噪声领域的教学和研究; 刘世勋(1980-),男,辽宁沈阳人,硕士研究生
更新日期/Last Update: 2018-07-25