[1]赵蕾,傅攀,胡龙飞,等.FOA-WPT降噪和PSO-SVM在滚动轴承故障诊断中的应用[J].机械与电子,2018,(12):3-8,13.
 ZHAO Lei,FU Pan,HU Longfei,et al.Applications of FOA-WPT and PSO-SVM in Faults Diagnosis of Rolling Bearing[J].Machinery & Electronics,2018,(12):3-8,13.
点击复制

FOA-WPT降噪和PSO-SVM在滚动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12期
页码:
3-8,13
栏目:
设计与研究
出版日期:
2018-12-24

文章信息/Info

Title:
Applications of FOA-WPT and PSO-SVM in Faults Diagnosis of Rolling Bearing
文章编号:
1001-2257(2018)12-0003-06
作者:
赵蕾傅攀胡龙飞张思聪石大磊
(西南交通大学机械工程学院,四川 成都 610031)
Author(s):
ZHAO LeiFU PanHU LongfeiZHANG SicongSHI Dalei
(School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China)
关键词:
小波包降噪果蝇优化算法粒子群算法支持向量机故障诊断
Keywords:
wavelet package diagnosis method fruit fly optimization algorithm particle swarm optimization support vector machines faults diagnosis
分类号:
TH133.33
文献标志码:
A
摘要:
在轴承故障诊断中,为了进一步提高诊断方法的自适应性和分类准确率,提出果蝇优化小波包降噪和粒子群支持向量机相结合的方法。利用果蝇算法对小波包降噪的阈值进行优化,结合粒子群算法在GCV算法下的错误率最低,得到SVM的最优惩罚参数和核函数参数,建立PSO-SVM分类模型,对4种工况下滚动轴承的10类故障进行分类。实验结果表明,使用FOA-WPT降噪后,信号有着更高的信噪比和更低的均方误差(MSE);和粒子群支持向量机相结合的分类方法准确率达到89%,与未使用粒子群算法优化的SVM相比,提高了约8%,进一步证明了该方法可以实现滚动轴承的多分类故障诊断。
Abstract:
In order to improve the self-adaptability and accuracy of faults diagnosis of rolling bearings, a method combined FOA-WPT and PSO-SVM was proposed. Fruit Fly Algorithm to optimize Wavelet Package Transformation, together with Particle Swarm Optimization with lower error-rates under GCV algorithm, gains the best punish parameter and kernel function parameter which are used to build SVM classification model to classify 10 kinds of rolling bearing faults. The experimental results show that the signal after FOA-WPT has higher Signal-Noise Ratio (SNR) and lower Mean Square Error (MSE); Besides, the accuracy of classification methods by using PSO-SVM can reach 89%, which is about 8% higher than that of traditional SVM without particle swarm optimization. All above prove that FOA-WPT combined with PSO-SVM can be applied to the faults diagnosis of rolling bearings

参考文献/References:

[1]刘玲,张西,汪琳娜.故障诊断技术的现状与发展[J].电子测试,2016(2/4):62-63.
[2]蒋恩超,傅攀,张思聪.小波包与GA-SVM在轴承故障诊断中的应用[J].计算机测量与控制,2017,25(10):7-10.
[3]李爱英,方立.基于小波分析和支持向量机的轴承故障诊断[J].甘肃科技,2018,34(4):47-48,20.
[4]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,2018,36(7):49-54.
[5]伯勒斯,戈皮纳特,郭海涛.小波与小波变换导论[M]. 芮国胜,程正兴,王文,译.北京:电子工业出版社,2013.
[6]曾宪伟,赵卫明,许晓庆.基于小波变换与小波包变换的降噪方法比较[J].地震地磁观测与研究,2010,31(4):14-19.
[7]许理,李戈壁,余亮,等.基于小波包与CNN的滚动轴承故障诊断[J].四川理工学院学报(自然科学版),2018,31(3):54-59.
[8]张弦,王宏力.利用粒子群优化的小波简化交叉验证消噪[J].仪器仪表学报,2010,31(5):1184-1189.
[9]李大中,赵杰,孙立江,等.果蝇优化小波阈值超声检测信号去噪[J].中国测试,2016,42(7):88-92.
[10]徐雪娇.基于支持向量机的旋转机械振动故障诊断研究[D].大庆:东北石油大学,2016.
[11]胡良谋,曹克强,徐浩军.支持向量机故障诊断及控制技术[M].北京:国防工业出版社,2011.
[12]陈园艺,孙建平.基于EEMD和PSO-SVM的滚动轴承故障诊断[J].电力科学与工程,2016,32(10):47-52.
[13]Shi P M, Liang K, Han D Y, et al. A novel intelligent fault diagnosis method of rotating machinery based on deep learning and PSO-SVM[J]. Journal of Vibroengineering,2017,19(8):5932-5946.
[14]Dou D Y, Zhou S S.Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery[J].Applied Soft Computer,2016,46:459-568.
[15]Zhang Y, Zuo H F, Bai F. Classification of fault location and performance degradation of a roller bearing[J].Measurement,2012,46(3):1178-1189.

备注/Memo

备注/Memo:
收稿日期:2018-09-07
基金项目:中央高校基本科研业务费专项资金资助(2682016CX033)
作者简介:赵蕾(1994-),女, 山东菏泽人,硕士研究生,主要研究方向为智能化状态监测与故障诊断;傅攀(1961-),男,河南浚县人,教授,博士研究生导师,研究方向为智能化状态监测与故障诊断。
更新日期/Last Update: 2019-10-29