摘要
人为因素对传统滚动轴承故障诊断方法有比较大的影响,并且故障起因比较复杂。针对此问题提出用基于量子粒子群(QPSO)算法优化的相关向量机(RVM)进行滚动轴承故障诊断。采用总体平均经验模态分解(EEMD)方法来处理滚动轴承的振动信号,分解后可以得到很多内禀模态函数(IMF)。再把IMF能量作为特征向量输入到QPSA-RVM诊断器中对滚动轴承的故障进行准确诊断。实验结果显示:该模型可以更快地实现对滚动轴承故障的准确识别,证明了该模型的稳定性及高效性。与支持向量机(SVM)分析对比后,进一步体现出RVM方法在智能故障诊断领域中具有优势。
Human factors have great influence on the traditional methods of rolling bearing fault diagnosis,and the cause of the fault is complicated. To solve the problem,we put forward fault diagnosis method based on QPSO to optimize the relevance vector machine( RVM). It was applied to the rolling bearing fault diagnosis. The ensemble empirical mode decomposition( EEMD) was adopted to deal withvibration signal of rolling bearing. Several intrinsic mode functions( IMF) could be obtained after decomposition. IMF energy was input into QPSA-RVM diagnoser as feature vector,and the fault of rolling bearing was diagnosed accurately. The experimental results show that the model can quickly and accurately recognize the rolling bearing fault,and is proven to be stable and efficient. Through the analysis and contrast with SVM,the RVM method has more advantages in the field of intelligent fault diagnosis.
引文
[1]Tang W H,Wu Q H.Condition monitoring and assessment of power transformers using computational intelligence[M].New York:Springer-Verlag Press,2011:95-104.
[2]张德明.变压器分接开关状态监测与故障诊断[M].北京:中国电力出版社,2008.
[3]贾嵘,张云,洪刚.基于改进PSO的LSSVM参数优化在变压器故障诊断中的应用[J].电力系统保护与控制,2014(17):121-124.
[4]Fei S W,Zhang X B.Fault diagnosis of power transformer based on support vector machine with genetic algorithm[J].Expert Systems With Applications,2009,36(8):11352-11357.
[5]董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003,23(7):88-92.
[6]Tipping M E.Sparse Bayesian learning and the relevance vector machine[J].Journal of Machine Learning Research,2001,1(3):211-244.
[7]Tipping M.Bayesian inference:An introduction to principles and practice in machine learning[J].Advanced Lectures on Machine Learning,2004,3176:41-62.
[8]刘敏庄.基于贝叶斯网络的电子系统故障诊断方法及应用研究[D].哈尔滨:哈尔滨工业大学,2016.
[9]Nie L,Azarian M H,Keimasi M,et al.Prognostics of ceramic capacitor temperature-humidity-bias reliability using Mahalanobis distance analysis[J].Circuit World,2007,33(3):21-28.
[10]Sun J,Xu W,Feng B.A global search strategy of quantumbehaved particle swarm optimization[C]//IEEE Conference on Cybernetics and Intelligent Systems.IEEE,2004:111-116.
[11]Huang N E,Shen Z,Long S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings Mathematical Physical&Engineering Sciences,1998,454(1971):903-995.
[12]李锋,汤宝平,刘文艺.遗传算法优化最小二乘支持向量机的故障诊断[J].重庆大学学报,2010,33(12):14-20.
[13]赵志国,司传胜.基于多岛遗传算法的铰接车轮边减速器优化设计[J].机械设计与制造,2010(12):213-215.
[14]Cui J,Wang Y.A novel approach of analog circuit fault diagnosis using support vector machines classifier[J].Measurement,2011,44(1):281-289.
[15]Long B,Tian S,Wang H.Diagnostics of filtered analog circuits with tolerance based on LS-SVM using frequency features[J].Journal of Electronic Testing,2012,28(3):291-300.
[16]Samanta B,Nataraj C.Prognostics of machine condition using soft computing[J].Robotics and Computer-Integrated Manufacturing,2008,24(6):816-823.
[17]Widodo A,Yang B S.Machine health prognostics using survival probability and support vector machine[J].Expert Systems with Applications,2011,38(7):8430-8437.
[18]Cherkassky V,Ma Y.Practical selection of SVM parameter and noise estimation for SVM regression[J].Neural Networks,2004,17(1):113-126.
[19]Huang C,Zhang R,Chen Z,et al.Predict potential drug targets from the ion channel proteins based on SVM[J].Journal of Theoretical Biology,2010,262(4):750-756.
[20]Widodo A,Yang B S,Kim E Y,et al.Fault diagnosis of low speed bearing based on acoustic emission signal and multi-class relevance vector machine[J].Nondestructive Testing&Evaluation,2009,24(4):313-328.