基于EEMD和CS-SVM的滚动轴承故障诊断研究
|
摘要
针对数据驱动的滚动轴承故障诊断大多采用支持向量机进行分类,而传统支持向量机的分类方法容易陷入局部最优,无法准确进行故障诊断的问题,对滚动轴承振动信号的特征选择和支持向量机的优化方法进行了研究。分析了粒子群算法优化支持向量机和遗传算法优化支持向量机的不足;基于莱维飞行的布谷鸟搜索算法,引入了一种对支持向量机的参数进行寻优的方法,用于提高滚动轴承故障诊断的识别准确率;该方法首先使用集合经验模态分解对信号数据进行了处理,然后计算本征模态函数的均方根作为特征向量,输入布谷鸟搜索算法优化的支持向量机;最后进行了训练和测试。研究结果表明:利用该方法对实测信号进行分析和诊断,可以准确地识别故障发生的位置以及严重程度;通过与传统优化方法进行对比,验证了该算法的优越性。
Aiming at the problem that in the optimization of support vector machines,data-driven rolling bearing fault diagnosis,most of them are classified by support vector machine,however,the traditional support vector machine classification method is easy to fall into local optimum,and it is impossible to carry out fault diagnosis accurately,the feature selection of rolling bearing vibration signal and the optimization method of support vector machine were studied. The disadvantages of the support vector machine optimization by using genetic algorithm and particle swarm optimization were pointed out. In order to improve the accuracy of rolling bearing fault diagnosis,a cuckoo search algorithm based on Levy flight was introduced to find the optimal parameters of support vector machine. First,ensemble empirical mode decomposition was used to process signal data,and then the root mean square of the intrinsic mode function was put into the support vector machine optimized by cuckoo search algorithm to train and test this model. The results indicate that the proposed method can be used to analyze and diagnose the measured signals,and the location and severity of the faults can be accurately identified. The superiority of the algorithm is verified by comparison with traditional optimization methods.
Aiming at the problem that in the optimization of support vector machines,data-driven rolling bearing fault diagnosis,most of them are classified by support vector machine,however,the traditional support vector machine classification method is easy to fall into local optimum,and it is impossible to carry out fault diagnosis accurately,the feature selection of rolling bearing vibration signal and the optimization method of support vector machine were studied. The disadvantages of the support vector machine optimization by using genetic algorithm and particle swarm optimization were pointed out. In order to improve the accuracy of rolling bearing fault diagnosis,a cuckoo search algorithm based on Levy flight was introduced to find the optimal parameters of support vector machine. First,ensemble empirical mode decomposition was used to process signal data,and then the root mean square of the intrinsic mode function was put into the support vector machine optimized by cuckoo search algorithm to train and test this model. The results indicate that the proposed method can be used to analyze and diagnose the measured signals,and the location and severity of the faults can be accurately identified. The superiority of the algorithm is verified by comparison with traditional optimization methods.
引文
[1]刘冬.基于振动信号处理的旋转机械故障诊断[D].上海:上海交通大学信息安全工程学院,2010.
[2]司景萍,马继昌,牛家骅,等.基于模糊神经网络的智能故障诊断专家系统[J].振动与冲击,2017,36(4):164-171.
[3]李舜酩,郭海东,李殿荣.振动信号处理方法综述[J].仪器仪表学报,2013,34(8):1907-1915.
[4] 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.
[5] WU Zhao-hua,HUANG N E. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis,2011,1(1):1-41.
[6]ZVOKELJ M,ZUPAN S,PREBIL I. Non-linear multivariate and multiscale monitoring and signal denoising strategy using kernel principal component analysis combined with ensemble empirical mode decomposition method[J]. Mechanical Systems&Signal Processing,2011,25(7):2631-2653.
[7] LEI Y,HE Z,ZI Y. EEMD method and WNN for fault diagnosis of locomotive roller bearings[J]. Expert Systems with Applications,2011,38(6):7334-7341.
[8] ZHOU Y,TAO T,MEI X,et al. Feed-axis gearbox condition monitoring using built-in position sensors and EEMD method[J]. Robotics&Computer Integrated Manufacturing,2011,27(4):785-793.
[9] WANG Y,LI Zhi-hua,WU Chun-hua,et al. A survey of online fault diagnosis for PV module based on BP neural network[J]. Power System Technology,2013,37(8):483-486.
[10] MURALIDHARAN V,SUGUMARAN V. Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump[J]. Measurement,2013,46(1):353-359.
[11] VAPNIK V N. The nature of statistical learning theory[J].Technometrics,2002,8(6):1564-1564.
[12] KONAR P,CHATTOPADHYAY P. Bearing fault detection of induction motor using wavelet and support vector machines(SVMs)[J]. Applied Soft Computing,2011,11(6):4203-4211.
[13] HUANG J,HU X,GENG X. An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J]. Electric Power Systems Research,2011,81(2):400-407.
[14] SAMANTA B. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms[J]. Mechanical Systems&Signal Processing,2004,18(3):625-644.
[15] WIDODO A,YANG B S. Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems&Signal Processing,2008,21(6):2560-2574.
[16]李嫄源,袁梅,王瑶,等. SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(1):99-107.
[17]蒋恩超,傅攀,张思聪.小波包和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.
[18]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.
[19]秦波,刘永亮,王建国,等.基于小波包与奇异值分解的GA-SVM滚动轴承故障诊断方法研究[J].机械设计与制造,2016(6):38-42.
[20]何青,褚东亮,毛新华.基于EEMD和MFFOA-SVM滚动轴承故障诊断[J].中国机械工程,2016,27(9):1191-1197.
[21]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,40(7):10-13.
[22] YANG X S,DEB S. Cuckoo search via lévy flights[C].Na BIC World Congress on Nature&Biologically Inspired Computing,Coimbatore:IEEE,2010.
[23] VISWANATHAN G M,BARTUMEUS F,BULDYREV S V,et al. Lévy flight random searches in biological phenomena[J]. Physica A Statistical Mechanics&Its Applications,2002,314(1):208-213.
[2]司景萍,马继昌,牛家骅,等.基于模糊神经网络的智能故障诊断专家系统[J].振动与冲击,2017,36(4):164-171.
[3]李舜酩,郭海东,李殿荣.振动信号处理方法综述[J].仪器仪表学报,2013,34(8):1907-1915.
[4] 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.
[5] WU Zhao-hua,HUANG N E. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis,2011,1(1):1-41.
[6]ZVOKELJ M,ZUPAN S,PREBIL I. Non-linear multivariate and multiscale monitoring and signal denoising strategy using kernel principal component analysis combined with ensemble empirical mode decomposition method[J]. Mechanical Systems&Signal Processing,2011,25(7):2631-2653.
[7] LEI Y,HE Z,ZI Y. EEMD method and WNN for fault diagnosis of locomotive roller bearings[J]. Expert Systems with Applications,2011,38(6):7334-7341.
[8] ZHOU Y,TAO T,MEI X,et al. Feed-axis gearbox condition monitoring using built-in position sensors and EEMD method[J]. Robotics&Computer Integrated Manufacturing,2011,27(4):785-793.
[9] WANG Y,LI Zhi-hua,WU Chun-hua,et al. A survey of online fault diagnosis for PV module based on BP neural network[J]. Power System Technology,2013,37(8):483-486.
[10] MURALIDHARAN V,SUGUMARAN V. Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump[J]. Measurement,2013,46(1):353-359.
[11] VAPNIK V N. The nature of statistical learning theory[J].Technometrics,2002,8(6):1564-1564.
[12] KONAR P,CHATTOPADHYAY P. Bearing fault detection of induction motor using wavelet and support vector machines(SVMs)[J]. Applied Soft Computing,2011,11(6):4203-4211.
[13] HUANG J,HU X,GENG X. An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J]. Electric Power Systems Research,2011,81(2):400-407.
[14] SAMANTA B. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms[J]. Mechanical Systems&Signal Processing,2004,18(3):625-644.
[15] WIDODO A,YANG B S. Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems&Signal Processing,2008,21(6):2560-2574.
[16]李嫄源,袁梅,王瑶,等. SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(1):99-107.
[17]蒋恩超,傅攀,张思聪.小波包和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.
[18]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.
[19]秦波,刘永亮,王建国,等.基于小波包与奇异值分解的GA-SVM滚动轴承故障诊断方法研究[J].机械设计与制造,2016(6):38-42.
[20]何青,褚东亮,毛新华.基于EEMD和MFFOA-SVM滚动轴承故障诊断[J].中国机械工程,2016,27(9):1191-1197.
[21]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,40(7):10-13.
[22] YANG X S,DEB S. Cuckoo search via lévy flights[C].Na BIC World Congress on Nature&Biologically Inspired Computing,Coimbatore:IEEE,2010.
[23] VISWANATHAN G M,BARTUMEUS F,BULDYREV S V,et al. Lévy flight random searches in biological phenomena[J]. Physica A Statistical Mechanics&Its Applications,2002,314(1):208-213.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |