混沌粒子群优化RVM的滚动轴承早期故障诊断
|
摘要
为了提高相关向量机在滚动轴承早期故障诊断中的诊断精度,对相关向量机的早期故障输入特征以及相关向量机的参数优化方法进行了研究。首先,以美国Cincinnati大学实测的滚动轴承全寿命振动数据为基础,结合信息熵原理计算振动信号的归一化小波包频带能量及小波信息熵,根据特征参数时间序列的渐进变化趋势,构造相关向量机的早期故障输入样本;其次通过混沌粒子群算法优化相关向量机的核函数参数;最后,利用优化后的相关向量机模型实现对机械设备的早期故障诊断。实际轴承的故障诊断实验结果表明,方法提取的早期故障特征敏感性更好,优化的相关向量机早期故障的模式分类性能也大大提高,验证了该方法对早期故障诊断的有效性和优势。
In order to improve the accuracy of relevance vector machine( RVM) in mechanical equipment early fault diagnosis,the early fault feature extraction method and the RVM parameters' optimization method are studied in this research. First,The normalized wavelet packet energy feature and wavelet information entropy were calculated based on the whole life vibration data of rolling bearings measured by American Cincinnati University. The RVM early fault features were selected according to the characteristics' trend changes. Second,the kernel function parameters of RVM was optimized by chaotic particle swarm optimization. Finally,the early fault diagnosis of mechanical equipment is realized by using the optimized relevance vector machine. The experimental results show that the proposed method is more sensitive to early fault features. The performance of optimized RVM in early fault pattern classification is also greatly improved,which verifies the effectiveness and advantages of the proposed method for early fault diagnosis.
In order to improve the accuracy of relevance vector machine( RVM) in mechanical equipment early fault diagnosis,the early fault feature extraction method and the RVM parameters' optimization method are studied in this research. First,The normalized wavelet packet energy feature and wavelet information entropy were calculated based on the whole life vibration data of rolling bearings measured by American Cincinnati University. The RVM early fault features were selected according to the characteristics' trend changes. Second,the kernel function parameters of RVM was optimized by chaotic particle swarm optimization. Finally,the early fault diagnosis of mechanical equipment is realized by using the optimized relevance vector machine. The experimental results show that the proposed method is more sensitive to early fault features. The performance of optimized RVM in early fault pattern classification is also greatly improved,which verifies the effectiveness and advantages of the proposed method for early fault diagnosis.
引文
[1]张云强,张培林,王怀光,等.基于双时域微弱故障特征增强的轴承早期故障智能识别[J].机械工程学报,2016,52(21):96-103.ZHANG Y Q,ZHANG P L,WANG H G,et al.Rolling bearing early fault intelligence recognition based on weak fault feature enhancement in time-time domain[J].Journal of Mechanical Engineering,2016,52(21):96-103.
[2]巩晓赟,王宏超,杜文辽.EEMD方法在转子碰摩故障诊断中的研究[J].电子测量与仪器学报,2017,31(3):415-421.GONG X Y,WAND H CH,DU W L.Research on EEMD in rub-impact fault diagnosis of rotor system[J].Journal of Electronic Measurement and Instrumentation,2017,31(3):415-421.
[3]WANG D,ZHAO Y,YI C,et al.Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings[J].Mechanical Systems and Signal Processing,2018(101):292-308.
[4]刘晓东,刘朦月,陈寅生,等.EEMD-PE与M-RVM相结合的轴承故障诊断方法[J].哈尔滨工业大学学报,2017,49(9):122-128.LIU X D,LIU M Y,CHEN Y SH,et al.Rolling bearing fault diagnosis based on EEMD-PE coupled with M-RVM[J].Tournal of Harbin Institute of Technology,2017,49(9):122-128.
[5]赵煦,刘晓航,孟永鹏,等.采用小波包树能量矩阵奇异值分解的局部放电模式识别[J].西安交通大学学报,2017,51(8):116-121.ZHAO X,LIU X H,MENG Y P,et al.Partial discharge pattern classification by singular value decomposition of wavelet packet energy features[J].Journal of Xi’an Jiaotong University,2017,51(8):116-121.
[6]SHAO H D,JIANG H K,WANG F,et al.Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J].ISA Transactions,2017(69):187-201.
[7]LIU D T,ZHOU J B,PAN D W,et al.Lithium-ion battery remaining useful life estimation with an optimized relevance vector machine algorithm with incremental learning[J].Measurement,2015(63):143-151.
[8]ANDRIYAS T,ANDRIYAS S.Relevance vector machines as a tool for forecasting geomagnetic storms during years 1996-2007[J].Journal of Atmospheric and Solar-Terrestrial Physics,2015(125-126):10-20.
[9]ZHOU Y,ZHAO H M,PAN X Y.Deception detecting from speech signal using relevance vector machine and non-linear dynamics features[J].Neurocomputing,2015(151):1042-1052.
[10]HE S M,XIAO L,WANG Y L.A novel fault diagnosis method based on optimal relevance vector machine[J].Neurocomputing,2017(267):651-663.
[11]唐贤伦,程祥,汪斌全.采用多Agent混沌粒子群算法的配电网重构[J].电力系统及其自动化学报,2015,27(3):17-23.TANG X L,CHENG X,WANG B Q.Distribution network reconfiguration adopting chaos particle swarm algorithm of multi-agent system[J].Proceedings of the CSU-EPSA,2015,27(3):17-23.
[12]CHEN F F,TANG B P,SONG T,et al.Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization[J].Measurement,2014(47)576-590.
[13]孙曙光,于晗,杜太行,等.基于多特征融合与改进QPSO-RVM的万能式断路器故障振声诊断方法[J].电工技术学报,2017,32(19):107-117.SUN SH G,YU H,DU T H,et al.Vibration and acoustic joint fault diagnosis of conventional circuit breaker based on multi-feature fusion and improved QPSO-RVM[J].Transactions of China Electrotechnical Society,2017,32(19):107-117.
[14]ZHAO F Q,LI G Q,YANG C,et al.A humancomputer cooperative particle swarm optimization based immune algorithm for layout design[J].Neurocomputing,2014(132):68-78.
[15]MOJTAB S,BAMAKAN H,WANG H D,et al.An effective intrusion detection framework based on MCLP/SVM optimized by time-varying chaos particle swarm optimization[J].Neurocomputing,2016(199):90-102.
[16]QIN Q D,CHENG S,CHU X H,et al.Solving nonconvex/non-smooth economic load dispatch problems via an enhanced particle swarm optimization[J].Applied Soft Computing,2017(59):229-242.
[2]巩晓赟,王宏超,杜文辽.EEMD方法在转子碰摩故障诊断中的研究[J].电子测量与仪器学报,2017,31(3):415-421.GONG X Y,WAND H CH,DU W L.Research on EEMD in rub-impact fault diagnosis of rotor system[J].Journal of Electronic Measurement and Instrumentation,2017,31(3):415-421.
[3]WANG D,ZHAO Y,YI C,et al.Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings[J].Mechanical Systems and Signal Processing,2018(101):292-308.
[4]刘晓东,刘朦月,陈寅生,等.EEMD-PE与M-RVM相结合的轴承故障诊断方法[J].哈尔滨工业大学学报,2017,49(9):122-128.LIU X D,LIU M Y,CHEN Y SH,et al.Rolling bearing fault diagnosis based on EEMD-PE coupled with M-RVM[J].Tournal of Harbin Institute of Technology,2017,49(9):122-128.
[5]赵煦,刘晓航,孟永鹏,等.采用小波包树能量矩阵奇异值分解的局部放电模式识别[J].西安交通大学学报,2017,51(8):116-121.ZHAO X,LIU X H,MENG Y P,et al.Partial discharge pattern classification by singular value decomposition of wavelet packet energy features[J].Journal of Xi’an Jiaotong University,2017,51(8):116-121.
[6]SHAO H D,JIANG H K,WANG F,et al.Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J].ISA Transactions,2017(69):187-201.
[7]LIU D T,ZHOU J B,PAN D W,et al.Lithium-ion battery remaining useful life estimation with an optimized relevance vector machine algorithm with incremental learning[J].Measurement,2015(63):143-151.
[8]ANDRIYAS T,ANDRIYAS S.Relevance vector machines as a tool for forecasting geomagnetic storms during years 1996-2007[J].Journal of Atmospheric and Solar-Terrestrial Physics,2015(125-126):10-20.
[9]ZHOU Y,ZHAO H M,PAN X Y.Deception detecting from speech signal using relevance vector machine and non-linear dynamics features[J].Neurocomputing,2015(151):1042-1052.
[10]HE S M,XIAO L,WANG Y L.A novel fault diagnosis method based on optimal relevance vector machine[J].Neurocomputing,2017(267):651-663.
[11]唐贤伦,程祥,汪斌全.采用多Agent混沌粒子群算法的配电网重构[J].电力系统及其自动化学报,2015,27(3):17-23.TANG X L,CHENG X,WANG B Q.Distribution network reconfiguration adopting chaos particle swarm algorithm of multi-agent system[J].Proceedings of the CSU-EPSA,2015,27(3):17-23.
[12]CHEN F F,TANG B P,SONG T,et al.Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization[J].Measurement,2014(47)576-590.
[13]孙曙光,于晗,杜太行,等.基于多特征融合与改进QPSO-RVM的万能式断路器故障振声诊断方法[J].电工技术学报,2017,32(19):107-117.SUN SH G,YU H,DU T H,et al.Vibration and acoustic joint fault diagnosis of conventional circuit breaker based on multi-feature fusion and improved QPSO-RVM[J].Transactions of China Electrotechnical Society,2017,32(19):107-117.
[14]ZHAO F Q,LI G Q,YANG C,et al.A humancomputer cooperative particle swarm optimization based immune algorithm for layout design[J].Neurocomputing,2014(132):68-78.
[15]MOJTAB S,BAMAKAN H,WANG H D,et al.An effective intrusion detection framework based on MCLP/SVM optimized by time-varying chaos particle swarm optimization[J].Neurocomputing,2016(199):90-102.
[16]QIN Q D,CHENG S,CHU X H,et al.Solving nonconvex/non-smooth economic load dispatch problems via an enhanced particle swarm optimization[J].Applied Soft Computing,2017(59):229-242.