基于改进果蝇算法优化WKELM的医疗滚动轴承故障诊断技术研究
|
摘要
针对传统小波核极限学习机(Extreme Learning Machine,ELM)应用于医疗滚动轴承故障诊断中识别精度不高且训练速度慢的一系列问题的出现,并针对性的想出一种更好地对滚动转轴发生的故障进行识别的办法,通过对小波核极限学习机算法进行改进的方法;该方法运用改进果蝇算法(LGMS-Fruit-flying Optimization Algorithm,LGMS-FOA)优化小波核极限学习机中的正则化系数和小波核函数中的参数;采用的方法是变分模态分解(Variational Mode Decomposition,VMD),通过这种方法能够对滚动轴承的故障信号分解为含有故障信息的各模态分量从而提取到故障特征;通过与其他三种算法的实验结果对比证明,基于LGMS-FOA-WKELM的滚动轴承故障诊断方法的识别精度更高且训练时间更短。
The regularization coefficient and the parameters in the wavelet kernel function of the rolling bearing fault diagnosis based on the extreme learning machine will affect the classification effect of WKELM.A fault identification method based on improved FOA algorithm to optimize WKLEM parameters is proposed.The method uses VMD to decompose the fault signal of the rolling bearing to obtain the modal components containing the fault information,and uses SVD to obtain each modal singular value as the feature vector.The LGMS improved FOA algorithm was introduced to optimize the relevant parameters of WKELM,and the optimal rolling bearing fault diagnosis classifier was constructed.The experimental comparison results show that the LGMS-FOA-WKELM method not only has high recognition accuracy,but also has shorter training time and stronger stability.
The regularization coefficient and the parameters in the wavelet kernel function of the rolling bearing fault diagnosis based on the extreme learning machine will affect the classification effect of WKELM.A fault identification method based on improved FOA algorithm to optimize WKLEM parameters is proposed.The method uses VMD to decompose the fault signal of the rolling bearing to obtain the modal components containing the fault information,and uses SVD to obtain each modal singular value as the feature vector.The LGMS improved FOA algorithm was introduced to optimize the relevant parameters of WKELM,and the optimal rolling bearing fault diagnosis classifier was constructed.The experimental comparison results show that the LGMS-FOA-WKELM method not only has high recognition accuracy,but also has shorter training time and stronger stability.
引文
[1]张诗慧,种银保,肖晶晶,等.基于LabVIEW的医疗设备故障智能诊断系统[J].仪表技术与传感器,2018(4):98-103.
[2]钱林,康敏,傅秀清,等.基于VMD的自适应形态学在轴承故障诊断中的应用[J].振动与冲击,2017(3):227-233.
[3]Zhong L,Tang G.Preface,special issue on combinatorial optimization in health care.J Comb Optim,2015,30(4):839-840.
[4]Zhong L,Luo S,Wu L,et al.A two-stage approach for surgery scheduling[J].J CombOptim,2014,27(3):545-556.
[5]Park S,Lee J.Stochastic Opposition-Based Learning Using a Beta Distribution in Differential Evolution[J].IEEE Transactions on Cybernetics(S2168-2267),2016,46(10):2184-2194.
[6]Tang J,Deng C,Guang G B.Extreme Learning Machine for Multilayer Perceptron[J].IEEE Transactions on Neural Networks&Learning Systems(S2162-237X),2016,27(4):809-821.
[7]Mirjalili S,Mirjalili M,Lewis A.Grey Wolf Optimizer[J].Advances in Engineering Software(S0965-9978),2014,69(3):46-61.
[8]Wen J,Gao H,Li S,et al.Fault Diagnosis of Ball Bearings using Synchrosqueezed Wavelet Transforms and SVM Prognostics and System Health Management Conference(PHM)[J].USA:IEEE,2015:1-6.
[9]Dragomiretskiy K,Zosso D.Variational Mode Decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[10]Huang G,Huang G B,Song S,et al.Trends in extreme learning machines:a review[J].Neural Networks,2015,61(C):32.
[11]Feng G,Huang G B,Lin Q,et al.Error minimized extreme learning machine with growth of hidden nodes and incremental learning[J].IEEE Transactions on Neural Networks,2009,20(8):1352-7.
[12]Liu N,Wang H.Ensemble Based Extreme Learning Machine[J].IEEE Signal Processing Letters,2010,17(8):754-757.
[2]钱林,康敏,傅秀清,等.基于VMD的自适应形态学在轴承故障诊断中的应用[J].振动与冲击,2017(3):227-233.
[3]Zhong L,Tang G.Preface,special issue on combinatorial optimization in health care.J Comb Optim,2015,30(4):839-840.
[4]Zhong L,Luo S,Wu L,et al.A two-stage approach for surgery scheduling[J].J CombOptim,2014,27(3):545-556.
[5]Park S,Lee J.Stochastic Opposition-Based Learning Using a Beta Distribution in Differential Evolution[J].IEEE Transactions on Cybernetics(S2168-2267),2016,46(10):2184-2194.
[6]Tang J,Deng C,Guang G B.Extreme Learning Machine for Multilayer Perceptron[J].IEEE Transactions on Neural Networks&Learning Systems(S2162-237X),2016,27(4):809-821.
[7]Mirjalili S,Mirjalili M,Lewis A.Grey Wolf Optimizer[J].Advances in Engineering Software(S0965-9978),2014,69(3):46-61.
[8]Wen J,Gao H,Li S,et al.Fault Diagnosis of Ball Bearings using Synchrosqueezed Wavelet Transforms and SVM Prognostics and System Health Management Conference(PHM)[J].USA:IEEE,2015:1-6.
[9]Dragomiretskiy K,Zosso D.Variational Mode Decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[10]Huang G,Huang G B,Song S,et al.Trends in extreme learning machines:a review[J].Neural Networks,2015,61(C):32.
[11]Feng G,Huang G B,Lin Q,et al.Error minimized extreme learning machine with growth of hidden nodes and incremental learning[J].IEEE Transactions on Neural Networks,2009,20(8):1352-7.
[12]Liu N,Wang H.Ensemble Based Extreme Learning Machine[J].IEEE Signal Processing Letters,2010,17(8):754-757.