Fault diagnosis of wind turbine bearing based on stochastic subspace identification and multi-kernel support vector machine
|
摘要
In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification(SSI) and multi-kernel support vector machine(MSVM) is proposed. Firstly, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine(SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K-means clustering, fuzzy means clustering and traditional SVM.
In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification(SSI) and multi-kernel support vector machine(MSVM) is proposed. Firstly, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine(SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K-means clustering, fuzzy means clustering and traditional SVM.
In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification(SSI) and multi-kernel support vector machine(MSVM) is proposed. Firstly, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine(SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K-means clustering, fuzzy means clustering and traditional SVM.
引文
[1] Hang J, Zhang JZ, Cheng M(2014)Fault diagnosis of wind turbine based on multi-sensors information fusion technology.IET Renew Power Gener 8(3):289-298
[2] Wilkinson M,Darnell B,Delft TV et al(2014)Comparison of methods for wind turbine condition monitoring with SCAD A data. IET Renew Power Gener 8(4):390-397
[3] Bindi C, Matthews PC, Tavner PJ(2015)Automated on-line fault prognosis for wind turbine pitch system using supervisory control and data acquisition. IET Renew Power Gener9(5):503-513
[4] Djurovic S, Ceartree CJ, Tavner PJ et al(2012)Condition monitoring of wing turbine induction generators with rotor electrical asymmetry. IET Renew Power Gener 6(4):207-216
[5] Hu AJ, Yan XA, Xiang L(2015)A new wind turbine fault diagnosis method based on ensemble intrinsic time-scale decomposition and WPT-fractal dimension. Renew Energy83:767-778
[6] Gong X,Qiao W(2013)Bearing fault diagnosis for direct-drive wind turbine via current-demodulated signals. IEEE Trans Ind Electron 60(8):3419-3428
[7] Chen JL, Pan J, Li ZP et al(2016)Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals. Renew Energy 89:80-92
[8] Sang TH(2010)The self-quality of discrete short-time Fourier transform and its applications. IEEE Trans Signal Process58(2):604-612
[9] Riera-Guaso M, Antonino-Daviu JA, Pineda-Sanchez M et al(2008)A general approach for the transient detection of slipdependent fault components based on the discrete wavelet transform. IEEE Trans Ind Electron 55(12):4167-4680
[10] Boashash B(1998)Note on the use of the Wigner distribution for time-frequency analysis. IEEE Trans Acoust Speech Signal Process 36(9):1518-1521
[11] Rai VK,Mohanty AR(2007)Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform. Mech Syst Signal Process 21:2607-2615
[12] An XL, Jiang DX, Li SH et al(2011)Application of the ensemble empirical mode decomposition and Hilbert transform to pedestal looseness study of direct-drive wind turbine.Energy30:5508-5520
[13] Liu CL,Wu YJ,Zhen CG(2015)Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering. Proc CSEE 35(13):3358-3365
[14] Zhao MY,Xu G(2017)Feature extraction for vibration signals of power transformer based on empirical wavelet transform.Autom Electr Power Syst 41(20):63-69
[15] Bassevill M, Benveniste A,Gach B et al(1993)In situ damage monitoring in vibration mechanics:diagnostics and predictive maintenance. Mech Syst Signal Process 7(5):401-423
[16] Bassevill M, Abdelghani M, Benveniste A(2000)Subspace based fault detection algorithms for vibration monitoring.Automatica 36(1):101-109
[17] Zhou N, Pierre JW, Hauer JF(2006)Initial results in power system identification from injected probing signals using a subspace method. IEEE Trans Power Syst 21(3):1296-1302
[18] Peeters B, Roeck GD(1999)Reference-based stochastic subspace identification for output only modal analysis. Mech Syst Signal Process 13(6):855-878
[19] Nezam SA, Vaithianathan V(2014)Electromechanical mode estimation using recursive adaptive stochastic subspace identification. IEEE Trans Power Syst 29(1):349-358
[20] Gryllias KC, Antoniadis IA(2012)A support vector machine approach based on physical model training for rolling element bearing fault detection in industrial environments. Eng Appl Artif Intell 25(2):326-344
[21] Kang SQ, Li ZQ, Yang GX et al(2014)Application of wavelet packet-locally linear embedding algorithm in rolling bearing fault degree recognization. Chin J Sci Instrum 35(3):614-619
[22] Yao YF, Zhang X(2013)Fault diagnosis approach for roller bearing based on EMD momentary energy entropy and SVM.J Electron Meas Instrum 27(10):957-962
[23] Chen FF, Tang BP, Song T et al(2014)Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization. Measurement 47:576-590
[24] Shen ZJ, Chen XF, Zhang XL et al(2012)A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM. Measurement 45:30-40
[25] Huang J,Hu XG,Geng X(2011)An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine. Electr Power Syst Res 81(2):400-407
[2] Wilkinson M,Darnell B,Delft TV et al(2014)Comparison of methods for wind turbine condition monitoring with SCAD A data. IET Renew Power Gener 8(4):390-397
[3] Bindi C, Matthews PC, Tavner PJ(2015)Automated on-line fault prognosis for wind turbine pitch system using supervisory control and data acquisition. IET Renew Power Gener9(5):503-513
[4] Djurovic S, Ceartree CJ, Tavner PJ et al(2012)Condition monitoring of wing turbine induction generators with rotor electrical asymmetry. IET Renew Power Gener 6(4):207-216
[5] Hu AJ, Yan XA, Xiang L(2015)A new wind turbine fault diagnosis method based on ensemble intrinsic time-scale decomposition and WPT-fractal dimension. Renew Energy83:767-778
[6] Gong X,Qiao W(2013)Bearing fault diagnosis for direct-drive wind turbine via current-demodulated signals. IEEE Trans Ind Electron 60(8):3419-3428
[7] Chen JL, Pan J, Li ZP et al(2016)Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals. Renew Energy 89:80-92
[8] Sang TH(2010)The self-quality of discrete short-time Fourier transform and its applications. IEEE Trans Signal Process58(2):604-612
[9] Riera-Guaso M, Antonino-Daviu JA, Pineda-Sanchez M et al(2008)A general approach for the transient detection of slipdependent fault components based on the discrete wavelet transform. IEEE Trans Ind Electron 55(12):4167-4680
[10] Boashash B(1998)Note on the use of the Wigner distribution for time-frequency analysis. IEEE Trans Acoust Speech Signal Process 36(9):1518-1521
[11] Rai VK,Mohanty AR(2007)Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform. Mech Syst Signal Process 21:2607-2615
[12] An XL, Jiang DX, Li SH et al(2011)Application of the ensemble empirical mode decomposition and Hilbert transform to pedestal looseness study of direct-drive wind turbine.Energy30:5508-5520
[13] Liu CL,Wu YJ,Zhen CG(2015)Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering. Proc CSEE 35(13):3358-3365
[14] Zhao MY,Xu G(2017)Feature extraction for vibration signals of power transformer based on empirical wavelet transform.Autom Electr Power Syst 41(20):63-69
[15] Bassevill M, Benveniste A,Gach B et al(1993)In situ damage monitoring in vibration mechanics:diagnostics and predictive maintenance. Mech Syst Signal Process 7(5):401-423
[16] Bassevill M, Abdelghani M, Benveniste A(2000)Subspace based fault detection algorithms for vibration monitoring.Automatica 36(1):101-109
[17] Zhou N, Pierre JW, Hauer JF(2006)Initial results in power system identification from injected probing signals using a subspace method. IEEE Trans Power Syst 21(3):1296-1302
[18] Peeters B, Roeck GD(1999)Reference-based stochastic subspace identification for output only modal analysis. Mech Syst Signal Process 13(6):855-878
[19] Nezam SA, Vaithianathan V(2014)Electromechanical mode estimation using recursive adaptive stochastic subspace identification. IEEE Trans Power Syst 29(1):349-358
[20] Gryllias KC, Antoniadis IA(2012)A support vector machine approach based on physical model training for rolling element bearing fault detection in industrial environments. Eng Appl Artif Intell 25(2):326-344
[21] Kang SQ, Li ZQ, Yang GX et al(2014)Application of wavelet packet-locally linear embedding algorithm in rolling bearing fault degree recognization. Chin J Sci Instrum 35(3):614-619
[22] Yao YF, Zhang X(2013)Fault diagnosis approach for roller bearing based on EMD momentary energy entropy and SVM.J Electron Meas Instrum 27(10):957-962
[23] Chen FF, Tang BP, Song T et al(2014)Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization. Measurement 47:576-590
[24] Shen ZJ, Chen XF, Zhang XL et al(2012)A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM. Measurement 45:30-40
[25] Huang J,Hu XG,Geng X(2011)An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine. Electr Power Syst Res 81(2):400-407