Fault diagnosis of planetary gear based on entropy feature fusion of DTCWT and OKFDA

Planetary gears are often used in the key parts of the transmission systems of mechanical equipment, and faults are the main factors that determine the reliability of equipment operation. A fault diagnosis method for planetary gears based on the entropy feature fusion of dual-tree complex wavelet transform (DTCWT) and optimized kernel Fisher discriminant analysis (OKFDA) is proposed. The original vibration signal is decomposed by DTCWT, the frequency band signals are obtained, and the extraction models for the entropy features are built from multiple perspectives according to the definition of entropy theory. But the original entropy features, which are extracted from multiple perspectives, lead to excessive feature dimensions, and there are also many insensitive features that have small effects on the identification of the faults of planetary gears. Feature dimension reduction and sensitive feature extraction were achieved by OKFDA. The effectiveness of OKFDA and the extracted sensitive features were analyzed for the original features with different dimensions. Fault diagnosis for planetary gears can be achieved by analyzing sensitive features accurately.

[1]  Zhi-Bo Zhu,et al.  Fault diagnosis based on imbalance modified kernel Fisher discriminant analysis , 2010 .

[2]  Yaguo Lei,et al.  Fault detection of planetary gearboxes using new diagnostic parameters , 2012 .

[3]  Jie Wang,et al.  Gaussian kernel optimization for pattern classification , 2009, Pattern Recognit..

[4]  Gerhard Tutz,et al.  Improved methods for the imputation of missing data by nearest neighbor methods , 2015, Comput. Stat. Data Anal..

[5]  Pan Lin,et al.  Dual-Tree Complex Wavelet Transform and Image Block Residual-Based Multi-Focus Image Fusion in Visual Sensor Networks , 2014, Sensors.

[6]  Jun Ye,et al.  Fault diagnosis of turbine based on fuzzy cross entropy of vague sets , 2009, Expert Syst. Appl..

[7]  Pasi Luukka,et al.  Feature selection using fuzzy entropy measures with similarity classifier , 2011, Expert Syst. Appl..

[8]  Feng Zhao,et al.  Learning kernel parameters for kernel Fisher discriminant analysis , 2013, Pattern Recognit. Lett..

[9]  Junhong Li,et al.  Improved kernel fisher discriminant analysis for fault diagnosis , 2009, Expert Syst. Appl..

[10]  Zhipeng Feng,et al.  Complex signal analysis for planetary gearbox fault diagnosis via shift invariant dictionary learning , 2016 .

[11]  Yitao Liang,et al.  A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM , 2015 .

[12]  林梦雷,et al.  A new nearest neighbor classifier via fusing neighborhood information , 2014 .

[13]  Deren Kong,et al.  Use of modified sample entropy measurement to classify ventricular tachycardia and fibrillation , 2011 .

[14]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Pawel Chudzian,et al.  Evaluation measures for kernel optimization , 2012, Pattern Recognit. Lett..

[16]  Hu Xiao,et al.  Research of weak fault feature information extraction of planetary gear based on ensemble empirical mode decomposition and adaptive stochastic resonance , 2015 .

[17]  Wei Liu,et al.  Image denoising using trivariate prior model in nonsubsampled dual-tree complex contourlet transform domain and non-local means filter in spatial domain , 2013 .

[18]  Zhipeng Feng,et al.  Complex signal analysis for wind turbine planetary gearbox fault diagnosis via iterative atomic decomposition thresholding , 2014 .

[19]  Nello Cristianini,et al.  Learning the Kernel Matrix with Semidefinite Programming , 2002, J. Mach. Learn. Res..

[20]  Wenjian Wang,et al.  An efficient Gaussian kernel optimization based on centered kernel polarization criterion , 2015, Inf. Sci..

[21]  J. Stoitsis,et al.  Assessment of carotid atherosclerosis from B-mode ultrasound images using directional multiscale texture features , 2012 .

[22]  Lin Cheng,et al.  The Health Monitoring Method of Concrete Dams Based on Ambient Vibration Testing and Kernel Principle Analysis , 2015 .

[23]  Zhao Zhang,et al.  Fault diagnosis of rolling element bearings via discriminative subspace learning: Visualization and classification , 2014, Expert Syst. Appl..

[24]  Li Jiang,et al.  Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis , 2013 .

[25]  Yu-Liang Chung,et al.  A looseness identification approach for rotating machinery based on post-processing of ensemble empirical mode decomposition and autoregressive modeling , 2012 .

[26]  P. K. Kankar,et al.  A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings , 2015 .

[27]  Diego H. Milone,et al.  Wavelet shrinkage using adaptive structured sparsity constraints , 2015, Signal Process..