Fault diagnosis for planetary gearboxes using multi-criterion fusion feature selection framework

Feature selection has been used to achieve dimension reduction in the field of fault diagnosis. This article introduces a multi-criterion fusion framework for feature selection that takes into account three aspects of features: effectiveness, correlation, and classification performance. This framework enables a more comprehensive evaluation of features than does a single criterion. The proposed framework is implemented using five effectiveness criteria and a correlation criterion. It is used to diagnose eight failure modes of a planetary gearbox. The experimental results demonstrate that the proposed multi-criterion framework outperforms many well-studied single criteria.

[1]  Son Doan,et al.  The Use of Multi-Criteria in Feature Selection to Enhance Text Categorization , 2005 .

[2]  J. Rafiee,et al.  INTELLIGENT CONDITION MONITORING OF A GEARBOX USING ARTIFICIAL NEURAL NETWORK , 2007 .

[3]  Radoslaw Zimroz,et al.  Vibration condition monitoring of planetary gearbox under varying external load , 2009 .

[4]  Weizhong Yan,et al.  Fusion in multi-criterion feature ranking , 2007, 2007 10th International Conference on Information Fusion.

[5]  Ming J. Zuo,et al.  Vibration-based fault diagnosis of slurry pump impellers using neighbourhood rough set models , 2010 .

[6]  Thy-Hou Lin,et al.  Implementing the Fisher's Discriminant Ratio in a k-Means Clustering Algorithm for Feature Selection and Data Set Trimming , 2004, Journal of Chemical Information and Modeling.

[7]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[8]  Ming J. Zuo,et al.  Feature selection for damage degree classification of planetary gearboxes using support vector machine , 2011 .

[9]  Xiaomin Zhao,et al.  EMD, Ranking Mutual Information and PCA Based Condition Monitoring , 2010 .

[10]  Ming J. Zuo,et al.  Classification of gear damage levels in planetary gearboxes , 2011, 2011 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings.

[11]  Radoslaw Zimroz,et al.  A new feature for monitoring the condition of gearboxes in non-stationary operating conditions , 2009 .

[12]  Yongming Li,et al.  Sequential multi-criteria feature selection algorithm based on agent genetic algorithm , 2008, Applied Intelligence.

[13]  Ming J. Zuo,et al.  A Gaussian radial basis function based feature selection algorithm , 2011, 2011 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings.

[14]  Robert B. Randall,et al.  Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine , 2009 .

[15]  Yaguo Lei,et al.  Gear crack level identification based on weighted K nearest neighbor classification algorithm , 2009 .

[16]  John Wang,et al.  Data Mining: Opportunities and Challenges , 2003 .

[17]  Filiberto Pla,et al.  Supervised feature selection by clustering using conditional mutual information-based distances , 2010, Pattern Recognit..

[18]  Darryll J. Pines,et al.  A review of vibration-based techniques for helicopter transmission diagnostics , 2005 .

[19]  Bor-Chen Kuo,et al.  Kernel Nonparametric Weighted Feature Extraction for Hyperspectral Image Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Filippo Menczer,et al.  Feature selection in data mining , 2003 .

[21]  Xiaomin Zhao,et al.  Diagnosis of artificially created surface damage levels of planet gear teeth using ordinal ranking , 2013 .

[22]  Ming J. Zuo,et al.  Support vector machine based data processing algorithm for wear degree classification of slurry pump systems , 2010 .

[23]  Jay Lee,et al.  A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis , 2011, Expert Syst. Appl..

[24]  Quansheng Jiang,et al.  Machinery fault diagnosis using supervised manifold learning , 2009 .

[25]  Kui Zhang,et al.  Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks , 2011, Neurocomputing.

[26]  Hongbing Xu,et al.  Parameter selection for Gaussian radial basis function in support vector machine classification , 2012, 2012 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering.

[27]  Zili Zhang,et al.  A multi-filter enhanced genetic ensemble system for gene selection and sample classification of microarray data , 2010, BMC Bioinformatics.