Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal

There are growing demands for condition-based monitoring of gearboxes, and techniques to improve the reliability, effectiveness and accuracy for fault diagnosis are considered valuable contributions. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance in the diagnosis system. The main aim of this research is to propose a multi-stage feature selection mechanism for selecting the best set of condition parameters on the time, frequency and time-frequency domains, which are extracted from vibration signals for fault diagnosis purposes in gearboxes. The selection is based on genetic algorithms, proposing in each stage a new subset of the best features regarding the classifier performance in a supervised environment. The selected features are augmented at each stage and used as input for a neural network classifier in the next step, while a new subset of feature candidates is treated by the selection process. As a result, the inherent exploration and exploitation of the genetic algorithms for finding the best solutions of the selection problem are locally focused. The approach is tested on a dataset from a real test bed with several fault classes under different running conditions of load and velocity. The model performance for diagnosis is over 98%.

[1]  Paola Zuccolotto,et al.  Variable Selection Using Random Forests , 2006 .

[2]  B. Samanta,et al.  Artificial neural networks and genetic algorithms for gear fault detection , 2004 .

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

[4]  Jing Yuan,et al.  Gearbox fault diagnosis of rolling mills using multiwavelet sliding window neighboring coefficient denoising and optimal blind deconvolution , 2009 .

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

[6]  B. Samanta,et al.  Gear fault detection using artificial neural networks and support vector machines with genetic algorithms , 2004 .

[7]  Barbara Hammer,et al.  Neural Smithing – Supervised Learning in Feedforward Artificial Neural Networks , 2001, Pattern Analysis & Applications.

[8]  Ahmad Ghasemloonia,et al.  Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis , 2011, Expert Syst. Appl..

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Anil K. Jain,et al.  Dimensionality reduction using genetic algorithms , 2000, IEEE Trans. Evol. Comput..

[11]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

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

[13]  Yaguo Lei,et al.  A new approach to intelligent fault diagnosis of rotating machinery , 2008, Expert Syst. Appl..

[14]  C. Gargour,et al.  A short introduction to wavelets and their applications , 2009, IEEE Circuits and Systems Magazine.

[15]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[16]  Wilson Wang,et al.  A Wavelet Spectrum Technique for Machinery Fault Diagnosis , 2011 .

[17]  G. N. Marichal,et al.  Extraction of rules for faulty bearing classification by a Neuro-Fuzzy approach , 2011 .

[18]  Peter W. Tse,et al.  A One-Versus-All Class Binarization Strategy for Bearing Diagnostics of Concurrent Defects , 2014, Sensors.

[19]  C. C. Wang,et al.  Gear Fault Diagnosis by Using Wavelet Neural Networks , 2007, ISNN.

[20]  Hui Li,et al.  Gear fault detection and diagnosis under speed-up condition based on order cepstrum and radial basis function neural network , 2009 .

[21]  K. I. Ramachandran,et al.  Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN) , 2010, Expert Syst. Appl..

[22]  Diego Cabrera,et al.  Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis , 2015, Neurocomputing.

[23]  Lalit M. Patnaik,et al.  Genetic algorithms: a survey , 1994, Computer.

[24]  Kesheng Wang,et al.  Application of computed order tracking, Vold–Kalman filtering and EMD in rotating machine vibration , 2011 .

[25]  K. Manivannan,et al.  A Gear Fault Identification using Wavelet Transform, Rough set Based GA, ANN and C4.5 Algorithm , 2014 .

[26]  K. R. Al-Balushi,et al.  Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection , 2003 .

[27]  Hua-Shu Dou,et al.  Vibration-Based Condition Monitoring , 2013 .

[28]  Radoslaw Zimroz,et al.  Dimensionality reduction via variables selection – Linear and nonlinear approaches with application to vibration-based condition monitoring of planetary gearbox , 2014 .

[29]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[30]  K. I. Ramachandran,et al.  Fault diagnosis of spur bevel gear box using artificial neural network (ANN), and proximal support vector machine (PSVM) , 2010, Appl. Soft Comput..

[31]  Claudia Beleites,et al.  Validation of soft classification models using partial class memberships: An extended concept of sensitivity & co. applied to grading of astrocytoma tissues , 2013, 1301.0264.

[32]  Nour El Islem Karabadji,et al.  Improved decision tree construction based on attribute selection and data sampling for fault diagnosis in rotating machines , 2014, Eng. Appl. Artif. Intell..

[33]  Hao Tian,et al.  A new feature extraction and selection scheme for hybrid fault diagnosis of gearbox , 2011, Expert Syst. Appl..

[34]  Chuan Li,et al.  Time-frequency signal analysis for gearbox fault diagnosis using a generalized synchrosqueezing transform , 2012 .

[35]  Sabrina Hirsch,et al.  Digital Signal Processing A Computer Based Approach , 2016 .

[36]  Hongxia Pan,et al.  A Fault Diagnosis Method under Varying Rotate Speed Conditions Based on Auxiliary Particle Filter , 2013, ICONIP.

[37]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[38]  Nouredine Ouelaa,et al.  Gears and Bearings Combined Faults Detection Using Hilbert Transform and Wavelet Multiresolution Analysis , 2012 .

[39]  Robert X. Gao,et al.  Wavelets for fault diagnosis of rotary machines: A review with applications , 2014, Signal Process..

[40]  Albert Y. Zomaya,et al.  Ensemble-Based Wrapper Methods for Feature Selection and Class Imbalance Learning , 2013, PAKDD.

[41]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[42]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[43]  Yaguo Lei,et al.  A multidimensional hybrid intelligent method for gear fault diagnosis , 2010, Expert Syst. Appl..

[44]  Farzad Sadjadi,et al.  Comparison of fitness scaling functions in genetic algorithms with applications to optical processing , 2004, SPIE Optics + Photonics.

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