Gear fault diagnosis using vibration signals based on decision tree assisted intelligent controllers

Gears are one of the most widely used elements in rotary machines for transmitting power and torque. The system is subjected to variable speed and torque which leads to faults in gears. This paper presents two different online condition monitoring systems using fuzzy and artificial neural network (ANN) controller for the fault diagnosis of spur gear. This work is conceived as pattern recognition problem and it consists of four main phases: viz. feature extraction, feature selection using C4.5 algorithm, training of fuzzy and ANN controllers with the selected features. Under feature extraction, statistical features like skewness, standard deviation, variance, root mean square (RMS) value, kurtosis, range, minimum value, maximum value, sum, median and crest factor are considered as features of the signal in the fault diagnostics. These features are extracted from vibration signals of time domain obtained from the experimental setup through a piezoelectric sensor. The vibration signals from the sensor are captured for normal tooth, wear tooth, broken tooth and broken tooth under loading conditions. The controllers are built and tested with representative data and the performance is also discussed.

[1]  Jin Chen,et al.  Neuro-fuzzy Based Condition Prediction of Bearing Health: , 2009 .

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

[3]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on a new hybrid clustering algorithm , 2008 .

[4]  Zhongyuan Su,et al.  Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform , 2011 .

[5]  V. Sugumaran,et al.  Decision tree: A very useful tool in analysing flow-induced vibration data , 2008 .

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

[7]  Hong-Tzer Yang,et al.  Developing a new transformer fault diagnosis system through evolutionary fuzzy logic , 1997 .

[8]  Earl Cox,et al.  The fuzzy systems handbook - a practitioner's guide to building, using, and maintaining fuzzy systems , 1994 .

[9]  K. I. Ramachandran,et al.  Automatic rule learning using decision tree for fuzzy classifier in fault diagnosis of roller bearing , 2007 .

[10]  G. Marichal,et al.  An intelligent system for faulty-bearing detection based on vibration spectra , 2011 .

[11]  Ying Peng,et al.  Current status of machine prognostics in condition-based maintenance: a review , 2010 .

[12]  A. Davies,et al.  Handbook of Condition Monitoring , 1998 .

[13]  Peter A. Flach,et al.  Decision Tree-Based Data Characterization for Meta-Learning , 2002 .

[14]  Selçuk Erkaya.  Analysis of the vibration characteristics of an experimental mechanical system using neural networks , 2012 .

[15]  Karim Salahshoor,et al.  A new integrated on-line fuzzy clustering and segmentation methodology with adaptive PCA approach for process monitoring and fault detection and diagnosis , 2013, Soft Comput..

[16]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[17]  Hsu-Pin Wang,et al.  Machine-fault classification: A fuzzy-set approach , 1991 .

[18]  K. I. Ramachandran,et al.  Feature selection using Decision Tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearing , 2007 .