Elman Neural Network for Diagnosis of Unbalance in a Rotor-Bearing System

The operational life of rotating machines has to be extended using a predictive condition maintenance tool. Among various condition monitoring techniques, vibration analysis is most widely used technique in industry. Signals are extracted for evaluating the condition of machine; further diagnostics is carried out with detected signals to extend the life of machine. With help of detected signals, further interpretations are done to predict the occurrence of defects. To study the problem of defects, a test rig with various possibilities of defects is constructed and experiments are performed considering the unbalanced condition. Further, this paper presents an approach for fault diagnosis of unbalance condition using Elman neural network and frequency-domain vibration analysis. Amplitudes with variation in acceleration are fed to Elman neural network to classify fault or no-fault condition. The Elman network is trained, validated and tested with experimental readings. Results illustrate the effectiveness of Elman network in rotor-bearing system. Keywords—Elman neural network, fault detection, rotating machines, unbalance, vibration analysis.

[1]  Cheng-Yuan Liou,et al.  Modeling word perception using the Elman network , 2008, Neurocomputing.

[2]  Nenad Mihajlovic,et al.  ON THE COUPLING BETWEEN TORSIONAL AND LATERAL VIBRATIONS IN A ROTOR DYNAMIC SYSTEM WITH SET-VALUED FRICTION , 2007 .

[3]  Biswanath Samanta,et al.  Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm , 2004, EURASIP J. Adv. Signal Process..

[4]  Zheng Tang,et al.  A Novel Learning Method for Elman Neural Network Using Local Search , 2007 .

[5]  Sahin Yildirim,et al.  Retraction notice to “Design of artificial neural networks for rotor dynamics analysis of rotating machine systems” [Mechatronics 15/5 (2005) 573–588] , 2013 .

[6]  Rongjun Li,et al.  An Improved Neural Network Model and Its Applications , 2011 .

[7]  M. Senthil Kumar,et al.  Condition Monitoring of rotating machinery through Vibration Analysis , 2014 .

[8]  Hua Xu,et al.  An Elman neural network-based model for predicting anti-germ performances and ingredient levels with limited experimental data , 2011, Expert Syst. Appl..

[9]  DeLiang Wang,et al.  On Temporal Generalization of Simple Recurrent Networks , 1996, Neural Networks.

[10]  Menderes Kalkat,et al.  RETRACTED: Design of artificial neural networks for rotor dynamics analysis of rotating machine systems , 2005 .

[11]  Tao Han,et al.  ART–KOHONEN neural network for fault diagnosis of rotating machinery , 2004 .

[12]  Şahin Yildirim,et al.  Rotor Dynamics Analysis of Rotating Machine Systems Using Artificial Neural Networks , 2003 .

[13]  Mohsen Esfahanian,et al.  Fault identification in rotating machinery using artificial neural networks , 2005 .

[14]  Jyoti K. Sinha,et al.  Estimating unbalance and misalignment of a flexible rotating machine from a single run-down , 2004 .

[15]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..