HOME JOURNALS CONTACT

Journal of Applied Sciences

Year: 2013 | Volume: 13 | Issue: 16 | Page No.: 3209-3214
DOI: 10.3923/jas.2013.3209.3214
Fault Diagnosis of Rotating Shaft Systems Based on Wavelet Entropy and GA-SVM
Hu Hai-Gang, Zhou Xin and Feng Zhi-Min

Abstract: A new fault diagnosis method for rotating shaft system of marine diesel engine is proposed in this paper. The proposed method is an integrated application of wavelet packet, Shannon entropy, SVM (Support Vector Machine) and GA (Genetic Algorithm) theory. Based on the simulation platform for marine diesel engine shafting, wavelet packet decomposition and strong fault-tolerant Shannon entropy are used to compute the feature vectors of vibration signals, which are then served as the input vectors of SVM; GA is used to optimize the parameters of SVM when it is trained to achieve higher veracity. The study result shows that WPS-GS can get higher reliability and veracity than the conventional SVM and BP neural network, which means the provided method is more suitable for the condition monitoring and fault diagnosis of rotating shaft system.

Fulltext PDF

How to cite this article
Hu Hai-Gang, Zhou Xin and Feng Zhi-Min, 2013. Fault Diagnosis of Rotating Shaft Systems Based on Wavelet Entropy and GA-SVM. Journal of Applied Sciences, 13: 3209-3214.

Keywords: Fault diagnosis, rotating shaft system, wavelet packet, shannon entropy, genetic algorithm and support vector machine

REFERENCES
  • Bowen, C. and R. Zhang, 2006. Fault detection and isolation if inverter based on FFT and neural network. Trans. China Electrotech. Soc., 21: 37-43.
    Direct Link    

  • Yu, F., G. Chen and J. Cao, 2003. Parameter estimation of LFM signal based on the chirp-fourier transform. J. Electron. Measur. Inst., 17: 75-79.
    Direct Link    

  • Wang, A., W. Shu and C. Mingxin, 2005. Study on spectrum of nonuniform sampling signals based on wavelet transform. J. Electron. Inform. Technol., 27: 427-429.

  • Cao, J.J. and P.L. Zhang, 2008. Feature extraction of an engine cylinder head vibration signalbased on lifting wavelet package transformation. J. Vibrat. Shock, 27: 34-37.
    Direct Link    

  • He, Z.Y., Y.M. Cai and Q.Q. Qian, 2005. A study of wavelet entropy theoryand its application in electric power system fault detection. Proc. Csee, 25: 38-43.
    Direct Link    

  • Jack, L.B. and A.K. Nandi, 2002. Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mech. Syst. Signal Proc., 16: 373-390.
    CrossRef    Direct Link    

  • Zhang, K., H.P. Huang, H.T. Yang and Q. Xie, 2010. A transformer fault diagnosis method integrating improved genetic algorithm with least square support vector machine. Power Syst. Technol., 34: 164-166.
    Direct Link    

  • Wu, J.D. and C.H. Liu, 2009. An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Syst. Appl., 36: 4278-4286.
    CrossRef    Direct Link    

  • Avci, E. and Z.H. Akpolat, 2006. Speech recognition using a wavelet packet adaptive network based fuzzy inference system. Expert Syst. Appl., 31: 495-503.
    CrossRef    

  • Goldberg, D.E., 1989. Genetic Algorithms in Search Optimization and Machine Learning. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA

  • Zhou, X. and X.H. Ling, 2010. Survey on the theory and technology of genetic algorithms. Comput. Inform. Technol., 4: 37-39.

  • Li, Q., B. Yang, Y. Li, N. Deng and L. Jing, 2003. Constructing support vector machine ensemble. Pattern Recognit., 36: 2757-2767.
    CrossRef    Direct Link    

  • Saleh, R.M., M.T. Martin-Valdivia, A. Montejo-Raez and L.A. Urena-Lopez, 2011. Experiments with SVM to classify opinions in different domains. Exp. Syst. Appl., 38: 14799-14804.
    CrossRef    Direct Link    

  • Feng, Z.M., Y. Wang, Z.G. Hu and H.X. Lang, 2002. Fault diagnosis means and experiment based on kohonen neural network. Trans. Chinese Soc. Agricul. Mach., 33: 103-106.

  • Hu, H.G., L. Cao and Z.M. Feng, 2008. Data collecting and processing system of torsional vibration of ship propulsion shafting. Mech. Elect. Engine. Magazine, 25: 24-26.
    Direct Link    

    • © Science Alert. All Rights Reserved