Induction motor fault conditioning is desirable to increase machine’s performance and efficiency by avoiding consequential damages in near future of testing. Vibration signals’ randomness prevents usage of any conventional methods for its analysis. Any non-conventional methods require extraction of different types of features and selection of features. This increases processing time of the whole conditioning system. In this paper, a different preprocessing technique, an extension to traditional approach, which uses basic statistical and frequency domain features, is used, hence reducing processing time. The preprocessing technique involves vibration signal denoising using wavelets and obtaining best trained data. Support vector machine classifier has been used for electrical and mechanical fault characterization. The effectiveness of the proposed method is proved through experimental results, and thus shown that a robust induction machine condition monitoring system has been produced.

1. Non-destructive testing of induction motor using multiple signature analysis by Sumesh.E.P, Aravindh Kumar.B, Saranya G, Selvakumar R, Swetha Shree R, Saranya M, S.Babu Devasenapathi
2. Support Vector Machine Used to Diagnose the Fault of Rotor Broken Bars of Induction Motors by Cao Zhitong', Fang Jiazhong', Chen Hongpingn', He Guoguang', Ewen Ritchie Electrical Machines and Systems, 2003. ICEMS 2003. Sixth International Conference on ,9-11 Nov. 2003
3. Wavelet aided SVM Classifier for Stator Inter-Turn Fault Monitoring in Induction Motors by S. Das, Member, IEEE, C. Koley, Member, IEEE, P. Purkait, Member, IEEE, and S. Chakravorti, : Power and Energy Society General Meeting, 2010 IEEE, 25-29 July 2010
4. Wavelet-based switching faults detection in direct torque control induction motor drives by M. Aktas V. Turkmenoglu, Science, Measurement & Technology, IET, November 2010
5. Application of MCSA and SVM to Induction Machine Rotor Fault Diagnosis by Ruiming Fang, Hongzhong Ma, Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on,
6. Bearing fault diagnosis using wavelet analysis by M Deriche, Computers, Communications, & Signal Processing with Special Track on Biomedical Engineering, 2005. CCSP 2005. 1st International Conference on, 14-16 Nov. 2005
7. Vibration monitoring and faults detection using wavelet techniques by Basel Isayed, Lahouari Cheded, Fadi Al-Badour*,Signal Processing and Its Applications, 2007. ISSPA 2007. 9th International Symposium on, 12-15 Feb. 2007
8. Broken bar detection in induction motor via wavelet transformation by K.Abbasezadeh, J.Milimonfared, M.Haji, H.A.Toliyat, Industrial Electronics Society, 2001. IECON '01. The 27th Annual Conference of the IEEE ,2001
9. Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography by Z.K. Peng, F.L. Chu, Mechanical Systems and Signal Processing 18 (2004)

wavelet denoising SVM piezoelectric accelerometer