Fourier and wavelet transformations application to fault detection of induction motor with stator current

Abstract

Fault detection of an induction motor was carried out using the information of the stator current. After synchronizing the actual data, Fourier and wavelet transformations were adopted in order to obtain the sideband or detail value characteristics under healthy and various faulty operating conditions. The most reliable phase current among the three phase currents was selected using an approach that employs the fuzzy entropy measure. Data were trained with a neural network system, and the fault detection algorithm was verified using the unknown data. Results of the proposed approach based on Fourier and wavelet transformations indicate that the faults can be properly classified into six categories. The training error is 5.3×10⁻⁷, and the average test error is 0.103.

Keywords

Fourier transformation / wavelet transformation / induction motor / fault detection

References

[1] VasP.Parameter estimation, condition monitoring, and diagnosis of electrical machines [M], 1993, Oxford, Clarendron Press

[2] HAJI M, TOLIYAT H A. Pattern recognition: A technique for induction machines rotor fault detection eccentricity and broken bar fault [C]// Proceedings of the 2001 IEEE Industry Applications Conference. Chicago, 2001: 1572–1578.

[3] NEELAM M, RATNA D. Motor current signature analysis and its applications in induction motor fault diagnosis [C]// Proceedings of the American Conference on Applied Mathematics. Massachusetts, 2008: 442–448.

[4] OlympiadaA. S., MariaG. I.. Induction motors’ faults detection and diagnosis by using dedicated software [J]. Journal of Materials Processing Technology, 2007, 181(1): 313-317

[5] NeelamM., RatnaD.. An approach of condition monitoring of induction motor using MCSA [J]. International Journal of Systems Applications, Engineering and Development, 2007, 1(1): 13-17

[6] LEBAROUD A, CLERC G. On-line diagnosis of induction motor faults [C]// Proceedings of the 4th International Conference: Sciences of Electronic, Technologies of Information and Telecommunications. Hammamet, 2007: 1–5.

[7] ABBASZADEH K, MILIMONFARED J, HAJI M, TOLIYAT H A. Broken bar detection in induction motor via wavelet transformation [C]// Proceedings of the 27th Annual Conference of the IEEE Industrial Electronics Society. Denver, 2001: 95–99.

[8] MallatS. A.. Theory for multiresolution signal decomposition: The wavelet representation [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693

[9] MallatS.A wavelet tour of signal processing [M], 1999, London, Academic Press

[10] LiuX.-cheng.. Entropy, distance measure and similarity measure of fuzzy sets and their relations [J]. Fuzzy Sets and Systems, 1992, 52: 305-318

[11] FanJ.-l., MaY.-l., XieW.-xin.. On some properties of distance measures [J]. Fuzzy Set and Systems, 2001, 117(3): 355-361

[12] LeeS. H., ChunS. P., KimJ. H.. Measure of certainty with fuzzy entropy function [J]. Lecture Note in Computer Science, 2006, 4114: 134-139

[13] MartinezW. L., MartinezA. R.Computational statistics handbook with Matlab [M], 2002, Florida, Chapman and Hall/CRC

[14] BaoZ.-j., ZhongW.-m., PiD.-y., SunY.-xian.. Robustly stable model predictive control based on parallel support vector machines with linear kernel [J]. Journal of Central South University of Technology, 2007, 14(5): 701-707

[15] PnadyaA. S., GibarT. C., KimK. B.. Neural network training using GMDH type algorithm [J]. International Journal of Fuzzy Logic and Intelligent Systems, 2005, 5(1): 52-58