Fault Detection and Diagnosis of a 3-Phase Induction Motor Using Kohonen Self-Organising Map

Main Article Content

Robert Agyare Ofosu
Benjamin Odoi
Daniel Fosu Boateng
Asaph Mbugua Muhia



This paper uses the Kohonen Self-Organising Map (KSOM) to detect, diagnose, and classify induction motor faults. A series of simulations using models of the 3-phase induction motor based on real industrial motor parameters were performed using MATLAB/Simulink under fault conditions such as inter-turn, power frequency variation, over-voltage and unbalance in supply voltage. The model was trained using the input signals of the various fault conditions. Various faults from an unseen induction motor were fed to the model to test the model’s ability to detect and classify induction motor faults. The KSOM adapted to the conditions of the unseen motor, detected, diagnosed and classified these faults with an accuracy of 94.12%.


C. Y. Eduardo, A. F. Arturo, G. Arturo, J. R. Rene and M. L. Jose, “Real-time condition monitoring of vsd-fed induction motors through statistical analysis and synchronous speed observation”, International Transactions on Electrical Energy Systems, Vol. 5, No. 8, pp. 1-15, 2015.

A. Soualhi, G. Clerc and A. Lebaroud, “Fault detection and diagnosis of induction motors based on hidden markov model”, IEEE Transactions, Vol. 20, No. 2, pp. 1-7, 2012.

W. J. Bradley, “Current-based fault detection and diagnosis of induction motors”, Ph.D. dissertation, University of Bradford, England, 2013.

V. H. Nguyen, “Model-based diagnosis and prognosis of induction motors under stator winding fault”, Ph.D. dissertation, Nanyang Technological University, Singapore, 2018.

A. Gheitasi, “Motor fault recognition using distributed current signature analysis”, Ph.D. dissertation, Auckland University of Technology, New Zealand, 2013.

L. Dezhi, “An intelligent system for induction motor health condition monitoring”, Ph.D. dissertation, University of Waterloo, Canada, 2015.

H., A. Talhaoui, A. K. Menacer, and T. Ameid, “Experimental diagnosis of broken rotor bar fault in induction motor based on hilbert and discrete wavelet transforms”, International Journal of Advanced Manufacturing Technology, Vol. 22, No. 12, pp. 1-11, 2017.

S. C. Karmakar, M. Surajit, M. Mitra and S. Senguta, “Induction motor fault diagnosis: approach through current signature analysis”, IEEE Journal of Industry Applications, Vol. 2, No. 7, pp. 30 – 32, 2016.

M. Rahman, and M. N. Uddin, “Online unbalanced rotor fault detection of an induction motor drive based on both time and frequency domain analyses”, IEEE Transactions on Industry Applications, Vol. 15, No. 5, pp. 1-11, 2016.

S. Sarkar and Hembram, P. K. “Acquisition and pre-processing of three phase induction motor”, IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering, Vol. 46, No. 8, pp. 45-58, 2016.

V. P. Mini, S. Ushakumari, “Rotor fault detection and diagnosis of induction motor using fuzzy logic, “American Society of Mechanical Journal, Vol. 87, No. 2, pp. 19-40, 2014.

R. A. Ofosu, A. B. Asiedu-Asante, R. B. Adjei, “Fuzzy logic-based condition monitoring of a 3-phase induction motor”, Proceedings of IEEE AFRICON 2019, Accra, Ghana, 2020.

A. Gandhi, T. Corrigan, and L. Parsa, “Recent advances in modelling and online detection of stator inter-turn faults in motors”, IEEE Transactions on Industry, Vol. 40, No.4, pp. 1564-1577, 2012.

T. Kohonen, MATLAB Implementation and Applications of the Self Organising Map, Unigratia Publishers, Finland, 201pp., 2014.

R. K. Rajput, Electrical Technology, Laxmi Publishers, Daryaganj, 2nd Edition, 514pp.

S. H. Haggag, M. Ali, and M. Hala, “A new fault detection tool for single phasing of a 3-phase induction motor”, Proceedings of the World Congress on Engineering, Vol. 2, No. 12, pp. 2 – 5, 2013.