Combination of Discriminant Analysis and Minimum Redundancy Maximum Relevance for Induction Motor Fault Diagnosis Using Stator Current Signals

Abstract:

Induction motors are critical components in various industrial applications. Any faults can seriously affect the production system. Therefore, early fault detection is essential to prevent such occurrences. This research aims to develop a fault diagnosis model for induction motors. Raw signal data were obtained experimentally in the laboratory using two identical three-phase induction motors. There are eight different conditions categorized into single-combined faults. 18 features were extracted from each signal, consisting of 12 time-domain features and 6 frequency-domain features. These features were selected using the minimum Redundancy maximum Relevance (mRmR) algorithm. The selected features were then used as input to build a model using the Discriminant Analysis. The results indicate that the Discriminant Analysis model achieved very high accuracy across all condition classes. The computation time of the developed model is exceptionally fast, even below one second. Quadratic Discriminant Analysis (QDA) proved to be more accurate than Linear Discriminant Analysis (LDA) in classifying faults data.

• Periodical: Applied Mechanics and Materials (Volume 932)
• Pages: 59-69
• DOI: https://doi.org/10.4028/p-L9YnF8
• Online since: February 2026
• Authors: Dwi Yulianto Kurniawan, Djoko Susilo Didik*, Joko Widodo Purwadi
• Keywords: Discriminant Analysis, Fault Diagnosis, Induction Motor, mRmR, Stator Current

References

[1] P.P.S. Saputra, F. D. Murdianto, R. Firmansyah, and K. Widarsono, "Combination of Quadratic Discriminant Analysis and Daubechis Wavelet for Classification Level of Misalignment on Induction Motor," in 2019 International Symposium on Electronics and Smart Devices (ISESD), IEEE, Oct. 2019.

DOI: 10.1109/ISESD.2019.8909431

[2] A. Chourasia, S. Salunke, and V. Saxena, "Efficiency Optimization of Three Phase Induction Motor by Slip Compensation: A Review," Int. J. Electron. Electr. Eng., p.308–314, 2013.

DOI: 10.12720/ijeee.1.4.308-314

[3] P. Gangsar and R. Tiwari, "Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review," Mech. Syst. Signal Process., vol. 144, 2020.

DOI: 10.1016/j.ymssp.2020.106908

[4] S. K. Gundewar and P. V Kane, "Condition Monitoring and Fault Diagnosis of Induction Motor," J. Vib. Eng. Technol., vol. 9, no. 4, p.643–674, 2020

DOI: 10.1007/s42417-020-00253-y

[5] M. R. Javed et al., "An Efficient Fault Detection Method for Induction Motors Using Thermal Imaging and Machine Vision," Sustainability, vol. 14, no. 15, p.1–17, 2022.

DOI: 10.3390/su14159060

[6] A. Stetco et al., "Machine Learning Methods For Wind Turbine Condition Monitoring : A Review," Renew. Energy, vol. 133, p.620–635, 2019.

DOI: 10.1016/j.renene.2018.10.047

[7] M. Blodt, P. Granjon, B. Raison, and G. Rostaing, "Models for bearing damage detection in induction motors using stator current monitoring," IEEE Trans. Ind. Electron., vol. 55, no. 4, p.1813–1822, 2008.

DOI: 10.1109/TIE.2008.917108

[8] A. Bellini, C. Tassoni, and G.-A. Capolino, "Advances in Diagnostic Techniques for Induction Machines," IEEE Trans. Ind. Electron., vol. 55, no. 12, p.4109–4125, 2008.

DOI: 10.1201/b11685-11

[9] A. Bellini, F. Immovilli, R. Rubini, and C. Tassoni, "Diagnosis of bearing faults in induction machines by vibration or current signals: A critical comparison," Conf. Rec. - IAS Annu. Meet. (IEEE Ind. Appl. Soc., vol. 46, no. 4, p.1350–1359, 2008.

DOI: 10.1109/08IAS.2008.26

[10] D. D. Susilo, A. Widodo, T. Prahasto, and M. Nizam, "Fault Diagnosis of Roller Bearing Using Parameter Evaluation Technique and Multi-class Support Vector Machine," AIP Conf. Proc., vol. 1788, no. 1, 2017.

DOI: 10.1063/1.4968334

[11] C. Y. Lee, Y.J. Hsieh, and T.A. Le, " Induction Motor Fault Classification Based On Combined Genetic Algorithm With Symmetrical Uncertainty Method For Feature Selection Task", Mathematics, vol. 10, no. 4, pp.1-22, 2022.

DOI: 10.3390/math10020230

[12] M.A. Asyrofi, D.D. Susilo, and A.R. Prabowo, "Study on the Optimal Feature Number in Induction Motor Fault Diagnosis Based on Support Vector Machine Using Current And Vibration Signals", In Proceedings of the 9th International Conference and Exhibition on Sustainable Energy and Advanced Materials, pp.251-255, 2024, Springer.

DOI: 10.1007/978-981-97-0106-3_42

[13] R.K. Patel, "Feature selection and fault classification for an induction motor using PCA and mRMR", International Journal of Quality Engineering and Technology, 10(3), 224–238.

DOI: 10.1504/IJQET.2023.134886

[14] H. Peng, F. Long, and C. Ding, "Feature Selection Based on Mutual Information : Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy," IEEE Trans. PATTERN Anal. Mach. Intell., vol. 27, no. 8, p.1226–1238, 2005.

DOI: 10.1109/tpami.2005.159

[15] A. Siddique, G. S. Yadava, and B. Singh, "Applications of Artificial Intelligence Techniques for Induction Machine Stator Fault Diagnostics : Review," 4th IEEE Int. Symp. Diagnostics Electr. Mach. Power Electron. Drives, p.29–34, 2003.

DOI: 10.1109/demped.2003.1234543

[16] K. Sarkodie and A. Fergusson-rees, "Flow regime identification in vertical upward gas - liquid flow using an optical sensor with linear and quadratic discriminant analysis," J. Fluids Eng., p.1–35.

DOI: 10.1115/1.4048613

[17] J. Lin, "Fault Diagnosis Method of Motor Bearing Based on Bayesian Optimized Quadratic Discriminant Analysis," no. Iccia, p.211–217, 2020.

DOI: 10.23977/iccia2020036

[18] E. Altman and F. Varetto, "Corporate distress diagnosis : Comparisons using linear discriminant analysis and neural networks ( the Italian experience )," J. Bank. Financ., p.505–529, 1994.

DOI: 10.1016/0378-4266(94)90007-8

[19] A. Tharwat, "Linear vs. quadratic discriminant analysis classifier: a tutorial," Int. J. Appl. Pattern Recognit., vol. 3, no. 2, p.145, 2016

DOI: 10.1504/ijapr.2016.079050