Research Article

Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors

Volume: 6 Number: 4 July 27, 2026

Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors

Abstract

Induction motors (IMs) are widely used in industrial applications due to their robustness, low cost, and simple construction. However, the increasing integration of power electronic devices such as inverters, soft starters, and variable frequency drives (VFDs) has made modern energy systems more complex, introducing significant harmonic distortions. These harmonics alter the sinusoidal nature of supply voltages, causing additional losses, torque pulsations, overheating, and reduced efficiency. In particular, odd-order harmonics such as the 5th, 7th, 11th, and 13th adversely affect motor performance by generating reverse torques, increasing mechanical vibrations, and accelerating insulation and bearing degradation. To address this challenge, this study investigates harmonic estimation in IMs using a combination of real measurements and artificial intelligence. Voltage signals were acquired from motors under star-delta, soft starter, and VFD-fed conditions at an industrial facility. To augment the dataset and model real noise environments, conditional Generative Adversarial Networks (cGANs) were employed to generate synthetic signals at varying signal-to-noise ratios. A feedforward neural network was then trained with these real and synthetic signals to estimate the amplitudes of key harmonics. The proposed model, optimized using the Adam optimization algorithm significantly improved estimation accuracy, reducing the Mean Absolute Error (MAE) from 0.9008 to 0.2993 and the Root Mean Squared Error (RMSE) from 1.0195 to 0.4123. The proposed framework also achieved very accurate estimation of the 5th, 7th, 11th, and 13th harmonics compared to ground-truth measurements. These results demonstrate the potential of combining real-world measurements, synthetic data generation, and machine learning regression for accurate harmonic characterization in IMs, contributing to improved diagnostics, monitoring, and efficiency in industrial energy systems.

Keywords

Thanks

The authors would like to thank to the administration of KNT Paper Industry and Trade Inc., Corum, Turkiye for the permission of data collection in the factory.

References

  1. Chapman, S. J. (2011). Electric machinery fundamentals (5th ed.). McGraw-Hill.
  2. Kundur, P. (1994). Power system stability and control. McGraw-Hill.
  3. El-Hawary, M. E. (2002). Principles of electric machines with power electronic applications (2nd ed.). Wiley-IEEE Press.
  4. Özüpak, Y., & Mamiş, M. S. (2020). Analysis of electromagnetic and loss effects of sub-harmonics on transformers by finite element method. Sādhanā, 45(1), Article 226. https://doi.org/10.1007/s12046-020-01473-4
  5. Liang, X., & Luy, Y. (2006). Harmonic analysis for induction motors. In 2006 Canadian Conference on Electrical and Computer Engineering (pp. 172–177). IEEE. https://doi.org/10.1109/CCECE.2006.277368
  6. Singh, G. K. (2005). A research survey of induction motor operation with non-sinusoidal supply wave forms. Electric Power Systems Research, 75(2–3), 200–213. https://doi.org/10.1016/j.epsr.2005.04.001
  7. Beleiu, H. G., Maier, V., Pavel, S. G., Birou, I., Pică, C. S., & Dărab, P. C. (2020). Harmonics consequences on drive systems with induction motor. Applied Sciences, 10(4), Article 1528. https://doi.org/10.3390/app10041528
  8. Yacamini, R., & Chang, S. C. (1995). Noise and vibration from induction machines fed from harmonic sources. IEEE Transactions on Energy Conversion, 10(2), 286–292. https://doi.org/10.1109/60.391894

Details

Primary Language

English

Subjects

Electrical Energy Transmission, Networks and Systems

Journal Section

Research Article

Publication Date

July 27, 2026

Submission Date

March 21, 2026

Acceptance Date

July 20, 2026

Published in Issue

Year 2026 Volume: 6 Number: 4

APA
Gafar, O., & Gençol, K. (2026). Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors. Engineering Perspective, 6(4), 543-552. https://doi.org/10.64808/engineeringperspective.1913726
AMA
1.Gafar O, Gençol K. Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors. engineeringperspective. 2026;6(4):543-552. doi:10.64808/engineeringperspective.1913726
Chicago
Gafar, Onur, and Kenan Gençol. 2026. “Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors”. Engineering Perspective 6 (4): 543-52. https://doi.org/10.64808/engineeringperspective.1913726.
EndNote
Gafar O, Gençol K (July 1, 2026) Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors. Engineering Perspective 6 4 543–552.
IEEE
[1]O. Gafar and K. Gençol, “Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors”, engineeringperspective, vol. 6, no. 4, pp. 543–552, July 2026, doi: 10.64808/engineeringperspective.1913726.
ISNAD
Gafar, Onur - Gençol, Kenan. “Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors”. Engineering Perspective 6/4 (July 1, 2026): 543-552. https://doi.org/10.64808/engineeringperspective.1913726.
JAMA
1.Gafar O, Gençol K. Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors. engineeringperspective. 2026;6:543–552.
MLA
Gafar, Onur, and Kenan Gençol. “Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors”. Engineering Perspective, vol. 6, no. 4, July 2026, pp. 543-52, doi:10.64808/engineeringperspective.1913726.
Vancouver
1.Onur Gafar, Kenan Gençol. Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors. engineeringperspective. 2026 Jul. 1;6(4):543-52. doi:10.64808/engineeringperspective.1913726

download?token=eyJhdXRoX3JvbGVzIjpbXSwiZW5kcG9pbnQiOiJqb3VybmFsIiwib3JpZ2luYWxuYW1lIjoiQ2l0ZVNjb3JlMjAyNV9FbmdpbmVlcmluZ19QZXJzcGVjdC5wbmciLCJwYXRoIjoiMjk0YS81N2EyLzlmYzcvNmEyMDA1NTk1OTk0NjMuMTIyOTg1NTEucG5nIiwiZXhwIjoxNzgwNDg3MDE3LCJub25jZSI6ImFjOTI3ZGIxMTUyNGUwZWRhYTlmMzc4ZDk4ZWIwOWQ0In0.VU0eXdFjkzGH_RYBvG3PsXcGoypETO7r1qIe7dMExbU