IRO Journals
Journal of Electronics and Informatics

Neural Network based Soft Starting Technique for Squirrel Cage Induction Motor

Open Access
Published: 20 May, 2026
Pages: 188-199
  • Mohamed Faizal A.A. , Mohamed Faizal A.A.
    Professor, Department of Electrical and Electronics Engineering, V V College of Engineering, Tisaiyanvilai, Thoothukudi, India
    Professor, Department of Electrical and Electronics Engineering, V V College of Engineering, Tisaiyanvilai, Thoothukudi, India
  • Muthulakshmi M. Muthulakshmi M.
    PG Student, Department of Electrical and Electronics Engineering, V V College of Engineering, Tisaiyanvilai, Thoothukudi, India
    PG Student, Department of Electrical and Electronics Engineering, V V College of Engineering, Tisaiyanvilai, Thoothukudi, India
view PDF
view PDF

How to Cite

A.A., Mohamed Faizal, and Muthulakshmi M. 2026. “Neural Network Based Soft Starting Technique for Squirrel Cage Induction Motor”. Journal of Electronics and Informatics 8 (2): 188-99. https://doi.org/10.36548/jei.2026.2.007.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Artificial Neural Network (ANN)
Soft Starting
Squirrel Cage Induction Motor
Starting Current
Torque Ripple
Motor Control

Abstract

The soft start of squirrel cage induction motors is highly imperative in order to avoid any excessive currents, torque pulses, and mechanical stresses. As a matter of fact, traditional Direct on Line (DOL) techniques of motor starting involve heavy current transients and torque pulses that tend to shorten the life of the motors and destabilize system performance. In this regard, this paper presents a soft starting scheme for a three-phase squirrel cage induction motor using an artificial neural network (ANN) based on a thyristor-controlled AC voltage controller. The proposed feed-forward multilayer perceptron (MLP) ANN model incorporates various motor operating parameters including motor current, speed, electromagnetic torque, and loading condition to provide optimal firing angles of the thyristors. The induction motor is represented in dq-coordinates while the MLP ANN is trained by means of backpropagation algorithm with the performance index being Mean Squared Error (MSE). From the MATLAB simulations, the results indicate that the proposed ANN model can significantly decrease the starting current from 90A to 30A and starting torque from 125N-m to 40N-m compared to the traditional DOL scheme.

References

  1. Mahfoud, Said, Najib El Ouanjli, Aziz Derouich, Abderrahman El Idrissi, Elmostafa Chetouani, Azeddine Loulijat, Shimaa A. Hussien, and Mohamed I. Mosaad. "An Advanced Direct Torque Control for Doubly Fed Induction Motor Using Evolutionary Computational Techniques." Scientific Reports 2025, vol. 15, no. 1: 22719.
  2. Rafia, Hassan, Hamid Ouadi, Fouad Giri, and Brahim El Bhiri. "Advanced Hybrid Control for Induction Motor Combining ANN-PID Speed Controller with Neural Predictive Current Regulator Based on Particle Swarm Optimization." Transactions of the Institute of Measurement and Control 2025, vol. 47, no. 7: 1387-1402.
  3. Chong Chen, “Neural Network Control of Induction Motor Speed Control System”, International Journal of Control and Automation 2014, vol. 7, no. 10, 243–254.
  4. Kashif, A. R., and M. A. Saqib. "Soft Starting of an Induction Motor Using Adaptive Neuro Fuzzy Inference System." International Conference on Electrical Engineering 2007, 1-5.
  5. Gürkan Zenginobuz, Isik Cadirci, Muammer Ermis, Cüneyt Barlak, “Performance Optimization of Induction Motors During Voltage Controlled Soft Starting”, IEEE Transactions on Energy Conversion 2004, vol. 19, no. 2, 278–288.
  6. Shabestari, Parisa M., and Ali Mehrizi-Sani. "Current Limiting and Torque Pulsation Reduction of the Induction Motors." IEEE Power & Energy Society General Meeting (PESGM) 2019, 1-5.
  7. Khudhur, Laith Najem Abood, and Amer Abdulmahdi Jabbar Chlaihawi. "Design and Implementation of IoT-based Soft Starter for Induction Motor." International Journal of Power Electronics and Drive System (IJPEDS) 2025, vol. 16, no. 4: 2170~2177.
  8. Aaradhna Soni, “Artificial Neural Network Based Soft-Starter for Induction Motor- A Review”,International Research Journal of Engineering & Applied Sciences, IRJEAS 2020, vol. 8, no. 4: 6-10.