Autors: Zhelyazkov, Y. K., Torlakov, I. D., Dimitrova, K. I. Title: Prediction of Induction Motor Parameters Using a Neural Network Keywords: deep learning, induction motor, MATLAB, neural network, optimizationAbstract: This study investigates an induction motor referenced in earlier research [1], focusing on the analysis of its primary characteristics and proposing a mechanism for predicting specific values utilizing a neural network. This study focuses on a feed-forward neural network model aimed at predicting specific parameters of the motor at a higher value of operating frequency, including voltage, current, speed, torque, power, and force, utilizing the measured and visualized values referenced in [1]. The anticipated outcomes of the examined characteristics are displayed, indicating minimal divergence of mean squared error (MSE) is less than 1% from the actual measurements following the training of the proposed neural network. References - K. Dimitrova, Y. Zhelyazkov and I. Torlakov, "About Characteristics of the Induction Motor", Proceedings of the Technical University of Sofia, ISSN: 2738-8549, 2738-8530 vol. 74, no. 3, 2024.
- N. Petrov and K. Dimitrova, Control of Electromechanical Systems and Their Reliability, Publishing House Zhelyo Uchkov, ISBN 978-954-391-147-9, 2020 (in Bulgarian).
- S. Bozhkov, V. Mladenov, "Model of photovoltaic system with connected dynamic load" Energy Forum, 2013.
- Y. LeCun, Y. Bengio and G. Hinton, Deep learning. Nature, 521(7553), 436-444, 2015.
- J. Schmidhuber, Deep learning in neural networks: An overview. Neural Networks, 61, 85-117, 2015.
- K. Hornik, "Approximation capabilities of multilayer feedforward networks. Neural Networks", 4(2), 251-257, 1991.
- D. Rumelhart, G. Hinton and R. Williams, Learning representations by back-propagating errors. Nature, 323(6088), pp. 533-536, 1986.
- C. M. Bishop, Neural Networks for Pattern Recognition. Oxford University Press, 1995.
- I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT Press, 2016.
- MathWorks, "fitnet, " MATLAB Deep Learning Toolbox, 2018. [Online]. Available: Https: //www. mathworks. com/help/deeplearning/ref/fitnet. html
- Y. Zhang, Q. Liu, and X. Zhao, "Recent advances in training techniques for feed-forward neural networks", Neural Processing Letters, 52(3), 2311-2323, 2020.
- R. Sun, and M. Er, "A comprehensive survey on learning algorithms for feed-forward neural networks" IEEE Access, 7, 151830-151844, 2019.
- V. Todorov and P. Mihaylov, "Enhancing the accuracy of induction motor prediction models using Bayesian regularization", IEEE Access, 8, 156293-156303, 2020
- I. Metodieva and S. Bozhkov, "Neural Network a Way to Forecast the Generation of Electricity From a Wind Turbine", https: //doi. org/10. 1109/eeae53789. 2022. 9831402, 2022.
- D. J. MacKay, "A practical Bayesian framework for backpropagation networks". Neural Computation, 4(3), pp. 448-472, 1992.
- C. M. Bishop, Pattern Recognition and Machine Learning. Springer, 2006.
- S. Haykin, Neural Networks and Learning Machines, 3rd ed., Upper Saddle River, NJ, USA: Prentice Hall, 2009.
Issue
| 60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, 2025, Macedonia, https://doi.org/10.1109/ICEST66328.2025.11098406 |
|