AUT Journal of Electrical Engineering

AUT Journal of Electrical Engineering

Predicting Torque Ripple and Average Torque of a Switched Reluctance Motor Using MLP and RBF Models

Document Type : Research Article

Authors
Siroos Hemmati 1
Milad Goldasteh 2
Mohsen Asadi 2
Seyed Shahrooz Hosseini 3
Sobhan Roshani 4
1 Kermanshah University of Technology, Kermanshah, Iran.
2 Razi University, Kermanshah, Iran.
3 Azad University, Kermanshah, Iran.
4 Azad University, Kermanshah, Iran
10.22060/eej.2026.25442.5934
Abstract
The optimal design of a Switched Reluctance Motor (SRM) requires an accurate model. Analytical models presented for SRM do not meet required accuracy. Approximate models also have varying degrees of accuracy in predicting SRM characteristics. Hence, in this paper, two Neural Network (NN) models, Radial Basis Function (RBF) and Multilayer Perceptron (MLP), have been proposed to predict torque ripple and average torque, respectively. To train and test the models, 100 samples were extracted, 90% for training and 10% for testing. Furthermore, the Finite Element Method (FEM) has been used to solve the samples. The influencing parameters of the proposed NN models (number of hidden layers, number of neurons in hidden layers, bias, etc.) also have been determined to achieve the desired accuracy and minimal complexity. To evaluate the performance of the models, two criteria, Root Mean Square Error (RMSE) and Mean Relative Error (MRE), have been used. Both criteria indicate that the MLP model is successful in predicting torque ripple, while the RBF model excels in predicting average torque.
Keywords
Switched Reluctance Motor
Torque
MLP
RBF
Neural Network
Subjects
[1] Vahedi, Payam, Babak Ganji, and Seyed Ebrahim Afjei. "Design Optimization of the Multi-layer Switched Reluctance Motor to Minimize Torque Ripple and Maximize Average Torque." AUT Journal of Electrical Engineering 56.1 (Special Issue) (2024): 95-112.
[2] Lee, Jaewook, Jeong Hun Seo, and Noboru Kikuchi. "Topology optimization of switched reluctance motors for the desired torque profile." Structural and Multidisciplinary Optimization 42 (2010): 783-796.‏
[3] N. K. Sheth and K. R. Rajagopal, "Optimum pole arcs for a switched reluctance motor for higher torque with reduced ripple," 2003 IEEE International Magnetics Conference (INTERMAG), Boston, MA, USA, 2003, pp. CP-06, doi: 10.1109/INTMAG.2003.1230356.
[4] Q. Sun, J. Wu, C. Gan, C. Shi and J. Guo, "DSSRM Design With Multiple Pole Arcs Optimization for High Torque and Low Torque Ripple Applications," in IEEE Access, vol. 6, pp. 27166-27175, 2018, doi: 10.1109/ACCESS.2018.2834901.
[5] Lu, Wenzhe, Ali Keyhani, and Abbas Fardoun. Neural network-based modeling and parameter identification of switched reluctance motors.  IEEE transactions on energy conversion 18.2 (2003): 284-290.‏
[6] Wang, Libiao, et al. "Parameter Identification of Nonlinear Flux-Linkage Model for Switched Reluctance Motor Based on Chaotic Diagonal Recurrent Neural Network. " Journal of Engineering Science & Technology Review 17.2 (2024).‏
[7] Aydemir, Mustafa, and Halil Ibrahim Okumus. "Phase flux linkage estimation of external rotor switched reluctance motor with NARX neural network." Electrical Engineering 105.2 (2023): 1223-1233.‏
[8] Ouannou, Abdelmalek, et al. "Identification of switched reluctance machine using fuzzy model. " International Journal of System Assurance Engineering and Management 13.6 (2022): 2833-2846.‏
[9] Liu, Jian, et al. "A new modeling method for switched reluctance motor based on the fuzzy logic system. " 2018 37th Chinese Control Conference (CCC). IEEE, 2018.‏
[10] Ding, Wen, and Deliang Liang. "Modeling of a 6/4 switched reluctance motor using adaptive neural fuzzy inference system. " IEEE Transactions on Magnetics 44.7 (2008): 1796-1804.‏
[11] Shin, Hye‐Ung, and Kyo‐Beum Lee. "Optimal design of a 1 kW switched reluctance generator for wind power systems using a genetic algorithm. " IET Electric Power Applications 10.8 (2016): 807-817.‏
 [12] Huang, Su-Dan, et al. "Nonlinear modeling of the inverse force function for the planar switched reluctance motor using sparse least squares support vector machines." IEEE Transactions on Industrial Informatics 11.3 (2015): 591-600.‏
[13] Kumar, S. Suresh, and J. Jayakumar. "Torque modeling of switched reluctance motor using LSSVM-DE." Neurocomputing 211 (2016): 117-128.
[14] Yalavarthi, Amarnath, and Bhim Singh. "Sensorless Speed Control of SRM Drive Using Optimized Neural Network Model for Rotor Position Estimation." IEEE Transactions on Energy Conversion (2024).‏
[15] Ozden, Semih, Gokhan Manav, and Mahir Dursun. "ANN-based magnetic field and inductance modeling of double-sided linear switched reluctance motor." 2018 5th international conference on electrical and electronic engineering (ICEEE). IEEE, 2018.‏
[16] Shen, Xun, et al. "Simulation Research on No Position Control Strategy of Switched Reluctance Motor Based on On-Line Training of BP Neural Network. " 2023 International Seminar on Computer Science and Engineering Technology (SCSET). IEEE, 2023.‏
[17] Gecer, Bekir, Alper Nabi Akpolat, Necibe Fusun Oyman Serteller, Ozturk Tosun, and Mehmet Gol. 2026. "Data-Driven Sensorless Rotor Position Estimation for Switched Reluctance Motors Using a Deep LSTM Network" Electronics 15, no. 6: 1330. https://doi.org/10.3390/electronics15061330
[18] Zhang, Zhu, Shenghua Rao, and Xiaoping Zhang. "Performance prediction of switched reluctance motor using improved generalized regression neural networks for design optimization." CES Transactions on Electrical Machines and Systems 2.4 (2018): 371-376.‏
[19] Ma, Cong, and Liyan Qu. "Multiobjective optimization of switched reluctance motors based on design of experiments and particle swarm optimization. " IEEE Transactions on Energy Conversion 30.3 (2015): 1144-1153.‏
AUT Journal of Electrical Engineering
Volume 58, Issue 4
2026
Pages 793-802