Search for Author, Title, Keyword
RESEARCH PAPER
Temperature Prediction and Performance Comparison of Permanent Magnet Synchronous Motors Using Different Machine Learning Techniques for Early Failure Detection
 
 
More details
Hide details
1
Dicle University, Turkey
 
 
Submission date: 2024-06-11
 
 
Final revision date: 2024-07-01
 
 
Acceptance date: 2024-08-08
 
 
Online publication date: 2024-08-09
 
 
Publication date: 2024-08-09
 
 
Corresponding author
Emrah Aslan   

Dicle University, Turkey
 
 
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(1):192164
 
HIGHLIGHTS
  • KNN Regressor achieved 99.65% training and 98.72% test accuracy for PMSM temperature prediction.
  • Machine learning models replace costly sensors, enabling low-cost, real-time motor temperature monitoring.
  • Model validation shows RMSE 2.16, R2 score 98.72, and CV R2 97.77%, proving practical effectiveness.
KEYWORDS
TOPICS
ABSTRACT
Electric motors are increasingly used in various products, including turbines and electric vehicles. Precise temperature measurement is essential for the safe operation of a Permanent Magnet Synchronous Motor. Direct temperature detection of the permanent magnet and stator involves significant costs and hardware requirements. To overcome these challenges, Machine Learning models can eliminate the need for specialized sensors. This study used four diverse regression algorithms: Linear, K-Nearest Neighbor, XGBoost, and AdaBoost. The objective of this study is to model a Permanent Magnet Synchronous Motor used in electric vehicles and predict the temperatures of some of its parameters. The K-Nearest Neighbor Regressor outperformed the other algorithms, achieving a training accuracy of 99.65%, test accuracy of 98.72%, root-mean-square error of 2.16, R2 score of 98.72, and Cross-Validation R2 of 97.77%. These results enable low-cost, real-time temperature monitoring of electrical machinery, enhancing power density, safety, and efficiency.
REFERENCES (26)
1.
Piechocki M, Pajchrowski T, Kraft M, Wolkiewicz M, Ewert P. Unraveling Induction Motor State through Thermal Imaging and Edge Processing: A Step towards Explainable Fault Diagnosis. Eksploatacja i Niezawodność – Maintenance and Reliability. 2023;25(3). doi:10.17531/ein/170114.
 
2.
Thosar P, Patil J, Singh M, Thamke S, Gonge S. Prediction of Motor Temperature using Linear Regression. 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), Bengaluru, India, 2020, pp. 7-12. doi: 10.1109/ICSTCEE49637.2020.9277184.
 
3.
Garniwa I, Dipantara B, Nugroho MV, Sudiarto B, Noorfatima N. Analysis of the effect of the motor temperature to brushless direct current motor performance on KARLING electric vehicle. Journal of Physics: Conference Series 2019;1376(1):012024. IOP Publishing. https://doi.org/10.1088/1742-6....
 
4.
Al-Gabalawy M, Elmetwaly AH, Younis RA, Omar AI. Temperature prediction for electric vehicles of permanent magnet synchronous motor using robust machine learning tools. Journal of Ambient Intelligence and Humanized Computing 2022 May 19:1-8. https://doi.org/10.1007/s12652....
 
5.
Le R, He K, Hu A. Motor Temperature Prediction with K-Nearest Neighbors and Convolutional Neural Network. International Research Journal of Engineering and Technology 2019.
 
6.
Rojas-Dueñas G, Riba JR, Moreno-Eguilaz M. CNN-LSTM-based prognostics of bidirectional converters for electric vehicles' machine. Sensors 2021;21(21): https://doi.org/10.3390/s21217....
 
7.
Jiménez-Guarneros M, Morales-Perez C, de Jesus Rangel-Magdaleno J. Diagnostic of combined mechanical and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN. IEEE Transactions on Industrial Informatics 2021;18(7):4688-97. https://doi.org/10.1109/TII.20....
 
8.
Pawlik P, Kania K, Przysucha B. Fault diagnosis of machines operating in variable conditions using artificial neural network not requiring training data from a faulty machine. Eksploatacja i Niezawodność – Maintenance and Reliability. 2023;25(3). doi:10.17531/ein/168109.
 
9.
Kłosowski G, Rymarczyk T, Niderla K, Kulisz M, Skowron Ł, Soleimani M. Using an LSTM network to monitor industrial reactors using electrical capacitance and impedance tomography – a hybrid approach. Eksploatacja i Niezawodność – Maintenance and Reliability. 2023;25(1):11. doi:10.17531/ein.2023.1.11.
 
10.
Kirchgassner W, Wallscheid O, Bocker J. Thermal neural networks: lumped-parameter thermal modeling with state-space machine learning. arXiv preprint 2021.
 
11.
Hughes R, Haidinger T, Pei X, Vagg C. Real-time temperature prediction of electric machines using machine learning with physically informed features. Energy and AI 2023;14:100288. doi: 10.1016/j.egyai.2023.100288.
 
12.
Kirchgassner W, Wallscheid O, Bocker J. Data-driven permanent magnet temperature estimation in synchronous motors with supervised machine learning: A benchmark. IEEE Transactions on Energy Conversion 2021;36(3):2059-67. https://doi.org/10.1109/TEC.20....
 
13.
Kasburg C, Stefenon SF. Deep learning for photovoltaic generation forecast in active solar trackers. IEEE Latin America Transactions 2019;17(12):2013-9. https://doi.org/10.1109/TLA.20....
 
14.
Gui N, Lou J, Qiu Z, Gui W. Temporal feature selection for multi-step ahead reheater temperature prediction. Processes 2019;7(7): https://doi.org/10.3390/pr7070....
 
15.
Kirchgassner W, Wallscheid O, Bocker J. Estimating electric motor temperatures with deep residual machine learning. IEEE Transactions on Power Electronics 2020;36(7):7480-8. https://doi.org/10.1109/TPEL.2....
 
16.
Lee J, Ha JI. Temperature estimation of PMSM using a difference-estimating feedforward neural network. IEEE Access 2020;8:130855-65. https://doi.org/10.1109/ACCESS....
 
17.
Hosseini S, Shahbandegan A, Akilan T. Deep Neural Network Modeling for Accurate Electric Motor Temperature Prediction. 2022 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Halifax, NS, Canada, 2022, pp. 170-175. doi: 10.1109/CCECE49351.2022.9918222.
 
18.
Ahmed M, Mao Z, Zheng Y, Chen T, Chen Z. Electric Vehicle Range Estimation Using Regression Techniques. World Electric Vehicle Journal 2022;13(6):105. doi: 10.3390/wevj13060105.
 
19.
Qiu Y, Dobbelaere C, Song S. Energy Cost Analysis and Operational Range Prediction Based on Medium- and Heavy-Duty Electric Vehicle Real-World Deployments across the United States. World Electric Vehicle Journal 2023;14(12):330. doi: 10.3390/wevj14120330.
 
20.
Ionel D, Popescu M, McGilp M, Miller T, Dellinger S, Heideman R. Computation of core losses in electrical machines using improved models for laminated steel. IEEE Transactions on Industry Applications 2007;43(6):1554-64. https://doi.org/10.1109/TIA.20....
 
21.
Hosseini S, Taylan O, Abusurrah M, Akilan T, Nazemi E, Eftekhari-Zadeh E, Bano F, Roshani GH. Application of wavelet feature extraction and artificial neural networks for improving the performance of gas-liquid two-phase flow meters used in oil and petrochemical industries. Polymers 2021;13(21): https://doi.org/10.3390/polym1....
 
22.
Bahiraei M, Foong LK, Hosseini S, Mazaheri N. Predicting heat transfer rate of a ribbed triple-tube heat exchanger working with nanofluid using neural network enhanced by advanced optimization algorithms. Powder Technology 2021;381:459-76. https://doi.org/10.1016/j.powt....
 
23.
Qinfen L, Xinmin Z, Liren H. Optimal Design of Shifted Type Double-Sided Permanent Magnet Linear Synchronous Motors. Transactions of China Electrotechnical Society 2013;11:35-41.
 
24.
Adamkiewicz A, Nikończuk P. An attempt at applying machine learning in diagnosing marine ship engine turbochargers. Eksploatacja i Niezawodność – Maintenance and Reliability. 2022;24(4):795-804. doi:10.17531/ein.2022.4.19.
 
25.
Wang R, Jia X, Liu Z, Dong E, Li S, Cheng Z. Conditional generative adversarial network based data augmentation for fault diagnosis of diesel engines applied with infrared thermography and deep convolutional neural network. Eksploatacja i Niezawodność – Maintenance and Reliability. 2024;26(1). doi:10.17531/ein/175291.
 
26.
Electric Motor Temperature Dataset. Kırgsın W, 2021. Kaggle. https://www.kaggle.com/dataset... /wkirgsn/electric-motor-temperature. Erişim tarihi: 23.04.2024.
 
 
CITATIONS (5):
1.
Can deep learning effectively diagnose cardiac amyloidosis with 99mTc-PYP scintigraphy?
Adem Maman, Ishak Pacal, Fatih Bati
Journal of Radioanalytical and Nuclear Chemistry
 
2.
A robust deep learning framework for multiclass skin cancer classification
Burhanettin Ozdemir, Ishak Pacal
Scientific Reports
 
3.
Intelligent Systems in Production Engineering and Maintenance IV
Anna Borucka, Liniewski Jakub
 
4.
Dizel Motorlarda Silindir İçi Basınç Tahmini için Veri Odaklı Makine Öğrenimi Modellerinin Performans Analizi
Ahmet Karaoğlu, Hüseyin Söyler
Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi
 
5.
Security Simulation Analysis of Magnetic Core Loss Prediction Model based on KD-Tree Federated XGBoost Prediction
Sihan Lin, Xinyi Lai
2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE)
 
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top