Improved Accuracy in Estimation of Temperature for Permanent Magnet Synchronous Motor (PMSM) using Machine Learning (ML) method for Electric Vehicle Application

Article Sidebar

Flow chart of the research work
PDF
Published: Nov 30, 2022
DOI: https://doi.org/10.17762/ijritcc.v10i11.5775
Keywords:
Electric Vehicles, Permanent Magnet Synchronous Motor, Machine Learning, Faults

Main Article Content

Prakhar Singh Bhadoria
Department Electronics & Communication Engineering Amity University Gwalior, India
Raghavendra Sharma
Department Electronics & Communication Engineering Amity University Gwalior, India
Rahul Dubey
Department of Electronics Engineering MITS Gwalior, India

Abstract

With the advancement of an electrical transportation system, demand for the efficient electric vehicles (EV’s) will be more. So, manufacturing industries of EV’s are using the latest technologies to design an efficient and reliable electric vehicles for the customers. Since, electric motor is the main driving component of the EVs, so our major concern is to protect the motor from various faults in the very early stage with better accuracy and with minimum error. Various types of faults which mainly oc-curs in the motors are, overheating, bearing fault, insulation breakdown, over speed, vibration, noise etc. So, in this paper Machine Learning (ML) technique is used to analyze various electrical parameters of Permanent Magnet Synchronous Motor (PMSM) taking coolant, ambient temperature, voltage, current, speed and torque as input parameters and winding temperature as output parameter. The test is performed in MATLAB software and the results found with the above method is found more improved and accurate with least error. The proposed method classifies the stator winding temperature into respective classes with 93.13% classification accuracy, sensitivity and specificity are 90.22% and 94.78% respectively.

Article Details

How to Cite
Bhadoria, P. S. ., Sharma, R. ., & Dubey, R. . (2022). Improved Accuracy in Estimation of Temperature for Permanent Magnet Synchronous Motor (PMSM) using Machine Learning (ML) method for Electric Vehicle Application. International Journal on Recent and Innovation Trends in Computing and Communication, 10(11), 22–27. https://doi.org/10.17762/ijritcc.v10i11.5775
Issue
Vol. 10 No. 11 (2022): November (2022) Issue
Section
Articles

References

Hassouna, F.M.A.; Nassar, R.; Tubaleh, H. Electric Vehicles as an Alternative to Conventional Vehicles: A Review. Int. J. Adv. Sci. Technol. 2020, 29, 5695–5701.

Mohammadi, F.; Nazri, G.-A.; Saif, M. Modeling, Simulation, and Analysis of Hybrid Electric Vehicle Using MATLAB/Simulink. In Proceedings of the 2019 International Conference on Power Generation Systems and Renewable Energy Technologies (PGSRET), Istanbul, Turkey, 26–27 August 2019; pp. 1–5.

(2015) Global ev outlook 2015. IEA, International Energy Agency, EVI, Electric Vehicles Initiative. Accessed 2015-04-27. Available: http://cleanenergyministerial.org/Portals/0/pdfs/EVI-globalEVOutlook2015-v14-landscape.pdf.

Bhadoria, P.S; Sharma, R; Dubey, R. Study on Machinery Fault Diagnosis using Signal Processing Techniques, Journal of Emerging Technologies and Innovative Research (JETIR), 2019, 6(6),247-250.

H, Li; Y, De. Survey on data driven fault diagnosis methods, Control and Decision, 2011, 26(1), pp. 1-9.

Kirchgassner, W; Wallscheid, O; Bocker, J. Estimating Electric Motor Temperatures with Deep Residual Machine Learning, IEEE trans. on power electron., 2021, 36(7), pp. 7480-7488.

M. Ganchev, C. Kral, H. Oberguggenberger, and T.Wolbank, Sensorless rotor temperature estimation of permanent magnet synchronous motor, Proc. Ind. Electron. Conf. Proc., pp. 2018–2023, 2011.

Kirchgässner, W; Wallscheid, O; and Böcker, J. Deep residual convolutional and recurrent neural networks for temperature estimation in permanent magnet synchronous motors, Proc. IEEE Int. Elect. Mach. Drives Conf., 2019, pp. 1439–1446.

Wallscheid, O; Specht, A; Böcker, J. Observing the permanent magnet temperature of synchronous motors based on electrical fundamental wave model quantities, IEEE Trans. Ind. Electron., 2017, 64(5), pp. 3921–3929.

Wallscheid, O; Huber, T; Peters, W; Böcker, J. Real-time capable methods to determine the magnet temperature of permanent magnet synchronous motors—A review, Proc. 40th Annu. Conf. IEEE Ind. Electron. Soc., 2014, pp. 811–818.

Celik, O; Salih, S. A Research on Machine Learning Methods and its Applications, Journal of Educational Technology & Online Learning, 2018, 1(3), pp. 25-40.

Guo, H; Ding, Q, Song, Y; Tang, H; Wang, L; Zhao, J. Predicting Temperature of Permanent Magnet Synchronous Motor based on Deep Neural Network, Energies- MDPI Journals, 2020, 13(4782), pp. 1-14.

Anuforo, K. Temperature Estimation in Permanent Magnet Synchronous Motor (PMSM) Components using Machine Learning, 2020, pp. 1-18.

Patel H, H; Prajapati, P. Study and Analysis of Decision Tree Based Classification Algorithms, International Journal of Computer Science and Engineering (JCSE), 2018, 6(10), pp. 74-78.