Journal Home > Volume 8 , Issue 4
Chinese Journal of Electrical Engineering 2022, 8(4): 30-38 https://doi.org/10.23919/CJEE.2022.000036
Open Access | Issue | Published: 31 December 2022

Physics Informed Neural Network-based High-frequency Modeling of Induction Motors

Show Author's Information Zhenyu Zhao1,  Fei Fan1( ),  Quqin Sun2,  Huamin Jie1,  Zhou Shu1,  Wensong Wang1,  Kye Yak See1
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
Science and Technology on Thermal Energy and Power Laboratory, Wuhan Second Ship Design and Research Institute, Wuhan 430000, China
Keywords:
parameterization, Equivalent circuit, induction motor, high-frequency (HF) modeling, physics informed neural network
Cite this article:
Zhao Z, Fan F, Sun Q, et al. Physics Informed Neural Network-based High-frequency Modeling of Induction Motors. Chinese Journal of Electrical Engineering, 2022, 8(4): 30-38. https://doi.org/10.23919/CJEE.2022.000036
Download citation
EndNote(RIS)
BibTeX

182

Views

14

Downloads

Citations

7

Crossref

N/A

WoS

6

Scopus

0

CSCD

Abstract Full text About this article

The high-frequency (HF) modeling of induction motors plays a key role in predicting the motor terminal overvoltage and conducted emissions in a motor drive system. In this study, a physics informed neural network-based HF modeling method, which has the merits of high accuracy, good versatility, and simple parameterization, is proposed. The proposed model of the induction motor consists of a three-phase equivalent circuit with eighteen circuit elements per phase to ensure model accuracy. The per phase circuit structure is symmetric concerning its phase-start and phase-end points. This symmetry enables the proposed model to be applicable for both star- and delta-connected induction motors without having to recalculate the circuit element values when changing the motor connection from star to delta and vice versa. Motor physics knowledge, namely per-phase impedances, are used in the artificial neural network to obtain the values of the circuit elements. The parameterization can be easily implemented within a few minutes using a common personal computer (PC). Case studies verify the effectiveness of the proposed HF modeling method.


menu
Abstract
Full text
Outline
About this article

Physics Informed Neural Network-based High-frequency Modeling of Induction Motors

Show Author's information Zhenyu Zhao1, Fei Fan1( ), Quqin Sun2, Huamin Jie1, Zhou Shu1, Wensong Wang1, Kye Yak See1
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
Science and Technology on Thermal Energy and Power Laboratory, Wuhan Second Ship Design and Research Institute, Wuhan 430000, China

Abstract

The high-frequency (HF) modeling of induction motors plays a key role in predicting the motor terminal overvoltage and conducted emissions in a motor drive system. In this study, a physics informed neural network-based HF modeling method, which has the merits of high accuracy, good versatility, and simple parameterization, is proposed. The proposed model of the induction motor consists of a three-phase equivalent circuit with eighteen circuit elements per phase to ensure model accuracy. The per phase circuit structure is symmetric concerning its phase-start and phase-end points. This symmetry enables the proposed model to be applicable for both star- and delta-connected induction motors without having to recalculate the circuit element values when changing the motor connection from star to delta and vice versa. Motor physics knowledge, namely per-phase impedances, are used in the artificial neural network to obtain the values of the circuit elements. The parameterization can be easily implemented within a few minutes using a common personal computer (PC). Case studies verify the effectiveness of the proposed HF modeling method.

Keywords: parameterization, Equivalent circuit, induction motor, high-frequency (HF) modeling, physics informed neural network

References(27)

[1]

S Amarir, K Al-Haddad. A modeling technique to analyze the impact of inverter supply voltage and cable length on industrial motor-drives. IEEE Trans. Power Electron., 2008, 23(2): 753-762.
DOI Google Scholar
[2]
G Skibinski, R Kerkman, D Leggate, et al. Reflected wave modeling techniques for PWM AC motor drives. Proc. Appl. Power Electron. Conf. (APEC), February 15-19, 1998, Anaheim, CA, USA. IEEE, 1998: 1021-1029.
[3]

M Ghassemi. Accelerated insulation aging due to fast, repetitive voltages: A review identifying challenges and future research needs. IEEE Trans. Dielectr. Electr. Insul., 2019, 26(5): 1558-1568.
DOI Google Scholar
[4]
Z Yang, H Li, Z Yang, et al. Conducted electromagnetic interference analysis method for traction drive system in high speed trains. 2017 IEEE Transp. Electrific. Conf. Expo, Asia-Pacific, August 7-10, 2017, Harbin, China. IEEE, 2017: 1-5.
DOI
[5]

Z Zhang, Y Hu, X Chen, et al. A review on conductive common-mode EMI suppression methods in inverter fed motor drives. IEEE Access, 2021, 9: 18345-18360.
DOI Google Scholar
[6]

G Grandi, D Casadei, U Reggiani. Common- and differential-mode HF current components in AC motors supplied by voltage source inverters. IEEE Trans. Power Electron., 2004, 19(1): 16-24.
DOI Google Scholar
[7]
Z Yang, H Li, C Feng, et al. Survey on electromagnetic interference analysis for traction converters in railway vehicles. Proc. IEEE Int. Power Electron. Conf., May 20-24, 2018, Niigata, Japan. IEEE, 2018: 2058-2065.
DOI
[8]

L Ran, S Gokani, J Clare, et al. Conducted electromagnetic emissions in induction motor drive systems Ⅰ: Time domain analysis and identification of dominant modes. IEEE Trans. Power Electron., 1998, 13(4): 757-767.
DOI Google Scholar
[9]

M M Swamy, K Yamada, T Kume. Common mode current attenuation techniques for use with PWM drives. IEEE Trans. Power Electron., 2001, 16(2): 248-255.
DOI Google Scholar
[10]

L Wang, C N Ho, F Canales, et al. High-frequency modeling of the long-cable-fed induction motor drive system using TLM approach for predicting overvoltage transients. IEEE Trans. Power Electron., 2010, 25(10): 2653-2664.
DOI Google Scholar
[11]

G Suresh, A Toliyat, A Rendusara, et al. Predicting the transient effects of PWM voltage waveform on the stator windings of random wound induction motors. IEEE Trans. Power Electron., 1999, 14(1): 23-30.
DOI Google Scholar
[12]
K Maki, H Funato, L Shao. Motor modeling for EMC simulation by 3-D electromagnetic field analysis. 2009 IEEE International Electric Machines and Drives Conf., May 3-6, 2009, Miami, FL, USA. IEEE, 2009: 103-108.
[13]

V Mihaila, S Duchesne, D Roger. A simulation method to predict the turn-to-turn voltage spikes in a PWM fed motor winding. IEEE Trans. Dielectr. Electr. Insul., 2011, 18(5): 1609-1615.
DOI Google Scholar
[14]

Y Ryu, M Yea, J Kim, et al. Stator impedance modeling platform for the electromagnetic compatibility aware design of 3.7-to 7.5-kW squirrel-cage induction motors. IEEE Trans. Ind. Electron., 2021, 68(11): 11255-11265.
DOI Google Scholar
[15]

L Ran, S Gokani, J Clare, et al. Conducted electromagnetic emissions in induction motor drive systems part Ⅱ: Frequency domain models. IEEE Trans. Power Electron., 1998, 13(4): 768-776.
DOI Google Scholar
[16]

F Fan, K Y See, X Liu, et al. Systematic common-mode filter design for inverter-driven motor system based on in-circuit impedance extraction. IEEE Trans. Electromagn. Compat., 2020, 62(5): 1711-1722.
DOI Google Scholar
[17]

F Costa, C Vollaire, R Meuret. Modeling of conducted common mode perturbations in variable-speed drive systems. IEEE Trans. Electromagn. Compat., 2005, 47(4): 1012-1021.
DOI Google Scholar
[18]

A F Moreira, T A Lipo, G Venkataramanan, et al. High-frequency modeling for cable and induction motor overvoltage studies in long cable drives. IEEE Trans. Ind. Appl., 2002, 38(5):1297-1306.
DOI Google Scholar
[19]

A Boglietti, A Cavagnino, M Lazzari. Experimental high-frequency parameter identification of AC electrical motors. IEEE Trans. Ind. Appl., 2007, 43(1): 23-29.
DOI Google Scholar
[20]

J Sun, L Xing. Parameterization of three-phase electric machine models for EMI simulation. IEEE Trans. Power Electron., 2014, 29(1): 36-41.
DOI Google Scholar
[21]

M S Toulabi, L Wang, L Bieber, et al. A universal high-frequency induction machine model and characterization method for arbitrary stator winding connections. IEEE Trans. Energy Convers., 2019, 34(3): 1164-1177.
DOI Google Scholar
[22]
M Schinkel, S Weber, S Guttowski, et al. Efficient HF modeling and model parameterization of induction machines for time and frequency domain simulations. Proc. IEEE Appl. Power Electron. Conf. Expo. (APEC), March 19-23, 2006, Dallas, TX, USA. IEEE, 2006: 1-6.
[23]

B Mirafzal, G Skibinski, R Tallam. Determination of parameters in the universal induction motor model. IEEE Trans. Ind. Appl., 2009, 45(1): 142-151.
DOI Google Scholar
[24]

V Karakaşlı, F Gross, T Braun, et al. High-frequency modeling of delta- and star-connected induction motors. IEEE Trans. Electromagn. Compat., 2022, 64(4): 1533-1544.
DOI Google Scholar
[25]

M Degano, P Zanchetta, L Empringham, et al. HF induction motor modeling using automated experimental impedance measurement matching. IEEE Trans. Ind. Electron., 2012, 59(10): 3789-3796.
DOI Google Scholar
[26]

H Chen, S Ye. Modeling of common-mode impedance of an inverter-fed induction motor from online measurement. IEEE Trans. Electromagn. Compat., 2018, 60(5): 1581-1589.
DOI Google Scholar
[27]
Z Zhao, F Fan, Q Sun, et al. High-frequency modeling of induction motor using multilayer perceptron. Proc. Asia-Pacific Int. Symp. Electro. Compat., September 1-4, 2022, Beijing, China. IEEE, 2022: 222-224.
DOI
Publication history
Copyright
Rights and permissions

Publication history

Received: 20 October 2022
Revised: 10 November 2022
Accepted: 21 November 2022
Published: 31 December 2022
Issue date: December 2022

Copyright

© 2022 China Machinery Industry Information Institute

Rights and permissions

Return