A MTPA and Flux-Weakening Curve Identification Method Based on Physics-Informed Network Without Calibration

被引：57
|
作者：
Wang, Haowen [1 ]
Sun, Wei [1 ]
Jiang, Dong [1 ]
Qu, Ronghai [1 ]
机构：
[1] Huazhong Univ Sci & Technol, Sch Elect & Elect Engn, Wuhan 430074, Peoples R China
来源：
IEEE TRANSACTIONS ON POWER ELECTRONICS | 2023年 / 38卷 / 10期
关键词：
Flux-weakening (FW); interior permanent magnet synchronous motor (IPMSM); maximum torque per ampere (MTPA); physics-informed network; synchronous reluctance motor (SynRM); TORQUE;
D O I：
10.1109/TPEL.2023.3295913
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In order to improve the efficiency, interior permanent magnet synchronous motors (IPMSMs) or the synchronous reluctance motors (SynRMs) need to be calibrated to obtain the maximum torque per ampere (MTPA) and flux-weakening (FW) curves. In industrial application, there are different types of IPMSMs and SynRMs. It is expensive and time-consuming to build test benches to calibrate each motor. In this letter, a physics-informed network is proposed to obtain the MTPA and FW operating curves. Only data from accelerating experiment, when motor operates without load, are adopted. The test bench is unnecessary. Experimental results show the validity of proposed method.
引用
收藏
页码：12370 / 12375
页数：6
相关论文
共 50 条
  • [21] Research on Modeling Method of Autonomous Underwater Vehicle Based on a Physics-Informed Neural Network
    Zhao, Yifeng
    Hu, Zhiqiang
    Du, Weifeng
    Geng, Lingbo
    Yang, Yi
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (05)
  • [22] Investigation on aortic hemodynamics based on physics-informed neural network
    Du, Meiyuan
    Zhang, Chi
    Xie, Sheng
    Pu, Fan
    Zhang, Da
    Li, Deyu
    MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2023, 20 (07) : 11545 - 11567
  • [23] A Physics-Informed Neural Network-Based Waveguide Eigenanalysis
    Khan, Md Rayhan
    Zekios, Constantinos L.
    Bhardwaj, Shubhendu
    Georgakopoulos, Stavros V.
    IEEE ACCESS, 2024, 12 : 120777 - 120787
  • [24] A Physics-Informed Deep Neural Network based beam vibration framework for simulation and parameter identification
    Soyleyici, Cem
    Unver, Hakki Ozgur
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 141
  • [25] The application of improved physics-informed neural network (IPINN) method in finance
    Yuexing Bai
    Temuer Chaolu
    Sudao Bilige
    Nonlinear Dynamics, 2022, 107 : 3655 - 3667
  • [26] Physics-Informed neural network for level set method in vapor condensation
    Tang, Minghai
    Xin, Zhiqiang
    Wang, Lei
    INTERNATIONAL JOURNAL OF HEAT AND FLUID FLOW, 2024, 110
  • [27] The application of improved physics-informed neural network (IPINN) method in finance
    Bai, Yuexing
    Chaolu, Temuer
    Bilige, Sudao
    NONLINEAR DYNAMICS, 2022, 107 (04) : 3655 - 3667
  • [28] Forecasting Method for NOx Emission in Coal Fired Boiler Based on Physics-informed Neural Network
    Ren, Shaojun
    Zhu, Baoyu
    Weng, Qihang
    Deng, Zhiping
    Si, Fengqi
    Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering, 2024, 44 (20): : 8157 - 8165
  • [29] Physics-Informed Neural Network for Parameter identification of Air Conditioning Load Models
    Luo, Xiao
    Wang, Yifei
    Zhu, Qing
    Liu, Hanyang
    Wang, Shuhong
    Wu, Minghe
    2024 THE 7TH INTERNATIONAL CONFERENCE ON ENERGY, ELECTRICAL AND POWER ENGINEERING, CEEPE 2024, 2024, : 948 - 953
  • [30] A Physics-Informed Neural Network Approach to Solution and Identification of Biharmonic Equations of Elasticity
    Vahab, Mohammad
    Haghighat, Ehsan
    Khaleghi, Maryam
    Khalili, Nasser
    JOURNAL OF ENGINEERING MECHANICS, 2022, 148 (02)
12345