Electromagnetic Design Optimization of a PMSG Using a Deep Neural Network Approach

被引:0
|
作者
Hernandez, C. [1 ]
Campos, B. [1 ]
Diaz, L. [1 ]
Lara, J. [2 ]
Arjona, M. A. [1 ]
机构
[1] Natl Technol Inst Mexico TNM, La Laguna Inst Technol, Grad Dept, Torreon 27000, Mexico
[2] Natl Technol Inst Mexico TNM, Lerdo Inst Technol, Grad Dept, Lerdo 35150, Mexico
关键词
Artificial neural networks; Optimization; Stator cores; Windings; Rotors; Correlation; Air gaps; Stator windings; Iron; Generators; Deep neural network (DNN); finite element method; genetic algorithms; optimization; permanent magnet synchronous generator (PMSG); NONDOMINATED SORTING APPROACH; ALGORITHM;
D O I
10.1109/TMAG.2024.3518536
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
This article presents the electromagnetic design optimization of a permanent magnet synchronous generator (PMSG) based on machine learning (ML). First, the optimization methodology is presented; then, a correlation and a sensitivity analysis are carried out to determine the set of design variables. The optimization goal is maximizing efficiency, which is equivalent to minimizing electrical PMSG losses. It also considers the core and copper materials by minimizing their weight. A deep neural network (DNN) architecture is developed and trained using PMSG 2D-FE data. The DNN is based on the nonlinear rectified linear unit (ReLU). The resulting DNN was later used to construct the PMSG objective function, which was then solved using non-sorting genetic algorithms. Numerical results and comparisons between two genetic algorithms are given to demonstrate the validity of the proposed approach.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Electromagnetic Design Optimization of a PMSG Using a Deep Neural Network Approach
    Campos, Belen
    Diaz, Luis
    Hernandez, Concepcion
    Arjona, Marco
    Lara, Jorge
    2024 IEEE 21ST BIENNIAL CONFERENCE ON ELECTROMAGNETIC FIELD COMPUTATION, CEFC 2024, 2024,
  • [2] Optimization design of electromagnetic system by neural network method
    Liu, GJ
    Lu, JG
    Su, XP
    Li, WH
    Tang, GF
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON ELECTROMAGNETIC FIELD PROBLEMS AND APPLICATIONS, 2000, : 223 - 226
  • [3] A Dual Neural Network Approach to Topology Optimization for Thermal-Electromagnetic Device Design
    Jasperson, Benjamin A.
    Wood, Michael G.
    Johnson, Harley T.
    COMPUTER-AIDED DESIGN, 2024, 168
  • [4] A neural network inversion approach to electromagnetic device design
    Marinova, I
    Panchev, C
    Katsakos, D
    IEEE TRANSACTIONS ON MAGNETICS, 2000, 36 (04) : 1080 - 1084
  • [5] Neural network inversion approach to electromagnetic device design
    Marinova, Iliana
    Panchev, Christo
    Katsakos, Demetrios
    IEEE Transactions on Magnetics, 2000, 36 (4 I) : 1080 - 1084
  • [6] Automated Design Optimization for CMOS Rectifier Using Deep Neural Network (DNN)
    Ho, Heng Wah
    Lau, Wendy W. Y.
    2019 IEEE MTT-S WIRELESS POWER TRANSFER CONFERENCE (WPTC) / IEEE PELS WORKSHOP ON EMERGING TECHNOLOGIES: WIRELESS POWER (WOW) / WIRELESS POWER WEEK (WPW 2019), 2019, : 599 - 603
  • [7] Turbine Design and Optimization for a Supercritical CO2 Cycle Using a Multifaceted Approach Based on Deep Neural Network
    Saeed, Muhammad
    Berrouk, Abdallah S.
    Burhani, Burhani M.
    Alatyar, Ahmed M.
    Wahedi, Yasser F. Al
    ENERGIES, 2021, 14 (22)
  • [8] Optimization of parameter design: an intelligent approach using neural network and simulated annealing
    Su, CT
    Chang, HH
    INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2000, 31 (12) : 1543 - 1549
  • [9] Modeling extra-deep electromagnetic logs using a deep neural network
    Alyaev, Sergey
    Shahriari, Mostafa
    Pardo, David
    Javier Omella, Angel
    Larsen, David Selvag
    Jahani, Nazanin
    Suter, Erich
    GEOPHYSICS, 2021, 86 (03) : E269 - E281
  • [10] An Embedded Feature Whitening Approach to Deep Neural Network Optimization
    Yong, Hongwei
    Zhang, Lei
    COMPUTER VISION, ECCV 2022, PT XXIII, 2022, 13683 : 334 - 351