• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Study on automatic tuning method for PMSM sensorless control using deep learning without adjustment process

Research Project

Project/Area Number 20K04451
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 21010:Power engineering-related
Research InstitutionMeiji University (2022)
Seikei University (2020-2021)

Principal Investigator

Maekawa Sari  明治大学, 理工学部, 専任准教授 (90849225)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2021: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2020: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywords永久磁石同期モータ / オートチューニング / ニューラルネットワーク / 制御ゲイン / 安定性 / PMSM / センサレス制御 / 制御パラメータ / パラメータ同定 / 自動調整 / 学習 / 深層学習
Outline of Research at the Start

永久磁石同期モータを高効率に駆動するためには、制御ゲイン・機器定数などの制御パラメータを調整しており、これらを自動で測定・調整する研究も進められている。しかし、自動測定・調整のためにあらかじめ決めなければならない新たな設定パラメータが発生し、完全な調整レスによる自動設定ができていない。本研究の目的は、モータのセンサレス制御において、①既存の大量データと深層学習を用いることで設定パラメータを用いない機器定数の自動測定法を構築 ②複数の制御間の安定性を考慮したセンサレス制御系の制御ゲイン設計法を確立し、これらの知見を踏まえた ③センサレス制御系の制御パラメータ自動調整法を実現することである。

Outline of Final Research Achievements

In this study, a large number of motors with various power, torque, and speed ratings were created in simulation, and combinations of control parameters that are considered optimal for these motors were prepared. A neural network (ANN) was constructed to automatically adjust these optimal control parameters. As a result, an ANN capable of outputting control parameters appropriate for the input data representing unknown motor ratings was constructed. Furthermore, the obtained control parameter combinations were input to a simulator that can reproduce actual motor drive, and it was confirmed that the motor can be driven by position sensor-less control.

Academic Significance and Societal Importance of the Research Achievements

本研究成果により既存の多くの調整データが準備できれば熟練した技術者でなくても簡単にモータを安定に駆動するための制御パラメータのチューニングを行うことができるようになる。また,一般的な制御だけでなく大きの製品で用いられている複数の制御器切替にも対応可能でありより実践的な成果を享受できると考えられる。

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (3 results)

All 2022 2020

All Journal Article (1 results) (of which Peer Reviewed: 1 results) Presentation (2 results) (of which Int'l Joint Research: 2 results,  Invited: 1 results)

  • [Journal Article] Automatic Tuning Method for PMSM using Big Data based Artificial Neural Network2022

    • Author(s)
      Sari Maekawa
    • Journal Title

      IEEJ Journal of Industry Applications

      Volume: 11 Issue: 1 Pages: 185-186

    • DOI

      10.1541/ieejjia.L21000741

    • NAID

      130008139369

    • ISSN
      2187-1094, 2187-1108
    • Year and Date
      2022-01-01
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Presentation] Self-Tuning for each PMSM Controller using Big Data based ANN2022

    • Author(s)
      Sari Maekawa
    • Organizer
      2022 International Power Electronics Conference (IPEC-Himeji 2022- ECCE Asia)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] The Proposal of discriminating stable control bandwidth using ANN in sensorless speed control system for PMSM2020

    • Author(s)
      Tanaka Ami、Maekawa Sari
    • Organizer
      2020 22nd European Conference on Power Electronics and Applications (EPE'20 ECCE Europe)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi