Online Automatic Parameter Optimization of Marine Permanent Magnet Synchronous Motor Speed Controller Based on Reinforcement Learning

被引：0

作者：

Peng, Tianyu ^{[1
]}

Li, Xuemin ^{[1
,2
,3
]}

Zhang, Jian ^{[3
]}

Wang, Chi ^{[1
]}

Yin, He ^{[1
]}

机构：

[1] Harbin Engn Univ, Coll Power & Energy Engn, Harbin 15001, Peoples R China

[2] Natl Key Lab Marine Engine Sci & Technol, Shanghai 201108, Peoples R China

[3] Shanghai Marine Diesel Engine Res Inst, Shanghai 201108, Peoples R China

来源：

39TH YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION, YAC 2024 | 2024年

关键词：

PMSM; reinforcement learning algorithm; rotary speed control;

D O I：

10.1109/YAC63405.2024.10598447

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

For the ship electric propulsion system, it is very important to maintain the stability of the speed. In this paper, the vector control system of permanent magnet synchronous motor (PMSM) is introduced. At the same time, aiming at the shortcomings of traditional proportional integral (PI) control, such as sensitivity to motor parameters and insufficient control performance when the load torque fluctuation is relatively large, a speed control strategy based on Q-learning reinforcement learning theory is proposed, which replaces the manual debugging process with intelligent algorithm online debugging.

引用

页码：750 / 754

页数：5

共 14 条

[1] Real-Time SIL Validation of a Novel PMSM Control Based on Deep Deterministic Policy Gradient Scheme for Electrified Vehicles [J].

Bhattacharjee, Soumava ;

Halder, Sukanta ;

Yan, Ye ;

Balamurali, Aiswarya ;

Iyer, Lakshmi Varaha ;

Kar, Narayan C. .

IEEE TRANSACTIONS ON POWER ELECTRONICS, 2022, 37 (08) :9000-9011

[2] Field-Oriented Control of the PMSM with 2-DOF PI Controller Tuned by Using PSO [J].

Celik, Hakan ;

Yigit, Tevfik .

2018 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP), 2018,

[3]

Najem Adil, 2023, 2023 3 INT C INN RES, P1

[4]

Nicola C. -I., 2023, 2023 3 INT C ELECT C, P1

[5] Improvement of PMSM Control Using Reinforcement Learning Deep Deterministic Policy Gradient Agent [J].

Nicola, Marcel ;

Nicola, Claudiu-Ionel .

2021 21ST INTERNATIONAL SYMPOSIUM ON POWER ELECTRONICS (EE 2021), 2021,

[6]

Peng W., 2020, P 2020 IEEE INT C KN, DOI [10.1109/ICKII50300.2020.9318882, DOI 10.1109/ICKII50300.2020.9318882]

[7]

Rossi Federico, 2023, IEEE EUROCON 2023 - 20th International Conference on Smart Technologies, P181, DOI 10.1109/EUROCON56442.2023.10198954

[8]

Schindler T., 2019, IKMT 2019 INN SMALL, P1

[9] Deep Reinforcement Learning Current Control of Permanent Magnet Synchronous Machines [J].

Schindler, Tobias ;

Broghammert, Lara ;

Karamanakost, Petros ;

Dietzt, Armin ;

Kennel, Ralph .

2023 IEEE INTERNATIONAL ELECTRIC MACHINES & DRIVES CONFERENCE, IEMDC, 2023,

[10]

Sutton RS, 2018, ADAPT COMPUT MACH LE, P1

← 1 2 →