PID Control of Permanent Magnet Synchronous Motor Based on Improved Actor-Critic Framework

Junrong Liao; Shiyue Liu; Qinghe Wu; Jiabin Chen; Fuhua Wei

doi:10.1088/1742-6596/2213/1/012005

PID Control of Permanent Magnet Synchronous Motor Based on Improved Actor-Critic Framework

Junrong Liao^*
, Shiyue Liu
, Qinghe Wu
, Jiabin Chen
, Fuhua Wei

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

4 Citations (Scopus)

Abstract

Aiming at the shortcomings of the traditional PID control method that the parameters cannot be adjusted flexible, an improved Actor-Critic reinforcement learning algorithm combined with incremental PID control is proposed to improve the control performance of permanent magnet synchronous motor (PMSM). The strategy function of Actor and value function of Critic are approximated by two back propagation (BP) neural networks respectively. The simulation results show that the proposed algorithm has better control performance and effect than the traditional PID control method.

Original language	English
Article number	012005
Journal	Journal of Physics: Conference Series
Volume	2213
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/2213/1/012005
Publication status	Published - 24 Mar 2022
Externally published	Yes
Event	2022 8th International Conference on Electrical Engineering, Control and Robotics, EECR 2022 - Virtual, Online Duration: 13 Jan 2022 → 15 Jan 2022

Access to Document

10.1088/1742-6596/2213/1/012005

Cite this

@article{2fc6ceed167740bc94c7fd0a1dc93482,

title = "PID Control of Permanent Magnet Synchronous Motor Based on Improved Actor-Critic Framework",

abstract = "Aiming at the shortcomings of the traditional PID control method that the parameters cannot be adjusted flexible, an improved Actor-Critic reinforcement learning algorithm combined with incremental PID control is proposed to improve the control performance of permanent magnet synchronous motor (PMSM). The strategy function of Actor and value function of Critic are approximated by two back propagation (BP) neural networks respectively. The simulation results show that the proposed algorithm has better control performance and effect than the traditional PID control method.",

author = "Junrong Liao and Shiyue Liu and Qinghe Wu and Jiabin Chen and Fuhua Wei",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 2022 8th International Conference on Electrical Engineering, Control and Robotics, EECR 2022 ; Conference date: 13-01-2022 Through 15-01-2022",

year = "2022",

month = mar,

day = "24",

doi = "10.1088/1742-6596/2213/1/012005",

language = "English",

volume = "2213",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - PID Control of Permanent Magnet Synchronous Motor Based on Improved Actor-Critic Framework

AU - Liao, Junrong

AU - Liu, Shiyue

AU - Wu, Qinghe

AU - Chen, Jiabin

AU - Wei, Fuhua

N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.

PY - 2022/3/24

Y1 - 2022/3/24

N2 - Aiming at the shortcomings of the traditional PID control method that the parameters cannot be adjusted flexible, an improved Actor-Critic reinforcement learning algorithm combined with incremental PID control is proposed to improve the control performance of permanent magnet synchronous motor (PMSM). The strategy function of Actor and value function of Critic are approximated by two back propagation (BP) neural networks respectively. The simulation results show that the proposed algorithm has better control performance and effect than the traditional PID control method.

AB - Aiming at the shortcomings of the traditional PID control method that the parameters cannot be adjusted flexible, an improved Actor-Critic reinforcement learning algorithm combined with incremental PID control is proposed to improve the control performance of permanent magnet synchronous motor (PMSM). The strategy function of Actor and value function of Critic are approximated by two back propagation (BP) neural networks respectively. The simulation results show that the proposed algorithm has better control performance and effect than the traditional PID control method.

UR - https://www.scopus.com/pages/publications/85127535728

U2 - 10.1088/1742-6596/2213/1/012005

DO - 10.1088/1742-6596/2213/1/012005

M3 - Conference article

AN - SCOPUS:85127535728

SN - 1742-6588

VL - 2213

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 1

M1 - 012005

T2 - 2022 8th International Conference on Electrical Engineering, Control and Robotics, EECR 2022

Y2 - 13 January 2022 through 15 January 2022

ER -

PID Control of Permanent Magnet Synchronous Motor Based on Improved Actor-Critic Framework

Abstract

Access to Document

Other files and links

Fingerprint

Cite this