Extreme learning machine-based field-oriented feedback linearization speed control of permanent magnetic synchronous motors

被引：9

作者：

Zheng, Yusai ^{[1
,2
]}

Cao, Zhenwei ^{[1
]}

Wang, Song ^{[2
]}

Man, Zhihong ^{[1
]}

Chuei, Raymond ^{[1
]}

机构：

[1] Swinburne Univ Technol, Sch Software & Elect Engn, Melbourne, Vic 3122, Australia

[2] Shandong Univ, Sch Mech Elect & Informat Engn, Weihai 264209, Peoples R China

来源：

NEURAL COMPUTING & APPLICATIONS | 2022年 / 34卷 / 07期

基金：

澳大利亚研究理事会;

关键词：

PMSM; Extreme learning machine; Feedback linearization control; Field-oriented control; Uncertainty; NEURAL-NETWORK APPROXIMATION; IMPLEMENTATION; REJECTION; SYSTEMS;

D O I：

10.1007/s00521-021-06722-z

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An extreme learning machine (ELM)-based field-oriented feedback linearization speed control (ELMFOFLC) is proposed to enhance the robustness and tracking performance of a permanent magnetic synchronous motor (PMSM) system. First, the field-oriented control (FOC) is adopted to control the electromagnetic torque and the stator magnetic flux of PMSM independently with a detailed discussion on effects especially brought by the model parameter uncertainties on a FOC-based PMSM model. Then, three field-oriented feedback linearization controllers (FOFLCs) are designed to control the electromagnetic torque loop, the stator magnetic flux loop and the outer speed loop, respectively, and cancel nonlinearities in these three loops. Furthermore, a specific ELM is proposed based on the analysis of the characteristics and the uncertainties of PMSM with FOFLC. The stability is proved using the Lyapunov method. Finally, comprehensive simulations and experiments demonstrate that the proposed control is robust to various uncertainties with a superior speed tracking performance.

引用

页码：5267 / 5282

页数：16

共 38 条

[11] An Artificial Neural Network approximation based decomposition approach for parameter estimation of system of ordinary differential equations
Dua, Vivek
[J]. COMPUTERS & CHEMICAL ENGINEERING, 2011, 35 (03) : 545 - 553
[12] Gao ZQ, 2003, P AMER CONTR CONF, P4989
[13] Grizzle J. W., 2002, NONLINEAR SYSTEMS, V3
[14] From PID to Active Disturbance Rejection Control
Han, Jingqing
[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2009, 56 (03) : 900 - 906
[15] PI Control Plus Electric Current Loops for PM Synchronous Motors
Hernandez-Guzman, Victor M.
Silva-Ortigoza, Ramon
[J]. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2011, 19 (04) : 868 - 873
[16] Extreme-learning-machine-based FNTSM control strategy for electronic throttle
Hu, Youhao
Wang, Hai
Cao, Zhenwei
Zheng, Jinchuan
Ping, Zhaowu
Chen, Long
Jin, Xiaozheng
[J]. NEURAL COMPUTING & APPLICATIONS, 2020, 32 (18) : 14507 - 14518
[17] Extreme learning machine: Theory and applications
Huang, Guang-Bin
Zhu, Qin-Yu
Siew, Chee-Kheong
[J]. NEUROCOMPUTING, 2006, 70 (1-3) : 489 - 501
[18] A compound control method for the rejection of spatially periodic and uncertain disturbances of rotary machines and its implementation under uniform time sampling
Huo, Xin
Tong, Xin-Gang
Liu, Kang-Zhi
Ma, Ke-Mao
[J]. CONTROL ENGINEERING PRACTICE, 2016, 53 : 68 - 78
[19] Improved Deadbeat Predictive Current Control Combined Sliding Mode Strategy for PMSM Drive System
Jiang, Yajie
Xu, Wei
Mu, Chaoxu
Liu, Yi
[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2018, 67 (01) : 251 - 263
[20] Liu J, 2013, Radial basis function (RBF) neural network control for mechanical systems: Design, analysis and MATLAB simulation, DOI [10.1007/978-3-642-34816-7, DOI 10.1007/978-3-642-34816-7]

← 1 2 3 4 →