基于模糊神经网络的永磁同步电机伺服系统研究

doi:10.16180/j.cnki.issn1007-7820.2022.06.013

摘要/Abstract

摘要：

永磁同步电机具有非线性、强耦合的特性,常规的矢量控制方法难以对其进行精确控制。此外,电机系统易受负载扰动影响,从而产生转速和电磁转矩波动。针对转速环参数固定会导致系统响应速度慢、超调量大的问题,文中提出了一种模糊径向基神经网络PID控制策略,用以替代矢量控制系统中转速环PID控制。将神经网络和模糊控制相结合,基于增量式PID控制方式,利用梯度下降优化算法动态调整转速环中的PID参数。系统模型仿真结果表明,模糊神经网络PID控制的电机系统超调量较小,相较于常规PID控制,新模型在低速和高速运行的启动时间分别缩短了66.7%和75.9%,动态响应更快,具有更好的鲁棒性和抗干扰能力。利用DSP搭建了实验平台,实验结果也证明了该控制方法的有效性。

关键词: 永磁同步电机, 伺服系统, 模糊控制器, 矢量控制, 径向基神经网络, 增量式PID, 梯度下降法, 转矩脉动

Abstract:

Permanent magnet synchronous motors have nonlinear and strong coupling characteristics, and it is difficult to accurately control them with conventional vector control methods. Besides, the motor system is susceptible to load disturbances, resulting in speed and electromagnetic torque fluctuations. In view of the problem of slow system response and large overshoot caused by fixed speed loop parameters, this study proposes a fuzzy radial basis function neural network PID control strategy to replace the PID control of speed loop in the vector control system. Based on the incremental PID control method, this strategy combines neural network and fuzzy control, and uses the gradient descent optimization algorithm to dynamically adjust the PID parameters in the speed loop. The simulation results show that the overshoot of the motor system controlled by the fuzzy neural network PID is small. Compared with conventional PID control, the proposed method has reduced the start-up time of low-speed and high-speed operation by 66.7% and 75.9%, respectively, and has faster dynamic response, better robustness and anti-interference ability. The experimental platform is built using DSP, and the experimental results prove the effectiveness of the control method.

Key words: permanent magnet synchronous motor, server system, fuzzy logical controller, vector control, radial basis function neural network, increment PID, gradient descent, torque pulsation

中图分类号:

TP273

王培宇,马立新. 基于模糊神经网络的永磁同步电机伺服系统研究[J]. 电子科技, 2022, 35(6): 83-88.

WANG Peiyu,MA Lixin. Research on Permanent Magnet Synchronous Motor Servo System Based on Fuzzy Neural Network[J]. Electronic Science and Technology, 2022, 35(6): 83-88.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

图11

参考文献 18

[1]	杨明, 付博, 李钊, 等. 永磁同步电动机矢量控制电压解耦控制研究[J]. 电气传动, 2010, 40(5):24-28.
	Yang Ming, Fu Bo, Li Zhao, et al. Research on voltage decoupling control of vector control for permanent magnet synchronous motor[J]. Electric Drive, 2010, 40(5):24-28.
[2]	Lu P, Gu M, Yang Y, et al. Research on adaptive control of PMSM based on fuzzy PID[C]. Chongqing: IEEE the Third Advanced Information Management,Communicates,Electronic and Automation Control Conference, 2019.
[3]	黄松, 李海剑, 石伟. 基于扰动观测器的内置式 PMSM 无传感器控制[J]. 电子科技, 2020, 33(1):57-62.
	Huang Song, Li Haijia, Shi Wei. Interior PMSM sensorless control based on disturbance observer[J]. Electronic Science and Technology, 2020, 33(1):57-62.
[4]	胡建秋, 丁学明. 永磁同步电机的双闭环调速系统设计[J]. 电子科技, 2019, 32(3):21-25.
	Hu Jianqiu, Ding Xueming. Design of double closed-loop speed regulating system for permanent magnet synchronous motor[J]. Electronic Science and Technology, 2019, 32(3):21-25.
[5]	杨博涵. 基于模糊PI的永磁同步电机伺服控制系统研究[D]. 大连: 大连海事大学, 2019.
	Yang Bohan. Study of a permanent magnet synchronous motor servo control system based on fuzzy PI[D]. Dalian: Dalian Maritime University, 2019.
[6]	霍召晗, 许鸣珠. 基于小波神经网络 PID 的永磁同步电机转速控制[J]. 电机与控制应用, 2019, 46(11):1-6.
	Huo Zhaohan, Xu Mingzhu. Speed control of permanent magnet synchronous motor based on wavelet neural network PID[J]. Electric Machines & Control Application, 2019, 46(11):1-6.
[7]	欧峰, 陈洪, 陈胜来. 基于模糊PID控制的永磁同步电机控制器研究[J]. 计算机测量与控制, 2017, 25(4):40-43.
	Ou Feng, Chen Hong, Chen Shenglai. Research on fuzzy PID control for PMSM[J]. Computer Measurement & Control, 2017, 25(4):40-43.
[8]	祁春清, 宋正强. 基于粒子群优化模糊控制器永磁同步电机控制[J]. 中国电机工程学报, 2006, 26(17):158-162.
	Qi Chunqing, Song Zhengqiang. Controlling of permanent-magnet synchronous machine based on particle swarm optimization fuzzy logical controller[J]. Proceedings of the CSEE, 2006, 26(17):158-162.
[9]	崔家瑞, 李擎, 张波, 等. 永磁同步电机变论域自适应模糊PID控制[J]. 中国电机工程学报, 2013, 33(S1):190-194.
	Cui Jiarui, Li Qing, Zhang Bo, et al. Permanent magnet synchronous motor of variable universe adaptive fuzzy PID control[J]. Proceedings of the CSEE, 2013, 33(S1):190-194.
[10]	陈文卓, 靳文涛, 马可. 永磁同步电机双模糊矢量控制系统研究[J]. 电气传动, 2019, 49(8):7-10.
	Chen Wenzhuo, Jin Wentao, Ma Ke. Research of PMSM field orientated control system using dual-fuzzy controllers[J]. Electric Drive, 2019, 49(8):7-10.
[11]	林伟杰. 永磁同步电机伺服系统控制策略的研究[D]. 杭州: 浙江大学, 2005.
	Lin Weijie. Research on control strategy of permanent magnet synchronous motor servo system[D]. Hangzhou: Zhejiang University, 2005.
[12]	赵剑飞, 丁朋飞, 翟雪松. 基于模糊神经网络的纯电动车永磁同步电机矢量控制[J]. 电机与控制应用, 2018, 45(12):108-112.
	Zhao Jianfei, Ding Pengfei, Zhai Xuesong. Vector control of permanent magnet synchronous motor for electric vehicle based on fuzzy neural network[J]. Electric Machines & Control Application, 2018, 45(12):108-112.
[13]	李学伟, 马立新, 袁沧虎. 模糊伸缩因子优化变论域的模糊 PID 矢量控制研究[J]. 电力科学与工程, 2019, 35(2):15-19.
	Li Xuewei, Ma Lixin, Yuan Canghu. Research on fuzzy PID vector control based on fuzzy expansion factor optimization variable domain[J]. Electric Power Science and Engineering, 2019, 35(2):15-19.
[14]	李佳懿. 永磁同步电机的递归模糊神经网络控制研究[D]. 沈阳: 沈阳工业大学, 2019.
	Li Jiayi. The research on permanent magnet synchronous motor based on recurrent fuzzy neural network control[D]. Shenyang: Shenyang University of Technology, 2019.
[15]	张艳, 郭凯, 丁茂森. 船舶柴油发电机组转速的模糊 RBF 神经网络PID 控制[J]. 船电技术, 2014, 34(5):1-5.
	Zhang Yan, Guo Kai, Ding Maosen. Fuzzy RBF neural network based speed PID control for marine diesel generator sets[J]. Marine Electric & Electronic Engineering, 2014, 34(5):1-5.
[16]	刘金琨. 先进PID控制MATLAB仿真[M].4版. 北京: 电子工业出版社, 2016.
	Liu Jinkun. Advanced PID control MATLAB simulation[M].4th ed. Beijing: Publishing House of Electronics Industry, 2016.
[17]	Zhang M G, Li W H, Liu M Q. Adaptive PID control strategy based on RBF neural network identification[C]. Beijing: IEEE International Conference on Neural Network and Brain, 2005.
[18]	潘玉成, 刘宝顺, 黄先洲, 等. 茶叶杀青机模糊RBF神经网络PID温控系统设计与试验[J]. 茶叶科学, 2019, 39(2):139-149.
	Pan Yucheng, Liu Baoshun, Huang Xianzhou, et al. Design and experiment of the temperature control system of the fuzzy RBF neural network PID in tea fixing machine[J]. Journal of Tea Science, 2019, 39(2):139-149.

控制方法	常规PID	模糊RBF神经网络PID
高速运行启动时间/s	0.079	0.019
高速运行超调量/%	20.6	1.6
低速运行启动时间/s	0.108	0.036
低速运行超调量/%	12.0	0.1