神经网络优化的无感永磁同步电机控制系统

doi:10.16182/j.issn1004731x.joss.19-0562

系统仿真学报 ›› 2021, Vol. 33 ›› Issue (3): 622-630.doi: 10.16182/j.issn1004731x.joss.19-0562

• 仿真支撑平台/系统技术 • 上一篇下一篇

神经网络优化的无感永磁同步电机控制系统

马立新, 朱勇杰, 季乐延

上海理工大学机械工程学院,上海 200093

收稿日期:2019-10-25 修回日期:2019-12-06 出版日期:2021-03-18 发布日期:2021-03-18
作者简介:马立新(1960-),男,博士,教授,研究方向为电力系统稳定性与优化运行、电机控制、智能电网等。E-mail：1022151953@qq.com
基金资助:
国家自然科学基金(6120576)

Neural Network Optimized Sensorless Permanent Magnet Synchronous Motor Control System

Ma Lixin, Zhu Yongjie, Ji Leyan

School of mechanical engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2019-10-25 Revised:2019-12-06 Online:2021-03-18 Published:2021-03-18

摘要/Abstract

摘要： 针对永磁同步电机(Permanent Magnet Synchronous Motor,PMSM)转速和转子位置容易受到传感器传输信号精度不佳的问题,提出了扩展卡尔曼滤波算法来测算电机转速和转子位置的无传感控制系统,采用BP (Back-ProPagation)神经网络算法优化EKF (Extended Kalman Filter)算法的协方差矩阵,提高了转速、转子位置测算值的精确度。同时采用速度滑模控制器结合电流前馈解耦单元,改善整个控制系统的稳定性。仿真结果表明了该套系统可以对转速、转子位置进行精确测算,转子位置偏差值在±0.3 rad左右波动,与传统PI控制相比,转速恢复时间缩短了50%,超调极小,具有更强的鲁棒性,在电机控制中有较强的实际应用价值。

关键词: 永磁同步电机, 扩展卡尔曼滤波, BP (Back-ProPagation)神经网络, 速度滑模, 前馈解耦

Abstract: In order to solve the poor accuracy of the speed and rotor position of permanent magnet synchronous motor caused by sensor, a sensorless control system is proposed to calculate the speed and rotor position of PMSM with extended Kalman filtering algorithm. BP neural network algorithm is used to optimize the covariance matrix Q and R of EKF, which improves the accurate calculation values of rotational speed and rotor position. At the same time, the speed sliding mode controller combined with the current feed-forward decoupling unit are used to improve the stability of the whole control system. The simulation results show that the system can accurately calculate speed and rotor position and the deviation value of rotor position fluctuates around ±0.3 rad. Compared with the traditional PI control, the speed recovery time is shortened by 50%, and the overshoot is very small, the robustness is stronger. It has strong practical application value in motor control.

Key words: permanent magnet synchronous motor, extended Kalman filtering, BP(Back-ProPagation) neural network, speed sliding mode, feed-forward decoupling

中图分类号:

马立新, 朱勇杰, 季乐延. 神经网络优化的无感永磁同步电机控制系统[J]. 系统仿真学报, 2021, 33(3): 622-630.

Ma Lixin, Zhu Yongjie, Ji Leyan. Neural Network Optimized Sensorless Permanent Magnet Synchronous Motor Control System[J]. Journal of System Simulation, 2021, 33(3): 622-630.

参考文献

[1] 李英强, 杨明, 龙江, 等. 基于扩展卡尔曼滤波的永磁同步电机无电流传感器预测控制[J]. 电机与控制应用, 2018, 45(1): 107-113.
Li Yingqiang, Yang Ming, Long Jiang, et al.Current Sensorless Predictive Control based on Extended Kalman Filter for PMSM Drives[J]. Electric Machines Control Application, 2018, 45(1): 107-113.
[2] 王鑫, 李伟力, 程树康. 永磁同步电动机发展展望[J]. 微电机, 2007, 40(5): 69-72.
Wang Xin, Li Weili, Cheng Shukang.Development and Prospect of Permanent Magnet Synchronous Motor[J]. Micromotors, 2007, 40(5): 69-72.
[3] 周阳, 马立新, 袁沧虎. PMSM带前馈控制的模型参考自适应矢量控制系统的研究[J]. 电力科学与工程, 2018, 34(5): 18-23.
Zhou Yang, Ma Lixin, Yuan Canghu.Research on Model Reference Adaptive Vector Control System with Feedforward Control in PMSM[J]. Electric Power Science and Engineering, 2018, 34(5): 18-23.
[4] 谷涛, 李孟秋, 黄庆, 等. 基于EKF的永磁同步电机无位置传感器控制[J]. 电源技术, 2016, 40(2): 430-433.
Gu Tao, Li Mengqiu, Huang Qing, et al.Permanent Magnet Synchronous Motor Position Sensorless Control based on EKF[J]. Chinese Journal of Power Sources, 2016, 40(2): 430-433.
[5] 佘致廷, 邹薇, 董旺华, 等. 扩展卡尔曼滤波结合前馈补偿永磁同步电机位置估计[J]. 控制理论与应用, 2016, 33(10): 1312-1318.
She Zhiting, Zou Wei, Dong Wanghua, et al.Extended Kalman Filters Combined with Feed-forward Compensation for Permanent Magnet Synchronous Motor Position Estimation[J]. Control Theory & Applications, 2016, 33(10): 1312-1318.
[6] 张相胜, 田佳文, 潘丰. 无传感器PMSM中基于IGSO优化EKF的速度估计方法[J]. 计算机应用研究, 2019, 36(4): 1006-1009.
Zhang Xiangsheng, Tian Jiawen, Pan Feng.Method of EKF Speed Estimation for Sensorless PMSM based on IGSO Optimizing[J]. Application Research of Computers, 2019, 36(4): 1006-1009.
[7] 李冉. 永磁同步电机无位置传感器运行控制技术研究[D]. 杭州: 浙江大学, 2012.
Li Ran.Research on the Sensorless Control Technique of Permanent Magnet Synchronous Motor[D]. Hangzhou: Zhejiang University, 2012.
[8] 朱晓虹, 张广明, 梅磊, 等. 基于滑模速度控制器的PMSM无速度传感器控制研究[J]. 电机与控制应用, 2016, 43(1): 1-6.
Zhu Xiaohong, Zhang Guangming, Mei Lei, et al.Research on Sensorless Control of PMSM based on Sliding Mode Speed Controller[J]. Electric Machines Control Application, 2016, 43(1): 1-6.
[9] 董晓光, 邹轩, 张宇慧. 新型PMSM速度控制方法设计[J]. 信息技术, 2017, 41(9): 171-176.
Dong Xiaoguang, Zou Xuan, Zhang Yuhui.Design of New Speed Control Method for Permanent Magnet Synchronous Motor[J]. Information Technology, 2017, 41(9): 171-176.
[10] Zarchan P, Musoff H.Fundamentals of Kalman Filtering: A Practical Approach[M]. Reston: American Institute of Aeronautics and Astronautics, Inc. 2015.
[11] Guo Zizhao, Xiang Guofei, Pu Ming, Dian Songyi.Sensorless drive of Direct-torque-controlled PMSMs based on robust extended Kalman filter[C]// Proc of Control Conference. Piscataway. NJ: IEEE Press, 2016: 4711-4716.
[12] 秦永元, 张洪钺, 汪叔华. 卡尔曼滤波与组合导航原理[M]. 西安: 西北工业大学出版社, 2015: 2.
Qin Yongyuan, Zhang Hongyue, Wang Shuhua.Kalman Filtering and Integrated Navigation Principles[M]. Xi’an: Northwestern Polytechnic University Press, 2015: 2.

[1]	王志伟, 胡继宗, 王风杰, 黄杰. 基于非线性观测器的导航过程仿真研究[J]. 系统仿真学报, 2022, 34(5): 1127-1139.
[2]	李晖, 云昊, 岳红丽. 基于SVM逆系统的PMSM云模型整定PID控制[J]. 系统仿真学报, 2021, 33(8): 1846-1855.
[3]	余伟, 梁恒辉, 罗映. 一种改进差分进化算法的分数阶系统辨识研究[J]. 系统仿真学报, 2021, 33(5): 1157-1166.
[4]	王琳, 仲崇权. 交流伺服系统网络控制的仿真研究[J]. 系统仿真学报, 2019, 31(8): 1674-1682.
[5]	侯利民, 任一夫, 刘恒飞, 林栋. 基于无速度传感器的永磁同步电机滑模自抗扰控制[J]. 系统仿真学报, 2019, 31(5): 963-970.
[6]	杨洋, 李擎. UWB与SINS融合的行人导航方法[J]. 系统仿真学报, 2019, 31(12): 2636-2642.
[7]	王海璐, 苏中, 刘宁, 刘洪, 付国栋. 双天线GNSS辅助MINS导航方法研究[J]. 系统仿真学报, 2019, 31(11): 2434-2441.
[8]	尹星, 袁登科, 甄永成, 邵仲书, 吕相杰. 基于SVPWM的永磁同步电机DTC技术[J]. 系统仿真学报, 2019, 31(11): 2535-2542.
[9]	任志玲, 张钟保, 侯利民, 张广全, 林冬, 赵星. 基于IMC观测器的永磁同步电机预测控制[J]. 系统仿真学报, 2019, 31(1): 94-101.
[10]	沈艳霞, 靳保龙. 永磁同步电机模糊遗忘因子最小二乘法参数辨识[J]. 系统仿真学报, 2018, 30(9): 3404-3410.
[11]	吴定会, 黄旭, 全亚威, 纪志成. 基于变异珊瑚礁算法的永磁同步电机参数辨识[J]. 系统仿真学报, 2018, 30(8): 3024-3032.
[12]	王梦茹, 周珊, 王金波, 薛盼盼. 基于MATLAB的智能测试系统PMSM物理实时仿真平台[J]. 系统仿真学报, 2018, 30(6): 2225-2236.
[13]	陈锦宝, 李杰, 王艳, 纪志成. 融合Levy飞行的教与学优化算法的PMSM参数辨识[J]. 系统仿真学报, 2018, 30(4): 1456-1463.
[14]	吴定会, 张建宇, 沈艳霞, 纪志成. 基于多新息近似最小一乘算法PMSM参数辨识[J]. 系统仿真学报, 2018, 30(3): 1001-1007.
[15]	谷志丹, 李擎, 赵辉. 行人自主导航定位的多级滤波方法[J]. 系统仿真学报, 2018, 30(12): 4727-4732.

神经网络优化的无感永磁同步电机控制系统

Neural Network Optimized Sensorless Permanent Magnet Synchronous Motor Control System

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价