留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于UMAC的RBF神经网络PID控制

李明 封航 张延顺

李明, 封航, 张延顺等 . 基于UMAC的RBF神经网络PID控制[J]. 北京航空航天大学学报, 2018, 44(10): 2063-2070. doi: 10.13700/j.bh.1001-5965.2017.0777
引用本文: 李明, 封航, 张延顺等 . 基于UMAC的RBF神经网络PID控制[J]. 北京航空航天大学学报, 2018, 44(10): 2063-2070. doi: 10.13700/j.bh.1001-5965.2017.0777
LI Ming, FENG Hang, ZHANG Yanshunet al. RBF neural network tuning PID control based on UMAC[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(10): 2063-2070. doi: 10.13700/j.bh.1001-5965.2017.0777(in Chinese)
Citation: LI Ming, FENG Hang, ZHANG Yanshunet al. RBF neural network tuning PID control based on UMAC[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(10): 2063-2070. doi: 10.13700/j.bh.1001-5965.2017.0777(in Chinese)

基于UMAC的RBF神经网络PID控制

doi: 10.13700/j.bh.1001-5965.2017.0777
基金项目: 

国家自然科学基金 11202010

国家自然科学基金 61473019

详细信息
    作者简介:

    李明  女, 博士, 讲师。主要研究方向:振动分析与控制、惯性导航与组合导航

    封航  男, 硕士研究生。主要研究方向:精密伺服控制、运动控制

    张延顺   男, 博士, 副教授。主要研究方向:惯性导航与组合导航

    通讯作者:

    李明, E-mail:liliyalm@buaa.edu.cn

  • 中图分类号: TP301.6

RBF neural network tuning PID control based on UMAC

Funds: 

National Natural Science Foundation of China 11202010

National Natural Science Foundation of China 61473019

More Information
  • 摘要:

    针对通用电机运动控制器(UMAC)下的传统PID控制和现有的模糊PID控制自适应性和鲁棒性较差,伺服系统的动静态性能不理想的问题,将RBF神经网络引入到UMAC的PID参数调节中,增强伺服系统的自适应性和鲁棒性,并提高系统动静态特性。通过UMAC的嵌入式PLC程序对算法进行了实现,位置阶跃响应实验和正弦跟踪实验表明,RBF神经网络PID控制下的伺服电机位置阶跃响应上升时间由传统PID控制下的0.164 s和模糊PID控制下的0.118 s减小到了0.017 s,峰值时间由传统PID控制下的0.196 s和模糊PID控制下的0.131 s减小到了0.023 s,调节时间由传统PID控制下的0.216 s和模糊PID控制下的0.142 s减小到了0.025 s,电机响应速度变快;RBF神经网络PID控制下的伺服电机位置正弦响应动态跟随最大误差由传统PID控制下的188 counts和模糊PID控制下的120 counts减小到了39 counts,且误差波动较小、平稳,伺服电机动态跟随性能显著提高。

     

  • 图 1  基于UMAC的伺服系统结构

    Figure 1.  Structure of servosystem based on UMAC

    图 2  PMSM传递模型

    Figure 2.  Transfer model of PMSM

    图 3  RBF神经网络结构

    Figure 3.  Structure of RBF neural network

    图 4  RBF神经网络PID控制的PMSM伺服仿真模型

    Figure 4.  Servo simulation model of PMSM based on RBF neural network tuning PID control

    图 5  传统PID控制、模糊PID控制、RBF神经网络PID控制下位置阶跃响应曲线

    Figure 5.  Step response of position by traditional PID control, fuzzy PID control and RBF neural network tuning PID control

    图 6  UMAC的PID算法原理图

    Figure 6.  PID algorithm schematic diagram of UMAC

    图 7  RBF神经网络PID控制PLC程序流程图

    Figure 7.  PLC program flowchart of RBF neural network tuning PID control

    图 8  精密装配系统

    Figure 8.  Precise assembly system

    图 9  基于UMAC的伺服系统

    Figure 9.  Servosystem based on UMAC

    图 10  给定位置条件下位置阶跃响应曲线

    Figure 10.  Position step response curves under given position condition

    图 11  给定位置条件下位置正弦响应曲线

    Figure 11.  Position sinusoidal response curves under given position condition

  • [1] 夏链, 俞晓慧, 韩江, 等.基于UMAC的工业机器人运动控制系统设计[J].合肥工业大学学报(自然科学版), 2015, 38(8):1009-1012. doi: 10.3969/j.issn.1003-5060.2015.08.001

    XIA L, YU X H, HAN J, et al.Design of motion control system of industrial robot based on UMAC[J].Journal of Hefei University of Technology(Natural Science), 2015, 38(8):1009-1012(in Chinese). doi: 10.3969/j.issn.1003-5060.2015.08.001
    [2] SPIESER A, IVANOV A.Design of an electrochemical micromachining machine[J].International Journal of Advanced Manufacturing Technology, 2015, 78(5-8):737-752. doi: 10.1007/s00170-014-6332-3
    [3] 刘金琨.先进PID控制MATLAB仿真[M].北京:电子工业出版社, 2011:301-319.

    LIU J K.MATLAB simulmion of advanced PID control[M].Beijing:Electronic Industry Press, 2011:301-319(in Chinese).
    [4] 赵凤姣, 厉虹.PID控制器改进方法研究[J].控制工程, 2015, 22(3):425-431. http://d.old.wanfangdata.com.cn/Periodical/jczdh201503011

    ZHAO F J, LI H.Research on improved methods of PID controller[J].Control Engineering of China, 2015, 22(3):425-431(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/jczdh201503011
    [5] 廖洪波, 范世珣, 黑墨, 等.光电稳定平台伺服系统动力学建模与参数辨识[J].光学精密工程, 2015, 23(2):477-484. http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201502022

    LIAO H B, FAN S X, HEI M, et al.Modeling and parameter identification for electro-optical stabilized platform servo systems[J].Optics and Precision Engineering, 2015, 23(2):477-484(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201502022
    [6] HUANG W L, KUO F C, CHOU S C, et al.High-performance and high-precision servo control of a single-deck dual-axis PMLSM stage[J].International Journal of Advanced Manufacturing Technology, 2017, 90(1-4):865-874. doi: 10.1007/s00170-016-9355-0
    [7] 王克选, 李新国.基于PMAC的模糊自整定PID算法设计[J].计算机仿真, 2013, 30(9):331-334. doi: 10.3969/j.issn.1006-9348.2013.09.077

    WANG K X, LI X G.Design of fuzzy self-regulation PID algorithm based on PMAC[J].Computer Simulation, 2013, 30(9):331-334(in Chinese). doi: 10.3969/j.issn.1006-9348.2013.09.077
    [8] 白晶, 于喜红, 秦现生.基于PMAC的码垛机器人模糊PID算法研究[J].机械设计与制造工程, 2016, 45(3):46-49. doi: 10.3969/j.issn.2095-509X.2016.03.010

    BAI J, YU X H, QIN X S.Study on fuzzy PID algorithm for palletizing robot based on PMAC[J].Machine Design and Manufacturing Engineering, 2016, 45(3):46-49(in Chinese). doi: 10.3969/j.issn.2095-509X.2016.03.010
    [9] TIAN C X, LI X W, HU Z.The study of fuzzy self-regulation PID algorithm based on PMAC[J].Machinery & Electronics, 2010, 57(10):60-63.
    [10] SONG Y, LIU Y, ZHU H.A PMSM speed controller based on RBF neural network and single neuron PID[J].Electronics World, 2017, 38(2):122-126. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dzsj201702061
    [11] 江维, 吴功平, 曹琪, 等.输电线路带电作业机器人机械手RBF神经网络控制[J].东北大学学报(自然科学版), 2017, 38(10):1388-1393. doi: 10.12068/j.issn.1005-3026.2017.10.005

    JIANG W, WU G P, CAO Q, et al.RBF neural network control of live operation robot manipulator for high voltage transmission line[J].Journal of Northeastern University(Natural Science), 2017, 38(10):1388-1393(in Chinese). doi: 10.12068/j.issn.1005-3026.2017.10.005
    [12] 周佳, 卢少武, 周凤星.伺服位置控制参数的RBF神经网络自整定研究[J].组合机床与自动化加工技术, 2016(3):75-77. http://d.old.wanfangdata.com.cn/Periodical/zhjc201603021

    ZHOU J, LU S W, ZHOU F X.Study on position control parameters auto-tuning of servo system based on RBF neural network[J].Modular Machine Tool & Automatic Manufacturing Technique, 2016(3):75-77(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/zhjc201603021
    [13] 舒志兵, 周玮, 李运华.交流伺服运动控制系统[M].北京:清华大学出版社, 2006:66-82.

    SHU Z B, ZHOU W, LI Y H.AC servo motion control system[M].Beijing:Tsinghua University Press, 2006:66-82(in Chinese).
    [14] ABU-RUB H, IQBAL A, GUZINSKI J.High performance control of AC drives with MATLAB/Simulink models[M].New York:Wiley, 2012.
    [15] KUNG Y S, NGUYEN V Q, HUANG C C, et al.Simulink/ModelSim co-simulation of sensorless PMSM speed controller[C]//Industrial Electronics and Applications.Piscataway, NJ: IEEE Press, 2012: 1405-1410.
    [16] DARKEN C, MOODY J.Fast adaptive k-means clustering: Some empirical results[C]//IJCNN International Joint Conference on Neural Networks.Piscataway, NJ: IEEE Press, 1990: 233-238.
    [17] 李文鹏.基于UMAC的超精密机床数控系统设计及参数自整定研究[D].哈尔滨: 哈尔滨工业大学, 2016: 45-57.

    LI W P.Design of ultra-precision machine tool numerical control system and auto-tuning for parameter based on UMAC[D].Harbin: Harbin Institute of Technology, 2016: 45-57(in Chinese).
    [18] 吴晓明, 马立廷, 郑协, 等.改进的RBF神经网络PID算法在电液伺服系统中应用[J].机床与液压, 2015, 43(11):63-66. doi: 10.3969/j.issn.1001-3881.2015.11.018

    WU X M, MA L T, ZHENG X, et al.Improved RBF neural network PID control strategy used in electro-hydraulic servo system[J].Machine Tool & Hydraulics, 2015, 43(11):63-66(in Chinese). doi: 10.3969/j.issn.1001-3881.2015.11.018
  • 加载中
图(11)
计量
  • 文章访问数:  636
  • HTML全文浏览量:  152
  • PDF下载量:  450
  • 被引次数: 0
出版历程
  • 收稿日期:  2017-12-19
  • 录用日期:  2018-01-19
  • 网络出版日期:  2018-10-20

目录

    /

    返回文章
    返回
    常见问答