基于神经网络的机电作动器滑模输出反馈控制

doi:10.3901/JME.2023.10.357

机械工程学报 ›› 2023, Vol. 59 ›› Issue (10): 357-365.doi: 10.3901/JME.2023.10.357

扫码分享

基于神经网络的机电作动器滑模输出反馈控制

曹萌萌¹, 胡健^1,2, 周海波², 姚建勇¹, 赵杰彦¹, 王俊龙¹

1. 南京理工大学机械工程学院南京 210094;
2. 中南大学高性能复杂制造国家重点实验室长沙 410083

收稿日期:2022-05-26 修回日期:2022-10-25 出版日期:2023-05-20 发布日期:2023-07-19
通讯作者: 胡健(通信作者),女,1980年出生,博士,副教授,硕士研究生导师。主要研究方向为机电伺服非线性控制,AI与智能控制,嵌入式系统开发,包括基于AVR、ARM、DSP、CPLD的伺服系统软硬件设计与开发,以及相关的以太网,can总线通信等的研发。E-mail:hujiannjust@163.com E-mail:hujiannjust@163.com
作者简介:曹萌萌,女,1996年出生,博士研究生。主要研究方向为机电伺服控制,控制系统软件设计。E-mail:caomengm@foxmail.com
基金资助:
国家自然科学基金(51975294)、高性能复杂制造国家重点实验室开放课题基金(Kfkt2019–11)和中央高校基本科研业务费专项资金(30920010009)资助项目。

Sliding Mode Output Feedback Control of Electromechanical Actuator Based on Neural Network

CAO Mengmeng¹, HU Jian^1,2, ZHOU Haibo², YAO Jianyong¹, ZHAO Jieyan¹, WANG Junlong¹

1. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094;
2. State Key Laboratory of High Performance and Complex Manufacturing, Central South University, Changsha 410083

Received:2022-05-26 Revised:2022-10-25 Online:2023-05-20 Published:2023-07-19

摘要/Abstract

摘要： 机电作动系统广泛应用于工业生产和军事领域,但机电作动系统存在的模型不确定性会使得基于模型的非线性控制器精度下降,同时由于安装空间、成本的限制,系统往往无法安装速度传感器。针对上述问题,提出一种基于神经网络的滑模输出反馈控制策略。针对系统中存在的常值扰动以及参数不确定性,用扩张状态观测器(Extended state observer, ESO)加以估计;针对系统中存在的时变扰动,利用径向基函数神经网络的万能逼近特性进行估计,然后通过前馈补偿技术对前者进行补偿;同时利用ESO观测的系统速度值设计控制量,从而实现输出反馈控制。利用Lyapunov稳定性定理证明了所设计的控制器可以实现系统的有界稳定。大量的仿真和试验结果证明了所设计的控制器相对于传统的PID以及非线性控制器控制精度可以提高一个数量级。

关键词: 机电作动器, 输出反馈控制, 神经网络, 滑模控制, 模型不确定性

Abstract: Electromechanical actuators are widely used in industrial production and military fields. However, the model uncertainty of electromechanical actuators will reduce the accuracy of model-based nonlinear controllers. At the same time, due to the limitation of installation space and cost, it is often impossible to install speed sensors in system. To solve these problems, a sliding mode output feedback control strategy based on neural network is proposed. The constant disturbance and parameter uncertainty in the system are estimated by extended state observer(ESO). The universal approximation property of radical basis function neural network is used to estimate the time-varying disturbances in the system, and then the feedforward compensation technology is used to compensate the former. At the same time, the speed of the system observed by the ESO is used to design the control quantity, so as to realize the output feedback control. By using Lyapunov stability theorem, it is proved that the designed controller can achieve bounded stability of the system. A large number of simulation and experimental results prove that the controller designed can improve the control accuracy by an order of magnitude compared with the traditional PID and nonlinear controller.

Key words: electromechanical actuator, output feedback control, neural network, sliding mode control, model uncertaint

中图分类号:

TP273

曹萌萌, 胡健, 周海波, 姚建勇, 赵杰彦, 王俊龙. 基于神经网络的机电作动器滑模输出反馈控制[J]. 机械工程学报, 2023, 59(10): 357-365.

CAO Mengmeng, HU Jian, ZHOU Haibo, YAO Jianyong, ZHAO Jieyan, WANG Junlong. Sliding Mode Output Feedback Control of Electromechanical Actuator Based on Neural Network[J]. Journal of Mechanical Engineering, 2023, 59(10): 357-365.

参考文献

[1] 邓文翔,马吴宁,姚建勇. 机电伺服系统鲁棒自适应重复控制[J]. 上海交通大学学报,2016,50(9):1486-1492. DENG Wenxiang,MA Wuning,YAO Jianyong. Robust adaptive repetitive control for electromechanical servo systems[J]. Journal of Shanghai Jiao Tong University,2016,50(9):1486-1492.
[2] LU Hao,LI Yunhua,TIAN Shengli,et al. Improved hybrid robust control method for the electromechanical actuator in aircrafts[J]. Chinese Journal of Mechanical Engineering,2010,23(4):443-450.
[3] JI Xuewu,HE Xiangkun,LÜ Chen,et al. A vehicle stability control strategy with adaptive neural network sliding mode theory based on system uncertainty approximation[J]. Vehicle System Dynamics,2018,56(6):923-946.
[4] YANG Jun,SU Jinya,LI Shihua,et al. High-order mismatched disturbance compensation for motion control systems via a continuous dynamic sliding-mode approach[J]. IEEE Transactions on Industrial Informatics,2014,10(1):604-614.
[5] 岳欣,姚建勇. 基于积分鲁棒的电液负载模拟器渐近跟踪控制[J]. 航空学报,2017,38(2):294-303. YUE Xin,YAO Jianyong. Asymptotic tracking control of electro-hydraulic load simulator based on integral robust[J]. Acta Aeronautica et Astronautica Sinica,2017,38(2):294-303.
[6] 曹文祺,李少远. 具有可参数化不确定性系统的对偶自适应模型预测控制[J]. 控制理论与应用,2019,36(8):1197-1206. CAO Wenqi,LI Shaoyuan. Dual adaptive model predictive control for systems with parameterized uncertainty[J]. Control Theory and Applications,2019,36(8):1197-1206.
[7] 姜仁华,刘闯,宁银行. 雷达伺服系统的自适应摩擦力矩补偿控制策略[J]. 机械工程学报,2019,55(18):187-195. JIANG Renhua,LIU Chuang,NING Yinhang. Control strategy with adaptive friction torque compensation for radar servo system[J]. Journal of Mechanical Engineering,2019,55(18):187-195.
[8] SONG Mingchao,LIN Yan. Robust adaptive output- feedback dynamic surface control of a class of nonlinear systems with unmodeled dynamics[J]. Asian Journal of Control,2013,15(5):1337-1345.
[9] DENG Wenxiang,YAO Jianyong. Extended-state- observer based adaptive control of electro-hydraulic servomechanisms without velocity measurement[J]. IEEE/ASME Transactions on Mechatronics,2019,8(9):1-11.
[10] Yao Jianyong,Jiao Zongxia,Ma Dawei. Output feedback robust control of direct current motors with nonlinear friction compensation and disturbance rejection[J]. Journal of Dynamic Systems Measurement and Control-Transactions of the ASME,2015,134(4):041004.
[11] Yao Jianyong,Jiao Zongxia,Ma Dawei. Adaptive robust control of DC motors with extended state observer[J]. IEEE Transaction on Industrial Electronics,2014,61(7):3630-3637.
[12] 刘金琨. 滑模变结构控制MATLAB仿真[M]. 北京:清华大学出版社,2019. LIU Jinkun. MATLAB simulation of sliding mode variable structure control[M]. Beijing:Tsinghua University Press,2019.
[13] 付东学,赵希梅. 永磁直线同步电机自适应反推全局快速终端滑模控制[J]. 电工技术学报,2020,35(8):1634-1641. FU Dongxue,ZHAO Ximei. Global fast terminal sliding mode control for permanent magnet linear synchronous motor adaptive backpushing[J]. Transactions of China Electrotechnical Society,2020,35(8):1634-1641.
[14] 李伟,宁君,李悦琪. 基于自抗扰的反步非奇异终端滑模船舶航向控制器设计[J]. 船舶工程,2019,41(11):83-88. LI Wei,NING Jun,LI Yueqi. Design of backstepping nonsingular terminal sliding mode ship heading controller based on active disturbance rejection[J]. Marine Engineering,2019,41(11):83-88.
[15] WU Qing,SAIF M. Robust fault detection and diagnosis in a class of nonlinear systems using a neural sliding mode observer[J]. International Journal of Systems Science,2007,38(11):881-899.
[16] 赵健,邓志辉,朱冰,等. 基于RBF网络滑模的电动助力制动系统液压力控制[J]. 机械工程学报,2020,56(24):106-114. ZHAO Jian,DENG Zhihui,ZHU Bing,et al. Sliding mode control based on RBF network for hydraulic pressure in electric power-assisted brake system[J]. Journal of Mechanical Engineering,2020,56(24):106-114.
[17] 米君杰,姚建勇,邓文翔. 基于神经网络的缠绕过程张力积分鲁棒控制[J]. 机械工程学报,2021,57(24):74-82. MI Junjie,YAO Jianyong,DENG Wenxiang. Neural network based RISE control of winding tension[J],Journal of Mechanical Engineering,2021,57(24):74-82.
[18] 赵健,邓志辉,朱冰,等. 基于RBF网络滑模的电动助力制动系统液压力控制[J]. 机械工程学报,2020,56(24):106-114. ZHAO Jian,DENG Zhihui,ZHU Bing,et al. Sliding mode control based on RBF network for hydraulic pressure in electric power-assisted brake system[J]. Journal of Mechanical Engineering,2020,56(24):106-114.
[19] Chu Yundi,Fei Juntao. Adaptive global sliding mode control for MEMs gyroscope using RBF neural network[J]. Mathematical Problems in Engineering,2015,2015(PT.5):403180.
[20] 韩松杉,焦宗夏,汪成文,等. 基于神经网络的电液转台非线性积分滑模控制[J]. 北京航空航天大学学报,2014,40(3):321-326. HAN Songshan,JIAO Zongxia,WANG Chengwen,et al. Nonlinear integral sliding mode control of electro-hydraulic turntable based on neural network[J]. Journal of Beijing University of Aeronautics and Astronautics,2014,40(3):321-326.

基于神经网络的机电作动器滑模输出反馈控制

Sliding Mode Output Feedback Control of Electromechanical Actuator Based on Neural Network

PDF

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

[1]	林亮行, 马国政, 孙建芳, 韩翠红, 雍青松, 苏峰华, 王海斗. 基于VMD-EEMD-LSTM的涂层型关节轴承剩余使用寿命预测方法[J]. 机械工程学报, 2023, 59(9): 125-136.
[2]	陆向宁, 刘凡, 何贞志, 廖广兰, 史铁林. 稀疏重构SAM芯片焊点检测方法研究[J]. 机械工程学报, 2023, 59(6): 95-102.
[3]	常建涛, 乔子萱, 孔宪光, 杨胜康, 罗才文. 多维非线性特征重构与融合的复杂产品工期预测方法[J]. 机械工程学报, 2023, 59(6): 295-309.
[4]	张旭飞, 刘欣超, 马杰, 张锋阳, 权龙. 基于最近邻均匀设计神经网络逆模型的电磁标准振动台谐波控制方法研究[J]. 机械工程学报, 2023, 59(5): 180-191.
[5]	董海江, 郑婷婷, 于进涛, 付正家, 刘秀成, 邢智翔, 闫正祥, 何存富. 汽车B柱加强板软硬部过渡特性的磁巴克豪森噪声检测方法[J]. 机械工程学报, 2023, 59(4): 10-17.
[6]	刘志状, 吴昊. 一种基于参数影响的数据驱动下的疲劳寿命预测方法[J]. 机械工程学报, 2023, 59(4): 71-79.
[7]	熊瑞, 孙万洲, 杨瑞鑫, 孙逢春. 储能电池外部短路的损伤与失效边界及其预测[J]. 机械工程学报, 2023, 59(4): 113-124.
[8]	吴建洋, 王震坡, 张雷, 丁晓林. 四轮轮毂电机驱动电动汽车纵侧向稳定性协调控制策略研究[J]. 机械工程学报, 2023, 59(4): 163-172.
[9]	邓磊鑫, 谢清林, 陶功权, 温泽峰. 基于轴箱振动与动力学模型驱动的高速列车车轮失圆状态识别方法[J]. 机械工程学报, 2023, 59(3): 110-121.
[10]	罗仕鉴, 崔志彤, 帅俊成, 陈霆, 张德寅. 基于群智协同计算的高速列车概念生成设计研究[J]. 机械工程学报, 2023, 59(11): 65-73.
[11]	李冬武, 张洁, 汪俊亮, 徐楚桥. 细纱接头机器人神经网络自适应力跟踪导纳控制[J]. 机械工程学报, 2023, 59(11): 221-231.
[12]	刘永刚, 张静晨, 王鑫, 张学勇, 吕豪, 秦大同. 摩擦因数自适应的双离合器自动变速器起步智能控制[J]. 机械工程学报, 2023, 59(10): 197-209.
[13]	梁忠超, 黄茁, 胡兴, 陈杰. 基于YOLO网络的车辆四点标定测距研究[J]. 机械工程学报, 2023, 59(10): 226-235.
[14]	易聪, 杜建军, 尹际雄, 朱海斌, 邓炜坤, 白宝亮, 付从艺. 基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法[J]. 机械工程学报, 2023, 59(1): 131-140.
[15]	张明月, 王新宇. 基于残差观测器的智能电网虚假数据攻击检测研究^*[J]. 电气工程学报, 2023, 18(1): 111-117.