基于流量脉动补偿的电静液作动器神经网络控制

doi:10.3901/JME.2025.04.355

机械工程学报 ›› 2025, Vol. 61 ›› Issue (4): 355-364.doi: 10.3901/JME.2025.04.355

扫码分享

基于流量脉动补偿的电静液作动器神经网络控制

葛曜文^1,2, 杨晓伟¹, 邓文翔¹, 姚建勇¹

1. 南京理工大学机械工程学院南京 210094;
2. 浙江大学流体动力基础件与机电系统全国重点实验室杭州 310027

收稿日期:2024-04-07 修回日期:2024-09-17 出版日期:2025-02-20 发布日期:2025-04-14
作者简介:葛曜文，男，1992年出生，博士。主要研究方向为电静液作动器系统建模、分析与控制。E-mail：geyaowen2020@163.com
姚建勇(通信作者)，男，1984年出生，博士，教授，博士研究生导师。主要研究方向为机电系统伺服控制、动态系统故障检测与容错、武器系统半实物仿真技术、火箭导弹发射技术。E-mail：jerryyao.buaa@gmail.com
基金资助:
国家重点研发计划(2021YFB2011300)、国家自然科学基金(52305063)、国家资助博士后研究人员计划(GZC20233497)、江苏省卓越博士后计划(2023ZB761)和浙江大学流体动力基础件与机电系统全国重点实验室开放基金(GZKF-202319)资助项目。

Neural Network Control of Electrohydrostatic Actuator Based on Flow Pulsation Compensation

GE Yaowen^1,2, YANG Xiaowei¹, Deng Wenxiang¹, YAO Jianyong¹

1. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094;
2. State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027

Received:2024-04-07 Revised:2024-09-17 Online:2025-02-20 Published:2025-04-14

摘要/Abstract

摘要： 流量脉动是柱塞泵的固有属性，理论而言其是由多个柱塞往复运动所产生，但在实际运行中柱塞在缸孔密封容腔内的一次次挤压和排放油液会积存残余压力，并伴随着泄漏等非线性不确定性，致使实际流量脉动与理论流量脉动之间存在偏差。现有电静液作动器(Electro-hydrostatic actuation，EHA)非线性控制方法研究中，通常对流量脉动进行线性处理并前馈补偿，忽视了泵流量脉动的非线性特征以及偏差效应，进而扩大了匹配不确定性的上界，致使控制器增益系数增大引起噪声放大，限制了电静液作动器系统控制精度的提升。为追求更高的控制精度，提出一种基于流量脉动补偿的电静液作动器神经网络控制方法。首先建立理论流量脉动的非线性范式模型用于前馈补偿，随后通过双通道神经网络实时逼近执行器的摩擦及第二通道干扰、理论与实际流量脉动的残差及第三通道干扰。试验结果表明，所提出的基于流量脉动补偿的电静液作动器神经网络控制和另外两种控制方法相比，跟踪精度提升了65%以上，在降低控制器增益和调参难度的同时，获得了更加优异的控制性能。

关键词: 电静液作动器, 神经网络控制, 流量脉动, 前馈补偿

Abstract: Flow pulsation is an inherent attribute of the plunger pump. Theoretically, it is generated by the reciprocating movement of multiple plungers. However, in actual operation, residual pressure will be accumulated by the extrusion and discharge of oil in the cylinder hole sealing cavity of the plunger, which is accompanied by nonlinear uncertainties such as leakage, resulting in deviation between the actual flow pulsation and the theoretical flow pulsation. In the current study of nonlinear control methods for electrohydrostatic actuators(EHA), the flow pulsation is usually treated linearly and compensated feedforward. The above processing method ignores the nonlinear characteristics and deviation effect of pump flow pulsation, thus enlarges the upper bound of the matching uncertainty, resulting in the increase of the controller gain coefficient and the amplification of noise, which limits the improvement of the control accuracy of the EHA. In order to achieve higher control accuracy, a neural network control method of the EHA based on flow pulsation compensation is proposed. Firstly, a nonlinear normal model of theoretical flow pulsation is established for feedforward compensation. Then the friction of the actuator, the interference of the second channel, the residual of the theoretical and actual flow pulsation and the interference of the third channel are approximated in real time by the two-channel neural network. The experimental results show that compared with two other control methods, the tracking accuracy of the proposed method is improved by more than 65%, and the control performance is better while reducing controller gain and tuning difficulty.

Key words: electro-hydrostatic actuator, neural network control, flow pulsation, feedforward compensation

中图分类号:

TG156

葛曜文, 杨晓伟, 邓文翔, 姚建勇. 基于流量脉动补偿的电静液作动器神经网络控制[J]. 机械工程学报, 2025, 61(4): 355-364.

GE Yaowen, YANG Xiaowei, Deng Wenxiang, YAO Jianyong. Neural Network Control of Electrohydrostatic Actuator Based on Flow Pulsation Compensation[J]. Journal of Mechanical Engineering, 2025, 61(4): 355-364.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.2025.04.355

http://www.cjmenet.com.cn/CN/Y2025/V61/I4/355

参考文献

[1] 陈斌，王占林，裘丽华. 机载液压系统的主要发展趋势[J]. 航空学报，1998，19(增刊1):2-7. CHEN Bin，WANG Zhanlin，QIU Lihua. Main developmental trend of aircraft hydraulic systems[J]. Acta Aeronautica et Astronautica Sinica，1998，19(Suppl.1):2-7.
[2] ALI S A，CHRISTEN A，BEGG S，et al. Continuous-discrete time-observer design for state and disturbance estimation of electro-hydraulic actuator systems[J]. IEEE Transactions on Industrial Electronics，2016，63(7):4314-4324.
[3] GUO Q，YIN J，TIAN Y，et al. Saturated adaptive control of electrohydraulic actuator with parametric uncertainty and load disturbance[J]. IEEE Transactions on Industrial Electronics，2017，64(10):7930-7941.
[4] LYU L，CHEN Z，YAO B. Development of pump and valves combined hydraulic system for both high tracking precision and high energy efficiency[J]. IEEE Transactions on Industrial Electronics，2018，66(9):7189-7198.
[5] CHEN Z，HELIAN B，ZHOU Y，et al. An integrated trajectory planning and motion control strategy of a variable rotational speed pump-controlled electro-hydraulic actuator[J]. IEEE/ASME Transactions on Mechatronics，2022，28(1):588-597.
[6] HELIAN B，CHEN Z，YAO B. Energy-saving and accurate motion control of a hydraulic actuator with uncertain negative loads[J]. Chinese Journal of Aeronautics，2021，34(5):253-264.
[7] LIN Y，SHI Y，BURTON R. Modeling and robust discrete-time sliding-mode control design for a fluid power electrohydraulic actuator (EHA) system[J]. IEEE/ASME Transactions on Mechatronics，2013，18(1):1-10.
[8] Ahn K K，Nam D N C，Jin M. Adaptive backstepping control of an electrohydraulic actuator[J]. IEEE/ASME Transactions on Mechatronics，2014，19(3):987-995.
[9] ZHENG J，ZHAO S，WEI S. Application of self-tuning fuzzy PID controller for a SRM direct drive volume control hydraulic press[J]. Control Engineering Practice，2009，17(12):1398-1404.
[10] DING R，ZHANG J，XU B，et al. Energy efficiency improvement of heavy-load mobile hydraulic manipulator with electronically tunable operating modes[J]. Energy Conversion & Management，2019，188:447-461.
[11] HELIAN B，CHEN Z，YAO B. Precision motion control of a servomotor-pump direct-drive electrohydraulic system with a nonlinear pump flow mapping[J]. IEEE Transactions on Industrial Electronics，2019，67(10):8638-8648.
[12] GE Y，YANG X，DENG W，et al. Rise-based composite adaptive control of electro-hydrostatic actuator with asymptotic stability[J]. Machines，2021，9(9):181.
[13] REN H，JIAO S，WANG X，et al. Fractional order integral sliding mode controller based on neural network:Theory and electro-hydraulic benchmark test[J]. IEEE/ASME Transactions on Mechatronics，2021，27(3):1457-1466.
[14] MERRITT H E. Hydraulic control systems[M]. New York:Wiley，1900.
[15] YAO J，DENG W，SUN W. Precision motion control for electro-hydraulic servo systems with noise alleviation:A desired compensation adaptive approach[J]. IEEE/ASME Transactions on Mechatronics，2017，22(4):1859-1868.
[16] 邓文翔. 兼顾各类不确定性的液压发射装置非线性控制研究[D]. 南京:南京理工大学，2018. DENG Wenxiang. Research on nonlinear control of hydraulic launcher with consideration of various uncertainties[D]. Nanjing:Nanjing University of Science and Technology，2018.
[17] GUSUSTAVO C， NARIMAN S. Hydrostatic transmissions and actuators[M]. New York:Wiley，2015.
[18] 葛曜文，朱威霖，刘家辉，等. 电静液作动器精细化建模和特性分析[J]. 机械工程学报，2021，57(24):66-73. GE Yaowen，ZHU Weilin，LIU Jiahui，et al. Refined modeling and characteristic analysis of electro-hydrostatic actuator[J]. Journal of Mechanical Engineering，2021，57(24):66-73.
[19] HYON S H，TANIAI Y，HIRANUMA K，et al. Overpressure compensation for hydraulic hybrid servo booster applied to hydraulic manipulator[J]. IEEE Robotics and Automation Letters，2019，4(2):942-949.
[20] HIPPALGAONKAR R，IVANTYSYNOVA M. Optimal power management of hydraulic hybrid mobile machines – Part I:Theoretical studies，modeling and simulation[J]. Journal of Dynamic Systems Measurement and Control，2016，138(5):051002.
[21] 杨国来，田丽红，张友亮，等. 大排量径向柱塞泵主要结构参数及流量脉动研究[J]. 液压气动与密封，2015，35(2):13-15. YANG Guolai，TIAN Lihong，ZHANG Youliang，et al. Study on main structural parameters and flow pulsation of large displacement radial piston pump[J]. Hydraulics Pneumatics & Seals，2015，35(2):13-15.
[22] 曹萌萌，胡健，周海波，等. 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，et al. Sliding mode output feedback control of electromechanical actuator based on neural network[J]. Journal of Mechanical Engineering，2023，59(10):357-365.

基于流量脉动补偿的电静液作动器神经网络控制

Neural Network Control of Electrohydrostatic Actuator Based on Flow Pulsation Compensation

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]	赵孝礼, 胡渊豪, 孙辉, 邓文翔, 胡健, 姚建勇, 李杨, 邵海东. 最大化聚合注意力卷积胶囊网络：一种电静液作动器复合故障智能解耦诊断方法[J]. 机械工程学报, 2026, 62(4): 355-365.
[2]	刘富文, 李清野, 宗超勇, 张彦峰, 宋学官. 基于流-固耦合的蠕动泵流量特性研究[J]. 机械工程学报, 2025, 61(8): 331-343.
[3]	张军辉, 倪小昊, 纵怀志, 郭怡涛, 杨梅生, 朱琦歆, 徐兵. 机器人用电静液作动器研究现状与发展趋势[J]. 机械工程学报, 2025, 61(4): 273-289.
[4]	尹方龙, 罗浩, 聂松林, 杨友胜, 纪辉, 马仲海. 海水淡化能量回收-增压一体式装置压力/流量脉动特性与试验[J]. 机械工程学报, 2025, 61(22): 329-341.
[5]	黄伟迪, 郭怡涛, 王峰, 纵怀志, 张军辉, 倪小昊, 徐兵. 挖掘机动臂集成一体式电静液作动器的设计与能量效率研究[J]. 机械工程学报, 2025, 61(18): 396-405.
[6]	杨为, 唐小林, 姜孔明, 付洋, 韩磊. 电动制动助力系统摩擦补偿模型及其控制方法研究[J]. 机械工程学报, 2024, 60(2): 252-261.
[7]	葛曜文, 朱威霖, 刘家辉, 邓文翔, 姚建勇. 电静液作动器精细化建模和特性分析[J]. 机械工程学报, 2021, 57(24): 66-73.
[8]	李波, 朱彦超, 舒亮, 杨家斌, 陈定方. 考虑流体体积模量变化的M-EHA非线性动力学模型[J]. 机械工程学报, 2020, 56(10): 225-234.
[9]	赵斌, 何焱泳, 郭伟伟, 郝云晓, 权龙. 新型变排量外啮合齿轮泵流量特性研究[J]. 机械工程学报, 2019, 55(24): 227-235,252.
[10]	朱碧海, 钱鹏程, 姬增起. 双斜盘阀配流轴向柱塞式液压电机泵配流特性和变量原理的研究[J]. 机械工程学报, 2018, 54(20): 220-234.
[11]	俞滨, 巴凯先, 王东坤, 刘雅梁, 李文锋, 孔祥东. 液压驱动单元位置控制系统前馈补偿控制研究[J]. 机械工程学报, 2018, 54(20): 159-169.
[12]	高有山, 成杰, 黄家海, 权龙. 变排量非对称轴向柱塞泵特性仿真分析及试验[J]. 机械工程学报, 2018, 54(14): 215-224.
[13]	权凌霄, 孔祥东, 俞滨, 白欢欢. 液压管路流固耦合振动机理及控制研究现状与发展[J]. 机械工程学报, 2015, 51(18): 175-183.
[14]	张铭钧;褚振忠. 自主式水下机器人自适应区域跟踪控制[J]. , 2014, 50(19): 50-57.
[15]	徐兵;宋月超;杨华勇. 复杂出口管道柱塞泵流量脉动测试原理[J]. , 2012, 48(22): 162-167.