摘要
电静液作动器(Electro-hydrostatic Actuator,EHA)作为一种高性能集成化的动力执行器,广泛应用于航天航空、工业生产和军事领域。在不同油液温度下,液压油的体积弹性模量、黏度等性质会发生变化,从而对EHA的控制精度产生影响。针对此问题,首先建立了EHA数学模型;其次,设计了反向传播(BP)神经网络对比例积分控制器(PI)控制参数进行在线调节,补偿温度变化对跟踪精度的影响;最后,通过实验验证了传统PI控制的EHA跟踪精度与温度变化有着密切关系,并将BPPI控制器与PI控制器进行实验对比。实验结果表明,所设计的BPPI控制器在不同油液温度下平均跟踪误差之间的差值较PI控制器降低80%以上;且在相同温度下,平均跟踪误差较PI控制器降低60%以上。
As a high-performance integrated power actuator,electro-hydrostatic actuator(EHA) is widely utilized in different applications.The control accuracy of EHA can be affected by variations in hydraulic oil properties such as bulk elastic modulus and viscosity,which are influenced by temperatures.To address this issue,a mathematical model for EHA was initially established.Subsequently,a back-propagation(BP) neural network was designed to dynamically adjust the proportional integral(PI) control parameters online,compensating for the adverse effects of temperature on tracking accuracy.Experimental investigations were conducted to verify the impact of temperature on the tracking accuracy of EHA controlled by PI controller.The results show that the average tracking error difference of BPPI under different oil temperatures is reduced by over 80% when compared to PI.And at the same temperature,the average tracking error of BPPI is reduced by more than 60% compared to PI.
作者
黄昊
刘家辉
朱威霖
高光发
姚建勇
HUANG Hao;LIU Jia-hui;ZHU Wei-lin;GAO Guang-fa;YAO Jian-yong(School of Sino-French Engineer,Nanjing University of Science Technology,Nanjing 210094,China;School of Mechanical Engineering,Nanjing University of Science Technology,Nanjing 210094,China)
出处
《液压气动与密封》
2024年第6期48-56,共9页
Hydraulics Pneumatics & Seals
关键词
电静液作动器
反向传播神经网络
温度补偿
比例积分控制
electro-hydrostatic actuator
back-propagation neural network
temperature compensation
proportional integral control
