基于RBF神经网络和重复控制PID的电动负载模拟器复合控制  

Composite control of electric load simulator based on RBF neural network and repetitive control PID

作　　者：王修岩[1] 刘艳敏[1] 李宗帅[1] WANG Xiu-yan;LIU Yan-min;LI Zong-shuai(College of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, China)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300

出　　处：《电力科学与技术学报》2017年第1期84-89,共6页Journal of Electric Power Science And Technology

基　　金：中央高校基本科研业务费项目(3122017009)

摘　　要：针对电动负载模拟器运行过程中存在的多余力矩问题,提出RBF神经网络和重复控制PID与前馈补偿控制器相结合的电动负载模拟器复合控制方法。该方法充分利用重复控制PID的优点,加入RBF神经网络控制,形成一种具有较强的抗干扰能力、较好的跟踪性能和自适应能力的控制算法;结合舵机速度的前馈补偿,实现多余力矩的抑制;引入弹簧杆,降低系统有害力矩,提高系统稳定性。仿真分析验证了所提复合控制方法的有效性和可行性。For the problem of surplus torque in the operation of electric load simulator,a composite control method of electric load simulator based on RBF neural network,repetitive PID controller and feed-forward control was proposed in this paper.The control method took full advantages of repetitive control PID and RBF neural network,a novel control algorithm was formed which has strong anti-interference ability,good tracking performance and adaptive capability.Rudder speeds were used as feed-forward to decrease surplus torque.At the same time,the elastic rod was used to reduce the harmful torque and improve the stability of the system.Simulation results verify the validity and feasibility of the proposed composite control method.

关 键 词：电动负载模拟器 复合控制 RBF神经网络 重复控制PID 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TM301.2[自动化与计算机技术—控制科学与工程]