某随动平台模糊RBF神经网络终端滑模控制设计  

Design of Terminal Sliding Mode Control Based on Fuzzy RBF Neural Network for a Servo Platform

作　　者：黎青鑫 陈机林[1] 侯远龙[1] 陶征勇 LI Qingxin;CHEN Jilin;HOU Yuanlong;TAO Zhengyong(School of Mechanical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学机械工程学院,南京210094

出　　处：《电光与控制》2020年第12期90-94,104,共6页Electronics Optics & Control

摘　　要：为了提高某随动系统负载模拟器加载系统的力矩跟踪精度,提出一种模糊RBF神经网络终端滑模复合控制方法。首先通过对随动负载模拟器的系统组成和工作原理的分析,简化力矩电机模型,根据扭矩传感器和惯量盘的模型,建立随动负载模拟器的简化等效模型。随后设计了一种快速终端滑模控制器,为了提高滑模的动态品质,利用模糊神经网络方法动态调节滑模面参数。同时,为了提高模糊RBF神经网络的学习和训练速度,用最近邻层次聚类和共轭梯度算法调整网络各参数,并对算法进行局部优化以提高算法性能。最后进行仿真,证明该方法提高了系统控制精度且具有良好的动态特性。In order to improve the torque tracking accuracy of a load simulator for a servo systema method of composite terminal sliding mode control based on the fuzzy RBF neural network is proposed.Firstlyby analyzing the system's composition and working principle of the servo load simulatorthe torque motor model is simplified.According to the models of the torque sensor and the inertia diskthe simplified equivalent model of the servo load simulator is established.Thena fast terminal sliding mode controller is designed.In order to improve the dynamic quality of the sliding modethe parameters of the sliding mode surface are dynamically adjusted by using the method of the fuzzy neural network.At the same timein order to improve the learning and training speed of the fuzzy RBF neural networkthe nearest-neighbor hierarchical clustering and the conjugate gradient algorithm are used to adjust the parameters of the networkand local optimization is carried out to improve the performance of the algorithm.Finallysimulations are conductedand the results show that the method can improve the system's control accuracy and has good dynamic characteristics.

关 键 词：负载模拟器 模糊RBF神经网络 快速终端滑模 最近邻层次聚类 改进共轭梯度算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]