改进的RBF神经网络在机械臂控制中的应用研究

Research on the Application of Improved RBF Neural Network in Manipulator Control

机械臂系统是多输入、多输出的非线性系统,其位姿输出精度不稳定,与给定信号存在一定的跟踪误差。为提高机械臂系统跟踪精度以及抗干扰性能,通过对比分析常用的RBF神经网络学习方法,结合机械臂系统的非线性因素及其控制的实时性要求,提出改进RAN学习方法;并根据RAN学习方法构建RBF神经网络,将其应用于机械臂系统的逆控制器设计中。仿真实验表明,改进后的RBF神经网络逆控制器具有良好的对给定信号的跟踪精度和抗干扰能力,适用于机械臂系统的实时控制。

The manipulator system is a multi input and multi output nonlinear system.Its position and attitude output accuracy is not stable,and there is a certain tracking error with the given signal.In order to improve the tracking accuracy and anti-interference performance of the manipulator system,by comparing and analyzing the common RBF neural network learning methods,combined with the nonlinear factors of the manipulator system and the real-time requirements of the control,an improved ran learning method was proposed.According to the ran learning method,RBF neural network was constructed and applied to the inverse controller design of the manipulator system.The simulation results show that the improved RBF neural network inverse controller has good tracking accuracy and anti-interference ability to the given signal,and is suitable for the real-time control of the manipulator system.