基于PID神经网络的倒立摆控制系统

Inverted Pendulum Control System Based on PID Neural Network

倒立摆是一个典型的高阶次、自然不稳定、快速响应、非线性运动控制系统,是现代控制研究的对象。PID神经网络是一种内含比例神经元、积分神经元和微分神经元的神经网络。本文介绍了采用PID神经网络控制的倒立摆系统,包括倒立摆系统的基本构成、PID神经网络单变量控制系统的算法和结构、权重初值的选择。进行了实际系统试验,比较了传统PID控制和PID神经网络控制倒立摆的效果,证明了PID神经网络控制系统的优良性能。

The inverted pendulum is a high order, unstable and nonlinear system and is a typical research object for modem control field. The PID （proportional-integral-derivative） neural network is a spechial network in which the proportional neurons, the integral neurons and the derivative neurons are included. The inverted pendulum control system based on PID neural network was introduced, including the algorithm, the structure and the initial values of the weights of the PID neural networks. The PID neural network was compared with conventional PID controller in the experiments. It is proved that PID neural control system has better dynamic and static performance.