预测控制算法及其在倒立摆中的应用  

A Predictive Control Algorithm Based on Neural Networks Model and Its Application to Inverted Pendulum

作　　者：单波[1] 徐燕[1] 赵建涛[1] 

机构地区：[1]华北电力大学信息工程系,北京102206

出　　处：《华北电力大学学报（自然科学版）》2001年第2期46-51,共6页Journal of North China Electric Power University：Natural Science Edition

摘　　要：基于神经网络模型的预测控制算法，是利用前向神经网络建立非线性被控对象的模型，以滚动优化、反馈校正实现对系统的控制。将其应用于倒立摆系统中，实现了对摆角和位移的同时控制。理论分析与仿真结果表明，该算法可避免对受控对象做复杂的数学分析。具有收敛速度快，鲁棒性较强的特点。A predictive control algorithm based on neural networks model is introduced. The object model is built using a feedforward neural network while the control is realized through rolling optimization and feedback adjustment. The pendulum angle and displacement can be controlled simultaneously by the algorithm when it is applied to an inverted pendulum system. It is proved by the theoretical analysis and simulation result that the method can avoid the complicated mathematical analysis of the object and has the features such as fast convergence and strong robustness.

关 键 词：神经网络 预测控制 倒立摆 数学分析 数学模型 算法 自动控制 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]