基于BP网络的一种非线性预测控制算法  

An Algorithm of Nonlinear Model Predictive Control Based on BP Network

作　　者：薛福珍[1] 汤瑜瑜[1] 柏洁[1] 

机构地区：[1]中国科学技术大学自动化系,安徽合肥230027

出　　处：《中国科学技术大学学报》2004年第5期593-598,共6页JUSTC

摘　　要：提出一种基于BP网络的非线性预测控制算法 .该算法根据被控对象自身的非线性特性 ,采用BP网络建立预测模型 ,并利用先验知识缩小网络的规模 ,提高网络的学习速度 ,然后利用遗传算法这一全局优化搜索方法对控制轨迹进行寻优 ,弥补神经网络容易陷入局部极小值的缺点 .非线性多变量系统友、码仿真 ,结果 。An algorithm of nonlinear predictive control method based on BP neural networks is proposed. According to the nonlinear characteristics of the controlled plant, the method builds its predictive model using BP networks. Furthermore, utilizing prior knowledge reduces the scale and raises the learning speed of the network. Then GA as a global optimization method is used to optimize the control trajectory, which makes up for the neural network’s disadvantage of easily getting trapped in local minimization. The results of mulitivariable nonlinear systems show that the method can accelerate convergence and is easy to implement.

关 键 词：非线性预测控制 神经网络 遗传算法 先验知识 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]