基于遗传算法的PID神经网络解耦控制  

A PID Neural Network Decoupling Control Based on Genetic Algorithm

作　　者：王晓哲[1] 顾树生[1] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110005

出　　处：《控制与决策》1999年第A11期617-620,共4页Control and Decision

基　　金：辽宁省自然科学基金

摘　　要：提出一种基于遗传算法的ＰＩＤ神经网络解耦控制算法。该算法将遗传算法用于多层前向神经网络的连接权系数的学习，克服了ＢＰ算法易陷入局部极值的缺点，并具备ＰＩＤ 神经网络控制器结构简单规范、动态和静态性能良好等优点。A PID neural network decoupling method based on genetic algorithm is presented. Genetic algorithm is applied in training weighting factor of multilayered forward neural network, thus the disadvantage of BP algorithm that easily fall into partial extreme value can be overcome and at the same time, the advantage of PID neurocontroller that has simple structure and good dynamic and static performance is provided with. This method can be applied to the decoupling control of nonlinear multivariable system.

关 键 词：遗传算法 PID控制 解耦控制 神经网络 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置] TP13[自动化与计算机技术—控制科学与工程]