一种综合改进型遗传算法及其在多变量解耦中的应用  

Research on Improved Genetic Algorithm and Its Applications in Multivariable Decoupling Control

作　　者：尹君[1] 薛福珍[1] 

机构地区：[1]中国科学技术大学自动化系,合肥230027

出　　处：《化工自动化及仪表》2008年第2期16-20,共5页Control and Instruments in Chemical Industry

基　　金：安徽省发改高技项目(2005661)

摘　　要：针对传统的遗传算法存在的未成熟收敛问题,提出一种综合改进型遗传算法,通过对选择算子、交叉算子、变异算子等方面进行综合设计,能有效改善遗传算法的全局搜索性能。基于该算法提出了一种复杂工业对象多变量系统解耦控制器的设计方法,对实际工业对象的解耦控制器设计结果表明该算法是一种通用高效率的最优化搜索方法。Taking into account immature convergence problem of the standard genetic algorithm, an integral genetic algorithm was presented. By integrated design on selection-operator, cross-operator and mutation-operator, the new algo- rithm has a good ability of the global search. Based on this algorithm, a disign method of decoupling controller for multivariable systems was given out. The proposed method was successfully applied to design a decoupling controller for a practical industrial plant. The results show that the improved algorithm is an efficient method of globe optimum.

关 键 词：遗传算法 未成熟收敛 多变量解耦 对角优势 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]