Adaptive double chain quantum genetic algorithm for constrained optimization problems  

作　　者：Kong Haipeng Li Ni Shen Yuzhong 

机构地区：[1]School of Automation Science and Electrical Engineering, Beihang University [2]Department of Modeling, Simulation and Visualization Engineering, Old Dominion University

出　　处：《Chinese Journal of Aeronautics》2015年第1期214-228,共15页中国航空学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61004089);supported by China Scholarship Council

摘　　要：Optimization problems are often highly constrained and evolutionary algorithms（EAs）are effective methods to tackle this kind of problems. To further improve search efficiency and convergence rate of EAs, this paper presents an adaptive double chain quantum genetic algorithm（ADCQGA） for solving constrained optimization problems. ADCQGA makes use of doubleindividuals to represent solutions that are classified as feasible and infeasible solutions. Fitness（or evaluation） functions are defined for both types of solutions. Based on the fitness function, three types of step evolution（SE） are defined and utilized for judging evolutionary individuals. An adaptive rotation is proposed and used to facilitate updating individuals in different solutions.To further improve the search capability and convergence rate, ADCQGA utilizes an adaptive evolution process（AEP）, adaptive mutation and replacement techniques. ADCQGA was first tested on a widely used benchmark function to illustrate the relationship between initial parameter values and the convergence rate/search capability. Then the proposed ADCQGA is successfully applied to solve other twelve benchmark functions and five well-known constrained engineering design problems. Multi-aircraft cooperative target allocation problem is a typical constrained optimization problem and requires efficient methods to tackle. Finally, ADCQGA is successfully applied to solving the target allocation problem.Optimization problems are often highly constrained and evolutionary algorithms（EAs）are effective methods to tackle this kind of problems. To further improve search efficiency and convergence rate of EAs, this paper presents an adaptive double chain quantum genetic algorithm（ADCQGA） for solving constrained optimization problems. ADCQGA makes use of doubleindividuals to represent solutions that are classified as feasible and infeasible solutions. Fitness（or evaluation） functions are defined for both types of solutions. Based on the fitness function, three types of step evolution（SE） are defined and utilized for judging evolutionary individuals. An adaptive rotation is proposed and used to facilitate updating individuals in different solutions.To further improve the search capability and convergence rate, ADCQGA utilizes an adaptive evolution process（AEP）, adaptive mutation and replacement techniques. ADCQGA was first tested on a widely used benchmark function to illustrate the relationship between initial parameter values and the convergence rate/search capability. Then the proposed ADCQGA is successfully applied to solve other twelve benchmark functions and five well-known constrained engineering design problems. Multi-aircraft cooperative target allocation problem is a typical constrained optimization problem and requires efficient methods to tackle. Finally, ADCQGA is successfully applied to solving the target allocation problem.

关 键 词：constrained rotation utilized benchmark constraints allocation fitness tackle illustrate facilitate 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] E91[自动化与计算机技术—控制科学与工程]