粒子群算法的改进及其在求解约束优化问题中的应用

A Modified Particle Swarm Optimization for Solving Constrained Optimization Problems

在用粒子群算法求解约束优化问题时,处理好约束条件是取得好的优化效果的关键.通过对约束问题特征和粒子群算法结构的研究,提出求解约束优化问题一种改进的粒子群算法,该算法让每个粒子都具有双适应值,通过双适应值决定粒子优劣,并提出了自适应保留不可行粒子的策略.实验证明,改进的算法是可行的,且在精度与稳定性上明显优于采用罚函数的粒子群算法和遗传算法等算法.

In trying to solve constrained optimization problems by particle swarm optimization, the way to handle the constrained conditions is the key factor for success. Some features of particle swarm optimization and a large number of constrained optimization problems are taken into account and then a new method is proposed, which means to separate the objective functions from its constrained functions. Therefore, every particle of (particle) swarm optimization has double fitness values whether the particle is better or not will be decided by its two fitness values. The strategy to keep a fixed proportion of infeasible individuals is used in this new method. (Numerical) results show that the improved PSO is feasible and can get more precise results than particle swarm optimization by using penalty functions and genetic algorithm and other optimization algorithms.