论文部分内容阅读
针对工程优化设计问题,提出了基于混沌粒子群算法的工程约束优化问题求解方法。CPSO算法利用混沌搜索的全局遍历性、随机性和规律性等特点,引导粒子在全局范围内搜索,从而克服了传统粒子群算法早熟收敛的缺点。该算法以种群适应度方差作为粒子群优化算法早熟收敛的判据,并用惩罚函数法处理违法约束的粒子,当基本粒子群算法陷入早熟时,随机选择粒子群中的部分粒子实施混沌搜索,直至满足迭代收敛条件为止。CPSO算法能提高种群的多样性和粒子搜索的遍历性,从而有效提高了PSO算法的收敛速度和精度。两个工程约束优化实例的求解结果表明,该算法的优化结果最好,收敛速度也比较快。
In order to solve the problem of engineering optimization design, a solution method of engineering constrained optimization problem based on chaos particle swarm optimization is proposed. The CPSO algorithm uses global traversal, randomness and regularity of chaotic search to guide the particle search in the global scope, thus overcoming the shortcomings of traditional PSO premature convergence. The algorithm uses the variance of population fitness as the criterion of premature convergence in PSO, and uses penalty function method to deal with illegally constrained particles. When the PSO gets into premature, some of the particles in the particle swarm are randomly selected and chaotic search is performed until Satisfy the condition of iterative convergence. CPSO algorithm can improve the diversity of population and the ergodicity of particle search, so as to effectively improve the convergence speed and accuracy of PSO algorithm. The results of two engineering constrained optimization examples show that the algorithm has the best optimization result and faster convergence rate.