论文部分内容阅读
提出一种自适应进化粒子群优化算法以求解多目标优化问题.采用非支配排序策略和动态加权法选择最优粒子,引导种群飞行,提高Pareto解的多样性.采用动态惯性权重,提高其全局寻优能力.当种群的寻优能力减弱时,采用变异操作以引导粒子群跳出局部最优.通过ZDT1～ZDT4基准函数验证,该算法能够在保持优化解多样性的同时实现较好的收敛性.与其他多目标进化算法和多目标粒子群优化算法相比,该算法具有较好的性能.
This paper proposes an adaptive evolutionary particle swarm optimization algorithm to solve the multi-objective optimization problem.Using the non-dominated sorting strategy and the dynamic weighting method to select the optimal particle to guide the flight of the population and improve the diversity of Pareto solutions.Using dynamic inertia weight, Optimization ability.When the optimization ability of the population weakens, the mutation operation is used to guide the particle swarm to jump out of the local optimum.According to the ZDT1 ~ ZDT4 benchmark functions, this algorithm can achieve good convergence while maintaining the optimal solution diversity Compared with other multi-objective evolutionary algorithms and multi-objective particle swarm optimization algorithms, this algorithm has better performance.