基于混合粒子群算法的烧结配料优化

Sintering Blending Optimization Based on Hybrid Particle Swarm Algorithm

在引入惩罚函数和对目标函数进行适当修改的前提下,充分利用粒子群优化算法的全局搜索能力和约束条件下共轭梯度法的局部搜索能力,设计了烧结配料优化算法.利用惩罚函数方法将约束条件优化问题转化为无约束条件优化问题,然后利用粒子群优化算法进行寻优.当群体最优信息陷入停滞时将目标函数进行适当变化,继续利用共轭梯度法进行寻优.计算结果表明,采用该方法能够在提高混合料中的有用成分、降低有害成分的前提下,更多地降低生产成本.

With the introduction of punishment function and the appropriate modification of objective function,a sintering blending optimization algorithm is proposed,which takes full advantage of the global search ability of particle swarm optimization（PSO） algorithm and the local search ability of conjugate gradient algorithm with constraints.Punishment function is used to transform the optimization problem with constraints into an unconstrained optimization problem,and then PSO is applied to search the optimum.When the optimization information of swarm becomes stagnant,the objective function is modified appropriately and the conjugate gradient algorithm is employed to continue searching the optimum.The calculation result shows that the presented method can reduce production cost by increasing the useful ingredient and reducing the harmful ingredient of the mixed material.