基于粒子群算法的自动配煤系统多目标优化  

Multi-target Optimization for Automatic Blending Coal System Based on PSO Algorithm

作　　者：彭娟[1] 程健 韩仿仿[1] 阙胜利[1] 宋万宝[1] 

机构地区：[1]中国矿业大学信电学院,江苏徐州221008

出　　处：《工矿自动化》2009年第10期25-28,共4页Journal Of Mine Automation

基　　金：江苏省高新技术重大项目(BG2007012)

摘　　要：粒子群优化(PSO)算法是一种有效的基于群体智能的全局优化方法,不能直接应用于多目标自动配煤系统的优化中。文章考虑实际灰分最大限度接近目标灰分、配煤时间最短、能耗最小经济效益最高这3个目标,建立了具有条件约束的多目标自动配煤系统模型;利用加权法将自动配煤系统的多目标优化问题转化为单目标优化问题,然后利用PSO算法对系统进行优化,求出最优解集。仿真结果表明,应用PSO算法优化多目标自动配煤系统的方法简单可行,效果较为理想,但也存在适应度函数和权值参数选取难的问题。The particle swarm optimization（PSO） algorithm is a powerful global optimization method based on swarm intelligence,but it cannot optimize automatic blending coal system with multi-target.Based on considering three targets that actual coal ash achieves object coal ash,time of coal blending is minimal,and energy is minimal and economic benefit is maximal,a model of automatic blending coal system with multi-target with condition restriction was constructed.It used weighting method to translate multi-target problem of automatic blending coal system into single target one, used PSO algorithm to optimize the system, so as to get the best solution set. The simulation result showed that the method that applying PSO algorithm to optimize automatic blending coal system with multi-target is simple and feasible, which has good effect. However, it is difficult to select fitness function and weighting parameters to the method.

关 键 词：自动配煤 多目标优化 粒子群优化算法 PSO算法 加权法 适应度函数 

分 类 号：TD921.6[矿业工程—选矿]