基于改进粒子群算法的加工方案多目标优化  

Multi-object optimization of machining scheme based on improved particle swarm optimization algorithm

作　　者：胡艳娟[1,2] 王义强[3] 王尧[1,2] 袁修华[1] 

机构地区：[1]吉林大学机械科学与工程学院,长春130025 [2]北华大学机械工程学院,吉林吉林132021 [3]浙江大学宁波理工学院,浙江宁波315100

出　　处：《沈阳工业大学学报》2011年第4期394-399,共6页Journal of Shenyang University of Technology

基　　金：国家"高档数控机床与基础制造装备"科技重大专项基金资助项目(2009ZX04014-013-01)

摘　　要：针对多个加工方案的选择和优化问题,建立了基于粒子群算法的多目标优化数学模型.以生产成本、生产时间、加工质量和生产利润为主要评价指标,利用层次分析法建立阶梯层次模型,根据决策者对各评价指标的不同要求确定了权重.将该方法应用于某汽车变速器四档中间轴齿轮的加工过程中,采用粒子位置取整操作的编码方式,用改进粒子群算法和层次分析法的混合算法进行求解.实例结果分析表明,多目标优化模型能够简单、有效、客观地根据对评价指标的不同要求选择出最优的加工方案.Aiming at the selection and optimization of several machining schemes, a mathematical model for multi-object optimization based on particle swarm optimization （PSO） algorithm was established. The production cost, production time, machining quality and production profit were chosen as the main evaluation indexes, and a step heirachy model was established with the analytic hierarchy process （AHP）. The weight was determined according to the different demands of decision maker on each evaluation index. The proposed algorithm was applied to the machining process of the four-grade intermediate shaft gear of an automobile transmission. The round-off operation of particle position was used as the coding mode, and the solution was carded out with the hybrid algorithm concerning both improved PSO and AHP. The analysis results of examples show that the multi-object optimization model can select the optimal machining scheme based on the different demands on evaluation indexes simply, effectively and objectively.

关 键 词：加工方案 汽车齿轮 粒子群 层次分析法 多目标 优化 建模 编码 

分 类 号：TH162[机械工程—机械制造及自动化]