基于离散差分进化算法的齿轮优化设计  

Optimization Design of Gear based on Discrete Differential Evolution Algorithm

作　　者：何兵[1,2] 车林仙[1,2] 刘初升[1] 

机构地区：[1]中国矿业大学机电工程学院,江苏徐州221008 [2]泸州职业技术学院机电工程研究所,四川泸州646005

出　　处：《机械传动》2012年第10期39-42,共4页Journal of Mechanical Transmission

基　　金：四川省应用基础研究计划项目(2008JY0163);泸州市重点科技计划资助项目(2010-S-21)

摘　　要：根据机械设计中大多数优化变量属于混合变量的实际情况,提出采用基于离散变量方法解决机械优化设计问题。开发了一种不同变量自由设置间距的离散差分进化算法,连续变量采用合适的微小间距,离散变量采用工程规定间距。结合机械约束处理的自适应罚函数方法,以典型机械产品———齿轮和齿轮轴重量最轻优化实例为例,进行数值实验。结果表明该算法可以非常方便地处理约束优化问题,与粒子群算法实验对比,具有较高精度和可靠性。离散变量优化结果无需作圆整后处理,避免了圆整处理带来的系列问题。The discrete variable method to solve the optimization problem of mechanical optimization design is proposed,according to the actual situation that the mechanical design optimization most variables belonging to mixed variables.A spaced discrete differential evolution algorithm of different variable is free set,continuous variables using the appropriate small spacing,discrete variables using the project specified spacing is developed,combining mechanical constraint handling adaptive penalty function method and taking the typical mechanical product —gear and gear shaft of the lightest weight optimization as examples,the numerical experiment is carried out.The results show that,the algorithm can solve the constrained optimization problems conveniently,and compared with the particle swarm algorithm experiment,it has higher accuracy and reliability.And discrete variable optimization results dispense with rounding after treatment,a series of problems on the rounding processing is avoided.

关 键 词：机械设计 离散优化 差分进化算法 约束处理 

分 类 号：TH132.41[机械工程—机械制造及自动化]