摘要
模块化设计能有效满足大批量定制生产的需要,模块划分是模块化设计的关键技术之一。在模块划分过程中使用智能优化算法,易于计算机编程实现且划分效率较高。首先在粒子群优化(Particle Swarm Optimization,PSO)算法中引入遗传算法(Genetic Algorithm,GA)的变异思想,通过C++语言将变异粒子群优化算法进行编程实现,并对粒子类编码、设计结构矩阵生成、适应度函数计算和变异策略技术进行了深入分析研究;然后在减速器的模块划分实例中进行了多次验证,并着重比较了2种变异PSO算法和标准PSO算法的划分效率,结果表明了变异粒子群算法的划分高效性;最后在模块划分过程中详细分析研究了种群规模和变异概率2个参数对模块划分效率的影响,找到了实现最优划分效率的参数组合范围,为产品模块数值划分方法以及关键参数的选取提供了一定的参考价值。
Product modularity can effectively meet the needs of mass customized production,and module division is one of the key technologies of modular design.Using the intelligent optimization algorithm for module division is easier to implement and has high efficiency in the computer.The mutation idea of Genetic Algorithm(GA)is introduced into Particle Swarm Optimization(PSO)algorithm,and mutation strategies are designed in the improved algorithm.It is implemented by C++language programming and verified in the module division example of reducer product,fitness function calculation and the division effects of two mutation PSO algorithms and classical PSO algorithm are compared.In the example of module division,the influence of population size and mutation probability on the effect of module division is analyzed and studied in detail,and the parameter combination and parameter variation range to achieve the optimal division effect are found,which provides a certain reference value for the numerical division method of product module and the selection of key parameters.
作者
陈砚
单泉
周云光
CHEN Yan;SHAN Quan;ZHOU Yunguang(School of Control Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China)
出处
《现代制造工程》
CSCD
北大核心
2023年第2期10-17,83,共9页
Modern Manufacturing Engineering
基金
国家自然科学基金项目(51905083)。
