基于多目标遗传算法的复杂产品设计变更传播优化  

Optimization of design-change propagation of complex products based on the multi-objective genetic algorithm

作　　者：骆建芬 李孟泽 李婷 任海兵[3] LUO Jian-fen;LI Meng-ze;LI Ting;REN Hai-bing(Yuanpei College,Shaoxing University,Shaoxing 312000;School of Mechanical Engineering,Zhejiang University,Hangzhou 310027;Department of Industrial Engineering,School of Mines,China University of Mining and Technology,Xuzhou 221116)

机构地区：[1]绍兴文理学院元培学院,浙江绍兴312000 [2]浙江大学机械工程学院,浙江杭州310027 [3]中国矿业大学矿业工程学院,江苏徐州221116

出　　处：《机械设计》2020年第10期66-72,共7页Journal of Machine Design

摘　　要：针对复杂产品设计变更传播路径优化问题,将复杂网络理论应用于复杂产品结构建模中,以零部件为节点,零部件间的物理连接关系为边,定义变更传播影响为边的权重,建立了有向加权的复杂产品零部件网络模型。根据变更传播特点,构建了一种多目标优化模型,模型同时考虑了研制时间、研制成本及变更风险多个优化目标。采用非支配排序遗传算法(Non-dominated Sorting Genetic Algorithm-Ⅱ,NSGA-Ⅱ)实现模型求解,得到pareto最优解集,可为设计人员选择最优的设计变更方案提供重要依据。最后,以某型号吸尘器设计变更传播路径多目标优化为例验证了方法的可行性和有效性。For the path optimization of the design-change propagation in complex products,the theory of complex network is applied to represent the complex products.These parts are defined as the vertices,the physical connections among different parts serve as the edges,and the pre-defined change-propagation impact is set as the weights of the edges.Thus,the weighted-directed complex network model of complex product is worked out.According to the characteristics of change propagation,the multi-objective optimization model is set up.In this model,such factors as development cost,development time and change risk are taken as multiple objectives.This model is solved by the non-dominated sorting genetic algorithm-Ⅱ(NSGA-Ⅱ)to get the pareto frontier.It provides important basis for designers to choose the best scheme of design change.Finally,the multi-objective optimization is conducted on a vacuum cleaner’s design-change propagation,which verifies that the proposed method is the feasible and effective.

关 键 词：复杂产品 NSGA-Ⅱ 多目标优化 设计变更预测 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]