基于遗传-粒子群混合优化算法的拆卸序列规划方法研究  

Disassembly sequence planning method based on hybridgenetic particle swarm optimization algorithm

作　　者：王玉鑫[1] 任帅 WANG Yu-xin;REN Shuai(College of Aeronautical Engineering,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学航空工程学院,天津300300

出　　处：《机电工程》2021年第3期337-342,共6页Journal of Mechanical & Electrical Engineering

基　　金：国家工信部民用飞机科研专项资助项目(MJZ-2017-Y-81)。

摘　　要：为确保使产品具有良好的维修性,针对现有拆卸序列规划方法存在无法高效得到最优解,甚至得不到最优解的问题,对拆卸序列规划问题特征进行了研究。确定了适用于拆卸任务排序的编码规则,设计了一种分层次的拆卸优先图,用分层次约束矩阵保证了拆卸中的优先约束,建立了随机序列合规化处理方法;定义了适用于此问题的遗传算法交叉算子和变异算子,结合全局搜索能力较好的遗传算法与局部搜索能力较好的粒子群算法,提出了适用于拆卸序列规划的遗传-粒子群算法;最后,以液压泵为例,建立了其拆卸模型,在MATLAB软件上进行了算例验证,并与文献中不同算法对此问题的求解结果进行了对比和分析。研究结果表明:此算法最优解适应度、得到最优解的迭代次数及运行时间均低于以往算法,即可以更加高效得出适应度值更优的拆卸序列,显示其有效性及优越性。Aiming at the problem that the optimal solution can not be obtained efficiently or even can not be got through the existing disassembly sequence planning method,a kind of hierarchical disassembly priority diagram was designed,and hierarchical constraint matrix was used to ensure the priority constraints,then the method of random sequence compliance was established by studying the problem of disassembly sequence planning features and determining suitable encoding rules for disassembly sequence.The genetic algorithm crossover operator and mutation operator suitable for this problem were defined,and the genetic algorithm-particle swarm optimization which is suitable for disassembly sequence planning was proposed by combining the global search ability of genetic algorithm with the local search ability of particle swarm optimization.The results indicate that the optimal solution fitness,iteration times and running time of the algorithm are lower than those of previous algorithms,that is,the disassembly sequence with better fitness value can be obtained more efficiently,which shows its effectiveness and superiority.

关 键 词：混合优化算法 拆卸序列规划 全局搜索 约束优化问题 液压泵 

分 类 号：TH17[机械工程—机械制造及自动化] TP301.6[自动化与计算机技术—计算机系统结构]