汽车投产排序时，希望同时实现零部件消耗均衡化、车型调整费用最小化、工位作业位置精准化三个目标，为此提出一种基于 Pareto 层级的混合多目标网格遗传算法(HmoGA)。先将个体排斥机制加入到 Pareto 层级构造中，使非支配解的分布更均匀，再融合 Pareto 层级划分、网格拥挤度评价与相邻个体几何距离计算，设计一种多目标自适应网格选择机制，用于从动态变化的父代种群中选择较优个体构成进化种群、获取交叉运算的父代基因、改善非支配解集的分布质量。混合双基因位的迁移算子对非支配解进行邻域搜索，适时扩大搜索空间，跳出局部最优。利用三组不同规模的测试问题集，从非支配率、非支配解数量和相邻个体距离偏差三个指标方面进行比较，实验证明 HmoGA 算法在收敛性、解的数量和分布性方面都比 NSGA-Ⅱ算法有显著优势。%Three objectives were expected to be achieved simultaneously when sequencing automo-biles in process,including equaling the spare parts consumption,minimizing the total adjustment cost resulting from exchanging automobile models,calibrating the work position for each automobile on any station.A new hybrid multi-objective grid genetic algorithm(HmoGA)was proposed based on Pa-reto stratum.In the algorithm,a new rejection mechanism was first considered in the sorting process of Pareto stratum,for the purpose of getting the even distribution of the non-dominated solutions. Then an adaptive grid selection scheme was designed by integrating Pareto stratum evaluation,crow-ding degree calculation and distance estimation among adjacent individuals.Thus,higher quality popu-lation can be generated,better parent chromosomes can be selected,and the distribution of the Pareto front can be improved constantly.Finally,the 2-opt shift operator was hybridized into the proposed ge-netic algorithm so as to broaden the search space and escape from local optimum.Three groups of ex-periments have done and three metrics including non-dominated ratio,the number of Pareto optimal solutions and the deviation of distances between neighbors were used as the performance measures. The results reveal that the proposed HmoGA dramatically outperforms NSGA-Ⅱ in terms of conver-gence and diversification.
展开▼
