基于遗传算法的网络化制造单元选择问题研究

Research on networked manufacturing unit selection based on genetic algorithm

为解决网络化协同制造过程中物理制造单元选择问题,提出一种改进的基于遗传算法的物理制造单元优化选择算法。算法采用整数编码,每个染色体代表一条可执行加工路线;为获取最优的可执行加工路线,以总的运行成本、运行时间和加工质量为优化目标构造目标函数;求解过程中,在每一代种群中计算出与每个染色体相对应的成本、时间、质量指标及目标非标准化对决策的影响度,进而利用影响度因子确定群体中每个染色体对最小运行成本、最小运行时间及最优加工质量的相对优属度,再利用相对优属度构造相对适应度函数,并求取相应的适应度函数值,减小了目标非标准化对优化结果的影响。最后给出了应用该算法处理复杂零件协同制造中制造单元选择的一个实例,以证明算法的可行性与有效性。

To solve physical manufacturing unit (PMU) selection question in the networked cooperative manufacturing process, an improved algorithm based on GA was proposed. Integer coding method was adopted in the algorithm, and a chromosome represented an executive manufacturing process (EMP). In order to obtain the optimized EMP, the objective function was constructed according to the optimizing objective, namely the total running costs, time and machining quality (CTQ). During seeking the answer to this question, the CTQ's value of each chromosome and the influence degree to decision making due to the CTQ's non-standardization were calculated in every generation. Through making using of the influence degree coefficient, the relative membership degree of each chromosome to the least total running cost, time and the best machining quality was calculated. Then, the relative fitness function was set up and its value was computed by using the relative membership degree to reduce the influence degree of CTQ's non-standardization to decision-making. At last, an example was given to prove the algorithm's feasibility and validity.