Partner selection model and soft computing approach for dynamic alliance of enterprises

Partner selection is an active research topic in agile manufacturing and supply chain management. In this paper, the problem is described by a 0-1 integer programming with non-analytical objective function. Then, the solution space is reduced by defining the inefficient candidate. By using the fuzzy rule quantification method, a fuzzy logic based decision making approach for the project scheduling is proposed. We then develop a fuzzy decision embedded genetic algorithm. We compare the algorithm with tranditional methods. The results show that the suggested approach can quickly achieve optimal solution for large size problems with high probability. The approach was applied to the partner selection problem of a coal fire power station construction project. The satisfactory results have been achieved.

基于自适应遗传算法的网络化制造盟员选择研究

针对网络化制造中动态联盟盟员选择优化问题,分析了盟友的评价指标体系,建立了盟友选择的多目标优化模型,并在此基础上提出一种自适应遗传算法。该算法设计了自适应交叉和变异概率,使其在遗传过程中根据适应度自动选择,从而使群体中每个个体对环境的变化具有自适应调节能力。通过保持迭代过程的最优解,加快了搜索速度,并保证收敛于全局最优解。

基于交互正交遗传算法的动态联盟伙伴选择研究

针对动态联盟中的伙伴选择问题,提出一种有交互作用的正交试验方法和遗传算法相结合的方法,对多目标伙伴选择问题进行求解。着重考虑成本、质量、时间、风险及其它们之间存在的交互作用作为伙伴选择中的主要评价指标,给出了基于交互正交遗传算法模型求解方法,并应用实例验证了该模型和算法的有效性。