基于神经网络和遗传算法的FMS能力规划问题

An Effective Method Using Neural Networks and Genetic Algorithms for FMS Capacity Planning Problems

针对柔性制造系统的制造过程,建立了一个基于多种需求状态的多计划期多种产品类的能力规划模型。该模型考虑了机器的柔性、产品类的BOM约束(产品结构约束)。由于建立的模型是一个大规模的混和整数规划问题,无法用一般的数学软件直接进行求解,由此提出了一种基于神经网络和遗传算法的求解近似最优解的方法,并通过实例分析验证了该方法的可行性及其在管理学上的意义。

A model of scenario-based line capacity planning problem for Flexible Manufacturing Systems is developed.The model brings together the feature of structure of product families（BOM constraints） and machine flexibility.Since the resulting model is a large-scale stochastic mixed integer programming problem,it is difficult to solve with standard software packages.We present a heuristic solution scheme using Neural Networks and Genetic Algorithms.We demonstrate the benefit of the model and the feasibility of our approach by numerical experiments.