In this paper, we develop a Generalized Systematic Procedure (GSP) for deter- mining the optimum kanban allocation in just-in-time (JIT) controlled produc- tion lines. This procedure is based on a meta-model that incorporates (1) a factorial design approach to select the appropriate kanban combinations, (2) a simulation model to simulate the JIT production line, and (3) a trained neural network model to evaluate the line performance over the entire domain of poss- ible kanban combinations. The GSP is then applied to a case problem and the results are presented.
展开▼
