A multi-criteria decision making procedure based on neural networks for kanban allocation

In this study, we proposed a methodology for determining optimal number of kanbans for each station in a JIT manufacturing system. In this methodology, a backpropagation neural network is used in order to generate simulation meta-models, and a multi-criteria decision making technique (TOPSIS) is employed in order to evaluate kanban combinations with respect to the relative importance of the performance measures. The proposed methodology is applied to a case problem and the results are presented. The results show that the methodology can solve this type of problems effectively and efficiently.