An intelligent approach to adapting Kanban cards with fuzzy controller for pull production control

This document presents research on an intelligent policy based on fuzzy logic for dynamically adjusting the number of Kanban cards in a pull production system operating in a stochastic environment, while taking into account fluctuations in customer demand. The objective is to maintain a high level of performance measures in terms of production costs and customer satisfaction. The proposed approach involves developing a fuzzy controller for adaptive control of the number of cards that considers only the level of inventory and the number of additional cards in circulation. However, this real-time dynamic adaptation can lead to an excessive number of changes that can negatively affect the production system. To evaluate the decisions made by the fuzzy controller in real-time, a simulation model was developed using a discrete event simulation environment based on Rockwell’s ARENA® platform. Furthermore, the optimization of the fuzzy system’s parameters was calculated using the OptQuest optimizer to reduce costs while ensuring customer satisfaction. The results were compared with other adaptive control approaches from the literature for a stochastic environment, without any estimation of future demands. The effectiveness of our fuzzy adaptive control approach was demonstrated in terms of relative performance measures for production costs and customer satisfaction. Additionally, the robustness of our fuzzy controller was tested in terms of nervousness, as measured by the number of changes in Kanban cards.