Dynamic decentralised balancing of CONWIP production systems

This paper presents a non-linear programming model for online balancing of the work-in-queue (WIQ) of a fast response production system that consists of multiple workstations and diverse part mix. The model resembles a multiple product CONWIP (constant work-in-progress) system with a variety of products' routings and bottlenecks. It maximises a global benefit of the production system subject to delay and loading rate bounds. The upper bounds on the delay symbolise the desired level of WIQ. The approach relies on the delay of the authorisation cards as a measure of the actual system WIQ. A real-time primal-dual algorithm associated with each part type is used to solve the optimisation problem in a decentralised manner. The algorithm solves for the optimal rates in a timely decentralised iterative way without the access to the global information of the production system. Each part route calculates its loading rate according to the arrival of the authorisation cards. Extensive simulation experiments were conducted to demonstrate the reliability of the algorithm. The calculated rates were found to be proportional to the level of WIQ at each workstation with reasonable resource allocation achieved between the different routes