A Dynamic Method for Optimal WIP Allocation and Control in a Semiconductor Manufacturing System

The required total WIP level of the semiconductor manufacturing system is estimated by using neural networks, and then the total number of WIP is allocated to each workstation and operation by using the queuing model. The resulting WIP level for each operation is then used to control the manufacturing system. The simulation results show that the proposed method for allocating total WIP to each workstation and operation can reduce 16% of mean cycle time and not increase the variation of cycle time for the manufacturing system.