Abstract
Uncertainty in semiconductor fabrication facilities (fabs) requires scheduling methods to attain quick real-time responses. They should be well tuned to track the changes of a production environment to obtain better operational performance. This paper presents an adaptive dispatching rule (ADR) whose parameters are determined dynamically by real-time information relevant to scheduling. First, we introduce the workflow of ADR that considers both batch and non-batch processing machines to obtain improved fab-wide performance. It makes use of such information as due date of a job, workload of a machine, and occupation time of a job on a machine. Then, we use a backward propagation neural network (BPNN) and a particle swarm optimization (PSO) algorithm to find the relations between weighting parameters and real-time state information to adapt these parameters dynamically to the environment. Finally, a real fab simulation model is used to demonstrate the proposed method. The simulation results show that ADR with constant weighting parameters outperforms the conventional dispatching rule on average; ADR with changing parameters tracking real-time production information over time is more robust than ADR with constant ones; and further improvements can be obtained by optimizing the weights and threshold values of BPNN with a PSO algorithm.
Note to Practitioners-Semiconductor wafer fabrication facilities require dispatching rules with good operational performance when facing a changing and uncertain environment. This work proposes an adaptive dispatching rule (ADR) to satisfy such requirement. Its advantages are to link its own parameters with due date of a job, workload of a machine, and occupation time of a job on a machine; and to adjust its weighting parameters in terms of real-time system status information, e. g., the ratio of hot jobs to work in process (WIP) and the ratio of jobs with one third of photo steps left to WIP in a fab. Thus, it can tune its parameters over time and is, hence, adaptive to a changing environment. The simulation results based on a real fab validate and verify the effectiveness and adaptability of the proposed ADR. It can be readily deployed to a practical fab.