Title | ||
---|---|---|
Model reduction method based on selective clustering ensemble algorithm and Theory of Constraints in semiconductor wafer fabrication. |
Abstract | ||
---|---|---|
Simulation model is extensively used for evaluation of dispatching rules in semiconductor wafer fabrication. However, due to the high complexity of the simulation model, the simulation is so time-consuming that it cannot response to the dynamic changes of practical fabrication well. In order to reduce computer execution time and in the same time maintain the ability of the model to evaluate the scheduling rules correctly, a model reduction method based on selective clustering ensemble algorithm (SCEA) and Theory of Constraints (TOC) is proposed. Firstly, SCEA is adopted to identify the unimportant machines steadily, in which multiple base clusterings (BCs) are trained by k-means with different initial cluster centers and then are combined into a final result based on selective weight-voting strategy. Secondly, unimportant machines are removed from the detailed model, since such machines may not significantly affect the performance of the system, according to TOC. Thirdly, closed-loop correction structure is built to ensure the robustness of the reduced model. Finally, the reduced simulation model is used to evaluate the dispatching rules respectively with the scheduling objective of on-time delivery (OTD) rate, mean cycle time (MCT) and throughput. The simulation results show that the method presented is available and effective. |
Year | Venue | Field |
---|---|---|
2016 | CASE | Mathematical optimization,Semiconductor wafer fabrication,Scheduling (computing),Semiconductor device modeling,Algorithm,Robustness (computer science),Theory of constraints,Throughput,Engineering,Cluster analysis,Fabrication |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuanguang Zhou | 1 | 0 | 0.34 |
Cao Zhengcai | 2 | 42 | 16.38 |
Min Liu | 3 | 1 | 1.02 |
Jiaqi Zhang | 4 | 15 | 3.70 |