作者: P.C. Chang , T.W. Liao
DOI: 10.1016/J.ASOC.2004.12.004
关键词:
摘要: This paper presents a novel approach by combining SOM and fuzzy rule base for flow time prediction in semiconductor manufacturing factory. Flow of new order is highly related to the shop floor status; however, processes are complicated involve more than hundred production steps. There no governing function identified so far among these status. Therefore, simulation model which mimics process real wafer fab located Hsin-Chu Science-based Park Taiwan built status collected fed into classification. Then, corresponding selected applied prediction. Genetic further fine-tune composition base. Finally, using simulated data, effectiveness proposed method shown comparing with other approaches.