[Cao Zhengcai; Zhao Huidan] Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China. [Cao Zhengcai] Xi An Jiao Tong Univ, State Key Lab Mfg Syst Engn, Xian 710054, Peoples R China. [Wang Yongji] Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China.
Abstract:
In this paper, an optimized mechanism for Semiconductor wafer fabrication (SWF) by integrating the Adaptive neuro-fuzzy inference system (ANFIS) with Simulated annealing (SA) algorithm is proposed. In this approach, aiming to solve the rush order problem which significantly affect the cycle time and impact the Work in process (WIP) of lots due to the high priority, we build an ANFIS based prediction model which will be embedded into releasing to forecast product codes and quantities of the contingent rush orders. Then a scheduler based on SA algorithm is constructed, the coding of which represents a combination of scheduling policies, including lot releasing policies, dispatching rules, batching rules and setting-up rules. When the SA finished its optimization process, an optimal scheduling policy is produced. By using the proposed approach, we will find that the system can be optimized to a large extent and give a better performance.
English Abstract:
In this paper, an optimized mechanism for Semiconductor wafer fabrication (SWF) by integrating the Adaptive neuro-fuzzy inference system (ANFIS) with Simulated annealing (SA) algorithm is proposed. In this approach, aiming to solve the rush order problem which significantly affect the cycle time and impact the Work in process (WIP) of lots due to the high priority, we build an ANFIS based prediction model which will be embedded into releasing to forecast product codes and quantities of the contingent rush orders. Then a scheduler based on SA algorithm is constructed, the coding of which represents a combination of scheduling policies, including lot releasing policies, dispatching rules, batching rules and setting-up rules. When the SA finished its optimization process, an optimal scheduling policy is produced. By using the proposed approach, we will find that the system can be optimized to a large extent and give a better performance.
Cao Zhengcai,Zhao Huidan,Wang Yongji. ANFIS and SA Based Approach to Prediction, Scheduling, and Performance Evaluation for Semiconductor Wafer Fabrication[J]. CHINESE JOURNAL OF ELECTRONICS,2013-01-01,22(1):25-30.
