Processing Time Prediction Method Based on SVR in Semiconductor Manufacturing  

作　　者：朱雪初 乔非 

机构地区：[1]College of Electronics & Information Engineering,Tongji University

出　　处：《Journal of Donghua University(English Edition)》2014年第2期98-101,共4页东华大学学报（英文版）

基　　金：National Natural Science Foundation of China(No.61034004)

摘　　要：The prediction problem of the actual value of the dynamic parameters in the simulation model in semiconductor manufacturing was discussed. Considering the fact that the default value of processing time of one certain equipment in the simulation model was not the same as its actual value,a general data driven prediction model of the processing time was built based on support vector regression( SVR),with the utilization of manufacturing information in manufacturing execution system( MES). The processing time of one certain equipment was highly related to the status of the equipment itself and the wafers being processed. To uncover the relationship of the processing time with the information of historical products,process flow,technical standard of silicon wafers and manual intervention,data were extracted from MES and used to build a prediction model. This model was employed on an ion implantation equipment as a case, and the effectiveness of the proposed method was shown by comparing with other approaches.The prediction problem of the actual value of the dynamic parameters in the simulation model in semiconductor manufacturing was discussed. Considering the fact that the default value of processing time of one certain equipment in the simulation model was not the same as its actual value. a general data driven prediction model of the processing time was built based on support vector regression （SVR） , with the utilization of manufacturing information in manufacturing execution system （MES）. The processing time of one certain equipment was highly related to the status of the equipment itself and the wafers being processed. To uncover the relationship of the processing time with the information of historical products. process flow. technical standard of silicon wafers and manual intervention. data were extracted from MES and used to build a prediction model. This model was employed on an ion implantation equipment as a case. and the effectiveness of the proposed method was shown by comparing with other approaches.

关 键 词：SEMICONDUCTOR MANUFACTURING SUPPORT VECTOR regression(SVR) PROCESSING time prediction 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]