A data mining project for solving low-yield situations of semiconductor manufacturing

Abstract

With huge amount of semiconductor engineering data stored in database and versatile analytical charting and reporting in production and development, the CIM/MES/EDA systems in the most semiconductor manufacturing companies help users to analyze the collected data in order to achieve the goal of yield enhancement. However, the procedures of semiconductor manufacturing are sophisticated and the collected data among these procedures are thus becoming high-dimensional and huge. Currently, some statistical methods, such like K-W test, covariance analysis, regression analysis, etc., have been used to analyze the information summarized from EDA system, and thus generate too many indexes that can not be easily judged and assimilated by engineers. Besides, too many false alarms may be raised and lots of time is required to check the factuality among them. In order to deal with the large amount and high-dimensional data, the data mining technologies are thus used to solve such problems. In this paper, we would like to propose a data mining solution and describe the experiences applying such solutions for discovering the root causes of low-yield situations in a worldwide semiconductor manufacturing company. Also, the situation of applying such mining solution for manufacturing defects detection in semiconductor manufacturing domain will be reviewed Finally, the architecture of a reasonable, reliable and flexible data mining system will be briefly described.