Constructing A Semiconductor Manufacturing Data Mining Framework, Developing A Decision Tree Algorithm for Classification, and Conducting Empirical Studies

• Main Authors: Perry Lee, 李培瑞
• Other Authors: C.F. Chien
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/41253592807711015896

碩士 === 國立清華大學 === 工業工程與工程管理學系 === 90 === Owing to the rise of e-commerce and information technology, a large amount of data has been automatically or semi- automatically collected in modern industry. Decision makers may potentially use the information buried in the raw data to assist their decisions through data mining for possibly identifying the specific patterns of the data. This study proposes data mining procedures for analyzing semiconductor manufacturing data in the purpose of manufacturing process monitoring and defect diagnosis. In particular, SOM is applied for clustering and decision tree is applied for feature extraction to analyze multi-dimensional semiconductor manufacturing data. We used real data from a fab to conduct two case studies for validation and found that this approach can effectively limit the scope for defect diagnosis and summarize the findings in specific decision rules. In addition, we developed a new decision tree algorithm focused on target class while classification and implement the algorithm on windows platform. We use IRIS data for validation and prove that our decision can correctly, flexibly match the target. And this prototype can be referenced while constructing completed data mining system for semiconductor manufacturing. We conclude this study with discussions on the results and future research.