Title :
On the use of decision tree induction for discovery of interactions in a photolithographic process
Author :
Braha, Dan ; Shmilovici, Armin
Author_Institution :
Sch. of Ind. Eng. & Manage., Ben-Gurion Univ., Beer-Sheva, Israel
Abstract :
This paper delineates a comprehensive and successful application of decision tree induction to 1054 records of production lots taken from a lithographic process with 45 processing steps. Complex interaction effects among manufacturing equipment that lead to increased product variability have been detected. The extracted information has been confirmed by the process engineers, and used to improve the lithographic process. The paper suggests that decision tree induction may be particularly useful when data is multidimensional, and the various process parameters and machinery exhibit highly complex interactions. Another implication is that on-line monitoring of the manufacturing process (e.g., closed-loop critical dimensions control) using data mining may be highly effective.
Keywords :
closed loop systems; data mining; decision trees; photolithography; process control; process monitoring; semiconductor device manufacture; closed-loop critical dimension control; data mining; decision tree induction; multidimensional data; on-line monitoring; photolithographic process control; semiconductor manufacturing; Data analysis; Data engineering; Data mining; Databases; Decision trees; Information analysis; Manufacturing processes; Process control; Production; Semiconductor device manufacture;
Journal_Title :
Semiconductor Manufacturing, IEEE Transactions on
DOI :
10.1109/TSM.2003.818959