A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced data. (July 2019)

• Record Type: Journal Article
• Authors: Lee, Dong-Hee; Yang, Jin-Kyung; Lee, Cho-Heui; Kim, Kwang-Jae
• Is Part Of: Journal of manufacturing systems. Volume 52(2019)Part A
• Page Start: 146
• Page End: 156
• Publication Date: 2019-07
• Subjects: Semiconductor manufacturing -- Data mining -- Missing value imputation -- Re-Sampling -- Feature selection; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2019.07.001
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: Critical process steps for wafer fabrication are selected by analyzing data. Yield prediction model is build based on the selected critical process steps. Yield prediction shows high accuracy. Various data mining techniques are validated and used for analyzing the data. Abstract: Semiconductor wafers are fabricated through sequential process steps. Some process steps have a strong relationship with wafer yield, and these are called critical process steps. Because wafer yield is a key performance index in wafer fabrication, the critical process steps should be carefully selected and managed. This paper proposes a systematic and data-driven approach for identifying the critical process steps. The proposed method considers troublesome properties of the data from the process steps such as imbalanced data, missing values, and random sampling. As a case study, we analyzed hypothetical operational data and confirmed that the proposed method works well.