A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced data

Dong-Hee Lee, Jin Kyung Yang, Cho Heui Lee, Kwang Jae Kim

Research output: Contribution to journalArticleResearchpeer-review

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.

Original languageEnglish
Pages (from-to)146-156
Number of pages11
JournalJournal of Manufacturing Systems
Volume52
DOIs
StatePublished - 2019 Jul 1

Fingerprint

Semiconductor materials
Sampling
Fabrication

Keywords

  • Data mining
  • Feature selection
  • Missing value imputation
  • Re-Sampling
  • Semiconductor manufacturing

Cite this

@article{25ace752bd7d42c8aea55ecba61ab1eb,
title = "A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced 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.",
keywords = "Data mining, Feature selection, Missing value imputation, Re-Sampling, Semiconductor manufacturing",
author = "Dong-Hee Lee and Yang, {Jin Kyung} and Lee, {Cho Heui} and Kim, {Kwang Jae}",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.jmsy.2019.07.001",
language = "English",
volume = "52",
pages = "146--156",
journal = "Journal of Manufacturing Systems",
issn = "0278-6125",

}

A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced data. / Lee, Dong-Hee; Yang, Jin Kyung; Lee, Cho Heui; Kim, Kwang Jae.

In: Journal of Manufacturing Systems, Vol. 52, 01.07.2019, p. 146-156.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced data

AU - Lee, Dong-Hee

AU - Yang, Jin Kyung

AU - Lee, Cho Heui

AU - Kim, Kwang Jae

PY - 2019/7/1

Y1 - 2019/7/1

N2 - 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.

AB - 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.

KW - Data mining

KW - Feature selection

KW - Missing value imputation

KW - Re-Sampling

KW - Semiconductor manufacturing

UR - http://www.scopus.com/inward/record.url?scp=85068842349&partnerID=8YFLogxK

U2 - 10.1016/j.jmsy.2019.07.001

DO - 10.1016/j.jmsy.2019.07.001

M3 - Article

VL - 52

SP - 146

EP - 156

JO - Journal of Manufacturing Systems

JF - Journal of Manufacturing Systems

SN - 0278-6125

ER -