A Clustering-Based Equipment Condition Model of Chemical Vapor Deposition Process

Youngji Yoo, Seung Hwan Park, Jun Geol Baek

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

In semiconductor manufacturing, equipment condition monitoring is important to improve the efficiency of the manufacturing process by performing equipment maintenance in a timely manner. In this paper, we propose the clustering-based equipment condition model to select key sensors relating to a maintenance. During the manufacturing process, huge amounts of data are collected in real time from sensors on the equipment. The sensor data has various patterns, such as increased pattern, decreased pattern, unchanged pattern, and other patterns. We apply five clustering algorithms to group the sensors with similar characteristics and extract key sensors that are highly correlated with equipment health condition. The health condition monitoring model consists of the combination of key sensors. To validate proposed method, the empirical study is conducted using collected sensor data from a chemical vapor deposition (CVD) process in a semiconductor company in the Republic of Korea. The model with clustered sensors outperforms the model with full sensors. The health condition monitoring model assists engineers in making decisions regarding the equipment maintenance.

Original languageEnglish
Pages (from-to)1677-1689
Number of pages13
JournalInternational Journal of Precision Engineering and Manufacturing
Volume20
Issue number10
DOIs
Publication statusPublished - 2019 Oct 1

Keywords

  • Chemical vapor deposition (CVD) process
  • Clustering
  • Health condition monitoring
  • Predictive maintenance
  • Semiconductor manufacturing process

ASJC Scopus subject areas

  • Mechanical Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Clustering-Based Equipment Condition Model of Chemical Vapor Deposition Process'. Together they form a unique fingerprint.

Cite this