Data science framework for variable selection, metrology prediction, and process control in TFT-LCD manufacturing

Chia-Yen Lee, Tsung Lun Tsai

Research output: Contribution to journalArticle

Abstract

TFT-LCD panel manufacturers rely on experimental design and engineering experience for process monitoring and quality control throughout the production line. To shorten production and reduce the cost of labor resources, this study proposes a three-phase data science framework embedded with several data mining and machine learning techniques, which can identify the variables affecting yield, predict the metrology result of photo spacer process, and suggest the process control in the color filter manufacturing process. An empirical study of Taiwan's leading TFT-LCD manufacturer is conducted to validate the proposed framework. The results indicate that the proposed framework effectively and quickly selects the important variables, predicts the metrology result with higher performance, and identifies the main effect and interaction effect of the selected variables for yield improvement.

LanguageEnglish
Pages76-87
Number of pages12
JournalRobotics and Computer-Integrated Manufacturing
Volume55
DOIs
Publication statusPublished - 2019 Feb 1

Fingerprint

Variable Selection
Metrology
Liquid crystal displays
Process Control
Process control
Manufacturing
Prediction
Process monitoring
Design of experiments
Quality control
Data mining
Learning systems
Predict
Production Line
Process Monitoring
Interaction Effects
Main Effect
Taiwan
Personnel
Quality Control

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Mathematics(all)
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

@article{d4aa963d2cb8486d8beb386b66b1e30f,
title = "Data science framework for variable selection, metrology prediction, and process control in TFT-LCD manufacturing",
abstract = "TFT-LCD panel manufacturers rely on experimental design and engineering experience for process monitoring and quality control throughout the production line. To shorten production and reduce the cost of labor resources, this study proposes a three-phase data science framework embedded with several data mining and machine learning techniques, which can identify the variables affecting yield, predict the metrology result of photo spacer process, and suggest the process control in the color filter manufacturing process. An empirical study of Taiwan's leading TFT-LCD manufacturer is conducted to validate the proposed framework. The results indicate that the proposed framework effectively and quickly selects the important variables, predicts the metrology result with higher performance, and identifies the main effect and interaction effect of the selected variables for yield improvement.",
author = "Chia-Yen Lee and Tsai, {Tsung Lun}",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.rcim.2018.07.013",
language = "English",
volume = "55",
pages = "76--87",
journal = "Robotics and Computer-Integrated Manufacturing",
issn = "0736-5845",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Data science framework for variable selection, metrology prediction, and process control in TFT-LCD manufacturing

AU - Lee, Chia-Yen

AU - Tsai, Tsung Lun

PY - 2019/2/1

Y1 - 2019/2/1

N2 - TFT-LCD panel manufacturers rely on experimental design and engineering experience for process monitoring and quality control throughout the production line. To shorten production and reduce the cost of labor resources, this study proposes a three-phase data science framework embedded with several data mining and machine learning techniques, which can identify the variables affecting yield, predict the metrology result of photo spacer process, and suggest the process control in the color filter manufacturing process. An empirical study of Taiwan's leading TFT-LCD manufacturer is conducted to validate the proposed framework. The results indicate that the proposed framework effectively and quickly selects the important variables, predicts the metrology result with higher performance, and identifies the main effect and interaction effect of the selected variables for yield improvement.

AB - TFT-LCD panel manufacturers rely on experimental design and engineering experience for process monitoring and quality control throughout the production line. To shorten production and reduce the cost of labor resources, this study proposes a three-phase data science framework embedded with several data mining and machine learning techniques, which can identify the variables affecting yield, predict the metrology result of photo spacer process, and suggest the process control in the color filter manufacturing process. An empirical study of Taiwan's leading TFT-LCD manufacturer is conducted to validate the proposed framework. The results indicate that the proposed framework effectively and quickly selects the important variables, predicts the metrology result with higher performance, and identifies the main effect and interaction effect of the selected variables for yield improvement.

UR - http://www.scopus.com/inward/record.url?scp=85050872315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050872315&partnerID=8YFLogxK

U2 - 10.1016/j.rcim.2018.07.013

DO - 10.1016/j.rcim.2018.07.013

M3 - Article

VL - 55

SP - 76

EP - 87

JO - Robotics and Computer-Integrated Manufacturing

T2 - Robotics and Computer-Integrated Manufacturing

JF - Robotics and Computer-Integrated Manufacturing

SN - 0736-5845

ER -