The use of mahalanobis distance in solving the sputtering process thin-film thickness uniformity quality problem

Ta-Ho Yang, Yuan Ting Cheng, Yu An Shen

Research output: Contribution to journalArticle

Abstract

Sputtering is one of the important processes in color filter (CF) manufacture, and the sputtering coating thin-film thickness uniformity affects the final quality of the products. The present study aims at solving the CF sputtering process thin-film thickness uniformity quality problem. The mean, the standard deviation and the range of the thickness are adopted as the quality characteristics, as opposed to the general approach that only considers the thickness mean in the measurements of thin-film thickness uniformity. The present study proposes Mahalanobis distance (MD) as a method to detect the nonconforming items in the sputtering process. The proposed method is a robust classification technique and has been applied in various fields effectively. In addition, it is applicable to solving the class imbalance problem. A practical case, which reveals very limited numbers of nonconforming items from the sputtering process in CF, is adopted for the empirical illustrations. The solution quality is compared with that of discriminant analysis (DA). By the MD method, the average accuracy of different quality measure criteria is between 91%∼94% and the results of relative sensitivity (RS) of the MD method are better than those of DA. In comparison with DA, the empirical results demonstrate that the MD method is more accurate and efficient in solving a multivariate, class imbalance problem.

Original languageEnglish
Pages (from-to)1021-1033
Number of pages13
JournalJournal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an
Volume33
Issue number7
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Sputtering
Film thickness
Discriminant analysis
Thin films
Color
Coatings

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{b63bd20d9f5545b083e23c5cb7d599ba,
title = "The use of mahalanobis distance in solving the sputtering process thin-film thickness uniformity quality problem",
abstract = "Sputtering is one of the important processes in color filter (CF) manufacture, and the sputtering coating thin-film thickness uniformity affects the final quality of the products. The present study aims at solving the CF sputtering process thin-film thickness uniformity quality problem. The mean, the standard deviation and the range of the thickness are adopted as the quality characteristics, as opposed to the general approach that only considers the thickness mean in the measurements of thin-film thickness uniformity. The present study proposes Mahalanobis distance (MD) as a method to detect the nonconforming items in the sputtering process. The proposed method is a robust classification technique and has been applied in various fields effectively. In addition, it is applicable to solving the class imbalance problem. A practical case, which reveals very limited numbers of nonconforming items from the sputtering process in CF, is adopted for the empirical illustrations. The solution quality is compared with that of discriminant analysis (DA). By the MD method, the average accuracy of different quality measure criteria is between 91{\%}∼94{\%} and the results of relative sensitivity (RS) of the MD method are better than those of DA. In comparison with DA, the empirical results demonstrate that the MD method is more accurate and efficient in solving a multivariate, class imbalance problem.",
author = "Ta-Ho Yang and Cheng, {Yuan Ting} and Shen, {Yu An}",
year = "2010",
month = "1",
day = "1",
doi = "10.1080/02533839.2010.9671691",
language = "English",
volume = "33",
pages = "1021--1033",
journal = "Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers",
issn = "0253-3839",
publisher = "Chinese Institute of Engineers",
number = "7",

}

TY - JOUR

T1 - The use of mahalanobis distance in solving the sputtering process thin-film thickness uniformity quality problem

AU - Yang, Ta-Ho

AU - Cheng, Yuan Ting

AU - Shen, Yu An

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Sputtering is one of the important processes in color filter (CF) manufacture, and the sputtering coating thin-film thickness uniformity affects the final quality of the products. The present study aims at solving the CF sputtering process thin-film thickness uniformity quality problem. The mean, the standard deviation and the range of the thickness are adopted as the quality characteristics, as opposed to the general approach that only considers the thickness mean in the measurements of thin-film thickness uniformity. The present study proposes Mahalanobis distance (MD) as a method to detect the nonconforming items in the sputtering process. The proposed method is a robust classification technique and has been applied in various fields effectively. In addition, it is applicable to solving the class imbalance problem. A practical case, which reveals very limited numbers of nonconforming items from the sputtering process in CF, is adopted for the empirical illustrations. The solution quality is compared with that of discriminant analysis (DA). By the MD method, the average accuracy of different quality measure criteria is between 91%∼94% and the results of relative sensitivity (RS) of the MD method are better than those of DA. In comparison with DA, the empirical results demonstrate that the MD method is more accurate and efficient in solving a multivariate, class imbalance problem.

AB - Sputtering is one of the important processes in color filter (CF) manufacture, and the sputtering coating thin-film thickness uniformity affects the final quality of the products. The present study aims at solving the CF sputtering process thin-film thickness uniformity quality problem. The mean, the standard deviation and the range of the thickness are adopted as the quality characteristics, as opposed to the general approach that only considers the thickness mean in the measurements of thin-film thickness uniformity. The present study proposes Mahalanobis distance (MD) as a method to detect the nonconforming items in the sputtering process. The proposed method is a robust classification technique and has been applied in various fields effectively. In addition, it is applicable to solving the class imbalance problem. A practical case, which reveals very limited numbers of nonconforming items from the sputtering process in CF, is adopted for the empirical illustrations. The solution quality is compared with that of discriminant analysis (DA). By the MD method, the average accuracy of different quality measure criteria is between 91%∼94% and the results of relative sensitivity (RS) of the MD method are better than those of DA. In comparison with DA, the empirical results demonstrate that the MD method is more accurate and efficient in solving a multivariate, class imbalance problem.

UR - http://www.scopus.com/inward/record.url?scp=78049457554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049457554&partnerID=8YFLogxK

U2 - 10.1080/02533839.2010.9671691

DO - 10.1080/02533839.2010.9671691

M3 - Article

VL - 33

SP - 1021

EP - 1033

JO - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

JF - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

SN - 0253-3839

IS - 7

ER -