Advanced ART2 scheme for enhancing metrology-data-quality evaluation

Yi Ting Huang, Fan-Tien Cheng, Yu Hsuan Shih, Yen Lun Chen

研究成果: Article

6 引文 (Scopus)

摘要

The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIyalgorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIyvalue and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIydetection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIyalgorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.

指紋

Liquid crystal displays
Industrial plants
Color

All Science Journal Classification (ASJC) codes

  • Engineering(all)

引用此文

@article{b70bbed7f7d94c7c8e797fc567d1ab1d,
title = "Advanced ART2 scheme for enhancing metrology-data-quality evaluation",
abstract = "The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIyalgorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIyvalue and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIydetection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIyalgorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.",
author = "Huang, {Yi Ting} and Fan-Tien Cheng and Shih, {Yu Hsuan} and Chen, {Yen Lun}",
year = "2014",
month = "11",
day = "1",
doi = "10.1080/02533839.2014.912773",
language = "English",
volume = "37",
pages = "1064--1079",
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 = "8",

}

TY - JOUR

T1 - Advanced ART2 scheme for enhancing metrology-data-quality evaluation

AU - Huang, Yi Ting

AU - Cheng, Fan-Tien

AU - Shih, Yu Hsuan

AU - Chen, Yen Lun

PY - 2014/11/1

Y1 - 2014/11/1

N2 - The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIyalgorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIyvalue and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIydetection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIyalgorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.

AB - The metrology-data-quality-index (DQIy) algorithm was proposed to perform metrology-data-quality evaluation of the automatic virtual metrology system developed by the authors. The DQIyalgorithm is based on the adaptive-resonance-theory 2 (ART2). ART2 divides data into different patterns according to the similarity of process data, and then calculates the corresponding DQIyvalue and its threshold, DQIyT, for evaluation and judgment. However, in practical applications, the classical ART2 technique still could not cluster process data very precisely. Since some samples with dissimilar process parameters might be sorted into the same cluster, two or more groups could be found in the corresponding metrology-data cluster. This phenomenon may cause invalid DQIydetection. To solve the problem above, the advanced ART2 scheme is proposed in this paper to enhance the accuracy of the DQIyalgorithm. A large industrial data-set showing both a shift in metrology measurements without a process shift and a process shift that was not captured by the metrology of the actual photo and color-filter production tools of a TFT-LCD factory were adopted as illustrative examples to verify the practicality of the proposed scheme. Experimental results show that the performance of the advanced ART2 is indeed better than that of the original ART2.

UR - http://www.scopus.com/inward/record.url?scp=84907711545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907711545&partnerID=8YFLogxK

U2 - 10.1080/02533839.2014.912773

DO - 10.1080/02533839.2014.912773

M3 - Article

AN - SCOPUS:84907711545

VL - 37

SP - 1064

EP - 1079

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 - 8

ER -