TY - JOUR
T1 - Automatic data quality evaluation for the AVM system
AU - Huang, Yi Ting
AU - Cheng, Fan Tien
N1 - Funding Information:
Manuscript received April 24, 2008; revised June 12, 2009; accepted April 4, 2011. Date of publication May 12, 2011; date of current version August 3, 2011. This work was supported by the National Science Council of the Republic of China, under Contracts NSC99-2221-E-006-201 and NSC99-2221-E-006-233 as well as Project 982C06. This work is Taiwan, China, Japan, and Korea patents pending under applications 97118526, 200810111271.9, 2009-016051, and 2008-137624, respectively. This paper is also with U.S. Patent Application Pub. U.S. 2009/0292386 A1.
PY - 2011/8
Y1 - 2011/8
N2 - This paper proposes the schemes of automatic process and metrology data-quality evaluations for the automatic virtual metrology (AVM) system. Firstly, principal component analysis is applied to extract data features of all the collected equipment process data; then Euclidean distance is utilized to unify all the principal components into a single index denoted by process data quality index (DQIX) for evaluating the quality of process data. Second, adaptive resonance theory 2 (ART2) and normalized variability are applied to define the metrology data quality index (DQIy) for appraising the quality of metrology data. The thresholds of both DQIX and DQIy are also defined and can be adaptively calculated. The DQIX and DQIy data quality evaluation schemes are well suited for the AVM systems of the semiconductor and thin film transistor-liquid crystal display industries to online, real-time, and automatically evaluate the quality of all the collected process and metrology data. As such, abnormal data will not be adopted for VM model training or tuning and VM conjecture accuracy can be maintained.
AB - This paper proposes the schemes of automatic process and metrology data-quality evaluations for the automatic virtual metrology (AVM) system. Firstly, principal component analysis is applied to extract data features of all the collected equipment process data; then Euclidean distance is utilized to unify all the principal components into a single index denoted by process data quality index (DQIX) for evaluating the quality of process data. Second, adaptive resonance theory 2 (ART2) and normalized variability are applied to define the metrology data quality index (DQIy) for appraising the quality of metrology data. The thresholds of both DQIX and DQIy are also defined and can be adaptively calculated. The DQIX and DQIy data quality evaluation schemes are well suited for the AVM systems of the semiconductor and thin film transistor-liquid crystal display industries to online, real-time, and automatically evaluate the quality of all the collected process and metrology data. As such, abnormal data will not be adopted for VM model training or tuning and VM conjecture accuracy can be maintained.
UR - https://www.scopus.com/pages/publications/80051553999
UR - https://www.scopus.com/pages/publications/80051553999#tab=citedBy
U2 - 10.1109/TSM.2011.2154910
DO - 10.1109/TSM.2011.2154910
M3 - Article
AN - SCOPUS:80051553999
SN - 0894-6507
VL - 24
SP - 445
EP - 454
JO - IEEE Transactions on Semiconductor Manufacturing
JF - IEEE Transactions on Semiconductor Manufacturing
IS - 3
M1 - 5766761
ER -