A virtual metrology approach for maintenance compensation to improve yield in semiconductor manufacturing

DOI

10.1080/18756891.2014.947116How to use a DOI?

Keywords

virtual metrology, manufacturing intelligence, maintenance, yield enhancement, chemical vapor deposition (CVD), semiconductor manufacturing enhancement

Abstract

Process condition was changed by preventative maintenance that may lead to the inconsistency of process output. In practice, process engineers have difficulties to discover the inconsistency that the defect wafer may have been produced before the next measurement. This study proposes a virtual metrology (VM) approach for maintenance compensation in semiconductor manufacturing. The tool process parameter streams were collected to predict the product metrology value, and a relation model was built to adjust the equipment settings for product recipe compensation. An empirical study in maintenance compensation of chemical vapor deposition (CVD) was conducted in a Taiwan semiconductor company for validation. The thickness difference caused by maintenance was reduced from 571Å to 77Å in training data and 564Å to 210Å in testing data. The results showed practical viability of the proposed approach and an intelligent system embedded with the developed algorithm has been implemented.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Kuo-Yi Lin
AU  - Chia-Yu Hsu
AU  - Hui-Chun Yu
PY  - 2014
DA  - 2014/07/01
TI  - A virtual metrology approach for maintenance compensation to improve yield in semiconductor manufacturing
JO  - International Journal of Computational Intelligence Systems
SP  - 66
EP  - 73
VL  - 7
IS  - Supplement 2
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2014.947116
DO  - 10.1080/18756891.2014.947116
ID  - Lin2014
ER  -