In semiconductor manufacturing, continuous on-line monitoring prevents production stop and yield loss. The challenges towards this accomplishment are: 1) the complexity of lithography machines which are composed of hundreds of mechanical and optical components, 2) the high rate and volume data acquisition from different lithography and metrology machines, and 3) the scarcity of performance measurements due to their cost. This paper addresses these challenges by 1) visualizing and ranking the most relevant factors to a performance metric, 2) organizing efficiently Big Data from different sources and 3) predicting the performance with machine learning when measurements are lacking. Even though this project targets semiconductor manufacturing, its methodology is applicable to any case of monitoring complex systems, with many potentially interesting features, and imbalanced datasets.

References

[1]

Leo Breiman. 2001. Random Forests. Machine Learning 45, 1 (2001), 5--32.

Digital Library

Google Scholar

[2]

Houtao Deng and George Runger. 2012. Feature Selection via Regularized Trees. The 2012 International Joint Conference on Neural Networks (IJCNN), IEEE (2012).

Crossref

Google Scholar

[3]

Pedro Domingos. 2012. A Few Useful Things to Know About Machine Learning. Commun. ACM 55, 10 (2012), 78--87.

Digital Library

Google Scholar

[4]

Peter Filzmoser. 2017. Multivariate Outlier Detection Based on Robust Methods. CRAN repository. (Jan. 2017). https://CRAN.R-project.org/package=mvoutlier

Google Scholar

[5]

Peter Filzmoser, Robert G. Garrett, and Clemens Reimann. 2005. Multivariate Outlier Detection in Exploration Geochemistry. Comput. Geosci. 31, 5 (June 2005), 579--587.

Digital Library

Google Scholar

[6]

Isabelle Guyon, Jason Weston, Stephen Barnhill, and Vladimir Vapnik. 2002. Gene Selection for Cancer Classification using Support Vector Machines. Machine Learning 46, 1 (2002), 389--422.

Digital Library

Google Scholar

[7]

A. Lam, F. Pasqualini, J. de Caunes, and M. Gatefait. 2010. Overlay breakdown methodology on immersion scanner. Proc. SPIE 7638 (2010).

Google Scholar

[8]

A. Lam, A. Ypma, M. Gatefait, D. Deckers, A. Koopman, R. van Haren, and J Beltman. 2015. Pattern recognition and data mining techniques to identify factors in wafer processing and control determining overlay error. Proc. SPIE 9424 (2015).

Google Scholar

[9]

Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9 (2008).

Google Scholar

[10]

M. Mitchell Waldrop. 2016. More than Moore. Nature 530 (2016), 144 âĂŞ 147.

Google Scholar

[11]

A. Ypma, J. Menger, D. Deckers, D. Han, A. Koopman, I. Lyulina, S. Middlebrooks, R. Haren Van, and J. Wildenberg. 2015. Methods and apparatus for obtaining diagnostic information relating to an industrial process. Patent WO2015049087 A1. (2015).

Google Scholar

Cited By

View all

Gentner TBreitenbach JNeitzel TSchulze JBuettner R(2022)A Systematic Literature Review of Machine Learning Applications for Process Monitoring and Control in Semiconductor Manufacturing2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)10.1109/COMPSAC54236.2022.00169(1081-1086)Online publication date: Jun-2022
https://doi.org/10.1109/COMPSAC54236.2022.00169
Wang YZhu ZWang LSun GLiang R(2022)Visualization and visual analysis of multimedia data in manufacturing: A surveyVisual Informatics10.1016/j.visinf.2022.09.0016:4(12-21)Online publication date: Dec-2022
https://doi.org/10.1016/j.visinf.2022.09.001
van Dijk LHasibi FLarrañaga MPastol ALam Avan Haren R(2019)Smart implant-layer overlay metrology to enable fab cycle time reductionMetrology, Inspection, and Process Control for Microlithography XXXIII10.1117/12.2515185(51)Online publication date: 26-Mar-2019
https://doi.org/10.1117/12.2515185
Show More Cited By

Recommendations

A Hybrid Big Data Analytics Method for Yield Improvement in Semiconductor Manufacturing
ASE BD&SI '15: Proceedings of the ASE BigData & SocialInformatics 2015

In the manufacturing of semiconductor encapsulation, the production yield is one of critical issues concerned by all foundries. It is because that yield rate can directly affects the quality of the final product and the profitability. In this work we ...
Introduction to Big Data: Scalable Representation and Analytics for Data Science Minitrack
HICSS '13: Proceedings of the 2013 46th Hawaii International Conference on System Sciences

Big data is an emerging phenomenon characterized by the three Vs: volume, velocity, and variety. The volume of data has increased from terabytes to petabytes and is encroaching on exabytes. Some pundits are suggesting that zettabytes (1021) are ...
Big data

We use structuralism and functionalism paradigms to analyze the origins of big data applications.Current trends and sources of big data.Processing technologies, methods and analysis techniques for big data are compared in detail.We analyze major ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

CF'17: Proceedings of the Computing Frontiers Conference

May 2017

450 pages

ISBN:9781450344876

DOI:10.1145/3075564

General Chair:
Roberto Giorgi
University of Siena, IT
,
Program Chairs:
Michela Becchi
North Carolina State University
,
Francesca Palumbo
University of Sassari, IT

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 May 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CF '17

Sponsor:

SIGMICRO

CF '17: Computing Frontiers Conference

May 15 - 17, 2017

Siena, Italy

Acceptance Rates

CF'17 Paper Acceptance Rate 43 of 87 submissions, 49%;

Overall Acceptance Rate 273 of 785 submissions, 35%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
453
Total Downloads

Downloads (Last 12 months)27
Downloads (Last 6 weeks)1

Reflects downloads up to 22 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Gentner TBreitenbach JNeitzel TSchulze JBuettner R(2022)A Systematic Literature Review of Machine Learning Applications for Process Monitoring and Control in Semiconductor Manufacturing2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)10.1109/COMPSAC54236.2022.00169(1081-1086)Online publication date: Jun-2022
https://doi.org/10.1109/COMPSAC54236.2022.00169
Wang YZhu ZWang LSun GLiang R(2022)Visualization and visual analysis of multimedia data in manufacturing: A surveyVisual Informatics10.1016/j.visinf.2022.09.0016:4(12-21)Online publication date: Dec-2022
https://doi.org/10.1016/j.visinf.2022.09.001
van Dijk LHasibi FLarrañaga MPastol ALam Avan Haren R(2019)Smart implant-layer overlay metrology to enable fab cycle time reductionMetrology, Inspection, and Process Control for Microlithography XXXIII10.1117/12.2515185(51)Online publication date: 26-Mar-2019
https://doi.org/10.1117/12.2515185
Lamghari-Idrissi DSoellaart DBasten RDellaert N(2019)Influence of Spare Parts Service Measures on the Performance of Front-End Wafer Production Process2019 Winter Simulation Conference (WSC)10.1109/WSC40007.2019.9004919(2269-2280)Online publication date: Dec-2019
https://doi.org/10.1109/WSC40007.2019.9004919
Cekli HNije JYpma ABastani VSonntag DNiesing HZhang LUllah ZSubramony VSomasundaram RSusanto WMatsunobu MJohnson JTabery CLin CZou Y(2018)A novel patterning control strategy based on real-time fingerprint recognition and adaptive wafer level scanner optimizationMetrology, Inspection, and Process Control for Microlithography XXXII10.1117/12.2297304(57)Online publication date: 13-Mar-2018
https://doi.org/10.1117/12.2297304

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Recommendations

A Hybrid Big Data Analytics Method for Yield Improvement in Semiconductor Manufacturing

Introduction to Big Data: Scalable Representation and Analytics for Data Science Minitrack

Big data