Real time plasma etch process modeling by neural networks

Jennie Si; Yuan Ling Tseng; Mike Clayton; Steve Felker; Bob Yoo; Jim Martinez; Jim Durham; Kim Dang

Real time plasma etch process modeling by neural networks

Jennie Si, Yuan Ling Tseng, Mike Clayton, Steve Felker, Bob Yoo, Jim Martinez, Jim Durham, Kim Dang

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In the present paper we address the problem of control relevant process modeling from production data for the N-Well Reactive Ion Etching processed by LAM Rainbow Etchers. Due to physical constraints we consider building an empirical neural network model using one lot of data which usually contains 24 wafers. Using the existence result of feedforward networks as universal approximators, we experimentally developed different network structures as models of the etching process under investigation. Our results are built upon extensive simulations on different lots of the process. The same modeling idea is also extended to use the network model to predict the end point detection signal prior the process of one wafer.

Original language	English (US)
Title of host publication	IEEE Symposium on Emerging Technologies & Factory Automation, ETFA
Place of Publication	Piscataway, NJ, United States
Publisher	IEEE
Pages	347-352
Number of pages	6
State	Published - 1997
Event	Proceedings of the 1997 IEEE 6th International Conference on Emerging Technologies and Factory Automation, ETFA'97 - Los Angeles, CA, USA Duration: Sep 9 1997 → Sep 12 1997

Other

Other	Proceedings of the 1997 IEEE 6th International Conference on Emerging Technologies and Factory Automation, ETFA'97
City	Los Angeles, CA, USA
Period	9/9/97 → 9/12/97

ASJC Scopus subject areas

Engineering(all)

Cite this

Si, J, Tseng, YL, Clayton, M, Felker, S, Yoo, B, Martinez, J, Durham, J & Dang, K 1997, Real time plasma etch process modeling by neural networks. in IEEE Symposium on Emerging Technologies & Factory Automation, ETFA. IEEE, Piscataway, NJ, United States, pp. 347-352, Proceedings of the 1997 IEEE 6th International Conference on Emerging Technologies and Factory Automation, ETFA'97, Los Angeles, CA, USA, 9/9/97.

@inproceedings{c4c2d51901fd4386af6e411efed89347,

title = "Real time plasma etch process modeling by neural networks",

abstract = "In the present paper we address the problem of control relevant process modeling from production data for the N-Well Reactive Ion Etching processed by LAM Rainbow Etchers. Due to physical constraints we consider building an empirical neural network model using one lot of data which usually contains 24 wafers. Using the existence result of feedforward networks as universal approximators, we experimentally developed different network structures as models of the etching process under investigation. Our results are built upon extensive simulations on different lots of the process. The same modeling idea is also extended to use the network model to predict the end point detection signal prior the process of one wafer.",

author = "Jennie Si and Tseng, {Yuan Ling} and Mike Clayton and Steve Felker and Bob Yoo and Jim Martinez and Jim Durham and Kim Dang",

year = "1997",

language = "English (US)",

pages = "347--352",

booktitle = "IEEE Symposium on Emerging Technologies & Factory Automation, ETFA",

publisher = "IEEE",

note = "Proceedings of the 1997 IEEE 6th International Conference on Emerging Technologies and Factory Automation, ETFA'97 ; Conference date: 09-09-1997 Through 12-09-1997",

}

TY - GEN

T1 - Real time plasma etch process modeling by neural networks

AU - Si, Jennie

AU - Tseng, Yuan Ling

AU - Clayton, Mike

AU - Felker, Steve

AU - Yoo, Bob

AU - Martinez, Jim

AU - Durham, Jim

AU - Dang, Kim

PY - 1997

Y1 - 1997

N2 - In the present paper we address the problem of control relevant process modeling from production data for the N-Well Reactive Ion Etching processed by LAM Rainbow Etchers. Due to physical constraints we consider building an empirical neural network model using one lot of data which usually contains 24 wafers. Using the existence result of feedforward networks as universal approximators, we experimentally developed different network structures as models of the etching process under investigation. Our results are built upon extensive simulations on different lots of the process. The same modeling idea is also extended to use the network model to predict the end point detection signal prior the process of one wafer.

AB - In the present paper we address the problem of control relevant process modeling from production data for the N-Well Reactive Ion Etching processed by LAM Rainbow Etchers. Due to physical constraints we consider building an empirical neural network model using one lot of data which usually contains 24 wafers. Using the existence result of feedforward networks as universal approximators, we experimentally developed different network structures as models of the etching process under investigation. Our results are built upon extensive simulations on different lots of the process. The same modeling idea is also extended to use the network model to predict the end point detection signal prior the process of one wafer.

UR - http://www.scopus.com/inward/record.url?scp=0030710315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030710315&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030710315

SP - 347

EP - 352

BT - IEEE Symposium on Emerging Technologies & Factory Automation, ETFA

PB - IEEE

CY - Piscataway, NJ, United States

T2 - Proceedings of the 1997 IEEE 6th International Conference on Emerging Technologies and Factory Automation, ETFA'97

Y2 - 9 September 1997 through 12 September 1997

ER -

Real time plasma etch process modeling by neural networks

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this