Intelligent condition-based maintenance of reactive ion etching process

Nazrul I Shaikh, V. V. Prabhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The semiconductor industry is facing increasing competition; motivating the need for condition-based maintenance in conjunction with process control. Condition-based maintenance can reduce the downtime of expensive equipment, production costs, and improve yield. Moreover, it can potentially reduce operation cost of semiconductor fabs by lowering the number of expensive spare parts that need to be in stock. This paper proposes an intelligent condition-based maintenance approach wherein the operating parameters for the process are selected while being constrained both by the process and maintenance requirements. Reactive ion etcher is selected as the target equipment: it is widely used and is a critical equipment in semiconductor industry. Based on real-time process and equipment condition data, artificial neural networks are used for assessing the current condition of the equipment and predicting the remaining time before the etcher needs to be shut down for maintenance. The proposed data driven approach is specially suited for the semiconductor industry, which relies heavily on statistical techniques for process control and optimization.

Original languageEnglish
Title of host publicationIntelligent Engineering Systems Through Artificial Neural Networks
EditorsC.H. Dagli, A.L. Buczak, J. Ghosh, M. Embrechts, O. Ersoy
Pages927-932
Number of pages6
Volume13
StatePublished - Dec 1 2003
Externally publishedYes
EventSmart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Complex Systems and Artificial Life - Proceedings of the Artificial Neural Networks in Engineering Conference - St. Louis, MO., United States
Duration: Nov 2 2003Nov 5 2003

Other

OtherSmart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Complex Systems and Artificial Life - Proceedings of the Artificial Neural Networks in Engineering Conference
CountryUnited States
CitySt. Louis, MO.
Period11/2/0311/5/03

Fingerprint

Reactive ion etching
Semiconductor materials
Process control
Industry
Costs
Neural networks
Ions

ASJC Scopus subject areas

  • Software

Cite this

Shaikh, N. I., & Prabhu, V. V. (2003). Intelligent condition-based maintenance of reactive ion etching process. In C. H. Dagli, A. L. Buczak, J. Ghosh, M. Embrechts, & O. Ersoy (Eds.), Intelligent Engineering Systems Through Artificial Neural Networks (Vol. 13, pp. 927-932)

Intelligent condition-based maintenance of reactive ion etching process. / Shaikh, Nazrul I; Prabhu, V. V.

Intelligent Engineering Systems Through Artificial Neural Networks. ed. / C.H. Dagli; A.L. Buczak; J. Ghosh; M. Embrechts; O. Ersoy. Vol. 13 2003. p. 927-932.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shaikh, NI & Prabhu, VV 2003, Intelligent condition-based maintenance of reactive ion etching process. in CH Dagli, AL Buczak, J Ghosh, M Embrechts & O Ersoy (eds), Intelligent Engineering Systems Through Artificial Neural Networks. vol. 13, pp. 927-932, Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Complex Systems and Artificial Life - Proceedings of the Artificial Neural Networks in Engineering Conference, St. Louis, MO., United States, 11/2/03.
Shaikh NI, Prabhu VV. Intelligent condition-based maintenance of reactive ion etching process. In Dagli CH, Buczak AL, Ghosh J, Embrechts M, Ersoy O, editors, Intelligent Engineering Systems Through Artificial Neural Networks. Vol. 13. 2003. p. 927-932
Shaikh, Nazrul I ; Prabhu, V. V. / Intelligent condition-based maintenance of reactive ion etching process. Intelligent Engineering Systems Through Artificial Neural Networks. editor / C.H. Dagli ; A.L. Buczak ; J. Ghosh ; M. Embrechts ; O. Ersoy. Vol. 13 2003. pp. 927-932
@inproceedings{0fe92cf972c64ef3b598fe39518a5eaf,
title = "Intelligent condition-based maintenance of reactive ion etching process",
abstract = "The semiconductor industry is facing increasing competition; motivating the need for condition-based maintenance in conjunction with process control. Condition-based maintenance can reduce the downtime of expensive equipment, production costs, and improve yield. Moreover, it can potentially reduce operation cost of semiconductor fabs by lowering the number of expensive spare parts that need to be in stock. This paper proposes an intelligent condition-based maintenance approach wherein the operating parameters for the process are selected while being constrained both by the process and maintenance requirements. Reactive ion etcher is selected as the target equipment: it is widely used and is a critical equipment in semiconductor industry. Based on real-time process and equipment condition data, artificial neural networks are used for assessing the current condition of the equipment and predicting the remaining time before the etcher needs to be shut down for maintenance. The proposed data driven approach is specially suited for the semiconductor industry, which relies heavily on statistical techniques for process control and optimization.",
author = "Shaikh, {Nazrul I} and Prabhu, {V. V.}",
year = "2003",
month = "12",
day = "1",
language = "English",
volume = "13",
pages = "927--932",
editor = "C.H. Dagli and A.L. Buczak and J. Ghosh and M. Embrechts and O. Ersoy",
booktitle = "Intelligent Engineering Systems Through Artificial Neural Networks",

}

TY - GEN

T1 - Intelligent condition-based maintenance of reactive ion etching process

AU - Shaikh, Nazrul I

AU - Prabhu, V. V.

PY - 2003/12/1

Y1 - 2003/12/1

N2 - The semiconductor industry is facing increasing competition; motivating the need for condition-based maintenance in conjunction with process control. Condition-based maintenance can reduce the downtime of expensive equipment, production costs, and improve yield. Moreover, it can potentially reduce operation cost of semiconductor fabs by lowering the number of expensive spare parts that need to be in stock. This paper proposes an intelligent condition-based maintenance approach wherein the operating parameters for the process are selected while being constrained both by the process and maintenance requirements. Reactive ion etcher is selected as the target equipment: it is widely used and is a critical equipment in semiconductor industry. Based on real-time process and equipment condition data, artificial neural networks are used for assessing the current condition of the equipment and predicting the remaining time before the etcher needs to be shut down for maintenance. The proposed data driven approach is specially suited for the semiconductor industry, which relies heavily on statistical techniques for process control and optimization.

AB - The semiconductor industry is facing increasing competition; motivating the need for condition-based maintenance in conjunction with process control. Condition-based maintenance can reduce the downtime of expensive equipment, production costs, and improve yield. Moreover, it can potentially reduce operation cost of semiconductor fabs by lowering the number of expensive spare parts that need to be in stock. This paper proposes an intelligent condition-based maintenance approach wherein the operating parameters for the process are selected while being constrained both by the process and maintenance requirements. Reactive ion etcher is selected as the target equipment: it is widely used and is a critical equipment in semiconductor industry. Based on real-time process and equipment condition data, artificial neural networks are used for assessing the current condition of the equipment and predicting the remaining time before the etcher needs to be shut down for maintenance. The proposed data driven approach is specially suited for the semiconductor industry, which relies heavily on statistical techniques for process control and optimization.

UR - http://www.scopus.com/inward/record.url?scp=2442472362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2442472362&partnerID=8YFLogxK

M3 - Conference contribution

VL - 13

SP - 927

EP - 932

BT - Intelligent Engineering Systems Through Artificial Neural Networks

A2 - Dagli, C.H.

A2 - Buczak, A.L.

A2 - Ghosh, J.

A2 - Embrechts, M.

A2 - Ersoy, O.

ER -