Fault detection and classification in plasma etch equipment for semiconductor manufacturing e-diagnostics

Sang Jeen Hong, Woo Yup Lim, Tae Su Cheong, Gary S. May

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

A method of fault detection and classification (FDC) for semiconductor manufacturing equipment -diagnostics using equipment data is presented. Detecting faulty processes, identifying any anomaly at their onsets, and rapidly classifying the root cause of the fault are crucial for maximizing equipment utilization in current semiconductor manufacturing; however, tool data acquired from production equipment contains much information that is often challenging to analyze due to its sheer volume and complexity. In this paper, modular neural network (MNN) modeling is presented as a method for fault detection modeling in plasma etching. Based on the result from the MNN modeling, a tool data set is grouped according to its related subsystems, and FDC is performed using Dempster-Shafer (D-S) theory to address the uncertainty associated with fault diagnosis. Subsystem level fault detections, such as radio frequency (RF) power source module, RF power bias module, gas delivery module, and process chamber module, are presented by combining related parameters, and successful fault detection is achieved. The evidential reasoning of RF probe is also beneficial for the detection of chamber leak simulation, and the classification of fault is made by further investigating voltage signal of RF probe. Successful fault detection in subsystem level with zero missed alarms was demonstrated using D-S theory of evidential reasoning, and the classification for finding root cause of the fault is presented in the chamber leak fault simulation. We realized that successful FDC can be accomplished by combining various related information and by incorporating engineering expert knowledge.

Original languageEnglish
Article number6074955
Pages (from-to)83-93
Number of pages11
JournalIEEE Transactions on Semiconductor Manufacturing
Volume25
Issue number1
DOIs
Publication statusPublished - 2012 Feb 1
Externally publishedYes

Fingerprint

Plasma diagnostics
fault detection
Fault detection
manufacturing
Semiconductor materials
Plasmas
radio frequencies
modules
chambers
Neural networks
Plasma etching
probes
warning systems
causes
plasma etching
classifying
Failure analysis
delivery
simulation
Gases

Keywords

  • Dempster-Shafer theory
  • fault detection and classification
  • modular neural networks
  • semiconductor equipment diagnosis

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

Fault detection and classification in plasma etch equipment for semiconductor manufacturing e-diagnostics. / Hong, Sang Jeen; Lim, Woo Yup; Cheong, Tae Su; May, Gary S.

In: IEEE Transactions on Semiconductor Manufacturing, Vol. 25, No. 1, 6074955, 01.02.2012, p. 83-93.

Research output: Contribution to journalArticle

@article{9885474d8b8f4f6dbe2d1a1cc3c870ee,
title = "Fault detection and classification in plasma etch equipment for semiconductor manufacturing e-diagnostics",
abstract = "A method of fault detection and classification (FDC) for semiconductor manufacturing equipment -diagnostics using equipment data is presented. Detecting faulty processes, identifying any anomaly at their onsets, and rapidly classifying the root cause of the fault are crucial for maximizing equipment utilization in current semiconductor manufacturing; however, tool data acquired from production equipment contains much information that is often challenging to analyze due to its sheer volume and complexity. In this paper, modular neural network (MNN) modeling is presented as a method for fault detection modeling in plasma etching. Based on the result from the MNN modeling, a tool data set is grouped according to its related subsystems, and FDC is performed using Dempster-Shafer (D-S) theory to address the uncertainty associated with fault diagnosis. Subsystem level fault detections, such as radio frequency (RF) power source module, RF power bias module, gas delivery module, and process chamber module, are presented by combining related parameters, and successful fault detection is achieved. The evidential reasoning of RF probe is also beneficial for the detection of chamber leak simulation, and the classification of fault is made by further investigating voltage signal of RF probe. Successful fault detection in subsystem level with zero missed alarms was demonstrated using D-S theory of evidential reasoning, and the classification for finding root cause of the fault is presented in the chamber leak fault simulation. We realized that successful FDC can be accomplished by combining various related information and by incorporating engineering expert knowledge.",
keywords = "Dempster-Shafer theory, fault detection and classification, modular neural networks, semiconductor equipment diagnosis",
author = "Hong, {Sang Jeen} and Lim, {Woo Yup} and Cheong, {Tae Su} and May, {Gary S.}",
year = "2012",
month = "2",
day = "1",
doi = "10.1109/TSM.2011.2175394",
language = "English",
volume = "25",
pages = "83--93",
journal = "IEEE Transactions on Semiconductor Manufacturing",
issn = "0894-6507",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Fault detection and classification in plasma etch equipment for semiconductor manufacturing e-diagnostics

AU - Hong, Sang Jeen

AU - Lim, Woo Yup

AU - Cheong, Tae Su

AU - May, Gary S.

PY - 2012/2/1

Y1 - 2012/2/1

N2 - A method of fault detection and classification (FDC) for semiconductor manufacturing equipment -diagnostics using equipment data is presented. Detecting faulty processes, identifying any anomaly at their onsets, and rapidly classifying the root cause of the fault are crucial for maximizing equipment utilization in current semiconductor manufacturing; however, tool data acquired from production equipment contains much information that is often challenging to analyze due to its sheer volume and complexity. In this paper, modular neural network (MNN) modeling is presented as a method for fault detection modeling in plasma etching. Based on the result from the MNN modeling, a tool data set is grouped according to its related subsystems, and FDC is performed using Dempster-Shafer (D-S) theory to address the uncertainty associated with fault diagnosis. Subsystem level fault detections, such as radio frequency (RF) power source module, RF power bias module, gas delivery module, and process chamber module, are presented by combining related parameters, and successful fault detection is achieved. The evidential reasoning of RF probe is also beneficial for the detection of chamber leak simulation, and the classification of fault is made by further investigating voltage signal of RF probe. Successful fault detection in subsystem level with zero missed alarms was demonstrated using D-S theory of evidential reasoning, and the classification for finding root cause of the fault is presented in the chamber leak fault simulation. We realized that successful FDC can be accomplished by combining various related information and by incorporating engineering expert knowledge.

AB - A method of fault detection and classification (FDC) for semiconductor manufacturing equipment -diagnostics using equipment data is presented. Detecting faulty processes, identifying any anomaly at their onsets, and rapidly classifying the root cause of the fault are crucial for maximizing equipment utilization in current semiconductor manufacturing; however, tool data acquired from production equipment contains much information that is often challenging to analyze due to its sheer volume and complexity. In this paper, modular neural network (MNN) modeling is presented as a method for fault detection modeling in plasma etching. Based on the result from the MNN modeling, a tool data set is grouped according to its related subsystems, and FDC is performed using Dempster-Shafer (D-S) theory to address the uncertainty associated with fault diagnosis. Subsystem level fault detections, such as radio frequency (RF) power source module, RF power bias module, gas delivery module, and process chamber module, are presented by combining related parameters, and successful fault detection is achieved. The evidential reasoning of RF probe is also beneficial for the detection of chamber leak simulation, and the classification of fault is made by further investigating voltage signal of RF probe. Successful fault detection in subsystem level with zero missed alarms was demonstrated using D-S theory of evidential reasoning, and the classification for finding root cause of the fault is presented in the chamber leak fault simulation. We realized that successful FDC can be accomplished by combining various related information and by incorporating engineering expert knowledge.

KW - Dempster-Shafer theory

KW - fault detection and classification

KW - modular neural networks

KW - semiconductor equipment diagnosis

UR - http://www.scopus.com/inward/record.url?scp=84858385673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858385673&partnerID=8YFLogxK

U2 - 10.1109/TSM.2011.2175394

DO - 10.1109/TSM.2011.2175394

M3 - Article

AN - SCOPUS:84858385673

VL - 25

SP - 83

EP - 93

JO - IEEE Transactions on Semiconductor Manufacturing

JF - IEEE Transactions on Semiconductor Manufacturing

SN - 0894-6507

IS - 1

M1 - 6074955

ER -