Causality Challenge: Benchmarking relevant signal components for effective monitoring and process control

Michael McCann, Yuhua Li, Liam Maguire, Adrian Johnston

Research output: Contribution to journalArticle

Abstract

A complex modern manufacturing process is normally under consistent surveillance via the monitoring of signals/variables collected from sensors. However, not all of these signals are equally valuable in a specific monitoring system. The measured signals contain a combination of useful information, irrelevant information as well as noise. It is often the case that useful information is buried in the latter two. Engineers typically have a much larger number of signals than are actually required. If we consider each type of signal as a feature, then feature selection may be used to identify the most predictive signals. Once these signals have been identified causal relevance may then be investigated to try and identify the causal features. The Process Engineers may then use these signals to ensure a small scrap rate further downstream in the process, increase the throughput and reduce the per unit production costs. Working in partnership with industry we aim to address this complex problem as part of their process control engineering in the context of wafer fabrication production and enhance current business improvement techniques with the application of causal feature selection as an intelligent systems technique.
LanguageEnglish
Pages277-288
JournalJournal of Machine Learning Research
Volume6
Publication statusPublished - 18 Feb 2010

Fingerprint

Benchmarking
Process control
Feature extraction
Engineers
Monitoring
Intelligent systems
Industry
Throughput
Fabrication
Sensors
Costs

Cite this

@article{f163d641bdb741a485f4498868f114cb,
title = "Causality Challenge: Benchmarking relevant signal components for effective monitoring and process control",
abstract = "A complex modern manufacturing process is normally under consistent surveillance via the monitoring of signals/variables collected from sensors. However, not all of these signals are equally valuable in a specific monitoring system. The measured signals contain a combination of useful information, irrelevant information as well as noise. It is often the case that useful information is buried in the latter two. Engineers typically have a much larger number of signals than are actually required. If we consider each type of signal as a feature, then feature selection may be used to identify the most predictive signals. Once these signals have been identified causal relevance may then be investigated to try and identify the causal features. The Process Engineers may then use these signals to ensure a small scrap rate further downstream in the process, increase the throughput and reduce the per unit production costs. Working in partnership with industry we aim to address this complex problem as part of their process control engineering in the context of wafer fabrication production and enhance current business improvement techniques with the application of causal feature selection as an intelligent systems technique.",
author = "Michael McCann and Yuhua Li and Liam Maguire and Adrian Johnston",
year = "2010",
month = "2",
day = "18",
language = "English",
volume = "6",
pages = "277--288",
journal = "Journal of Machine Learning Research",
issn = "1532-4435",

}

Causality Challenge: Benchmarking relevant signal components for effective monitoring and process control. / McCann, Michael; Li, Yuhua; Maguire, Liam; Johnston, Adrian.

In: Journal of Machine Learning Research, Vol. 6, 18.02.2010, p. 277-288.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Causality Challenge: Benchmarking relevant signal components for effective monitoring and process control

AU - McCann, Michael

AU - Li, Yuhua

AU - Maguire, Liam

AU - Johnston, Adrian

PY - 2010/2/18

Y1 - 2010/2/18

N2 - A complex modern manufacturing process is normally under consistent surveillance via the monitoring of signals/variables collected from sensors. However, not all of these signals are equally valuable in a specific monitoring system. The measured signals contain a combination of useful information, irrelevant information as well as noise. It is often the case that useful information is buried in the latter two. Engineers typically have a much larger number of signals than are actually required. If we consider each type of signal as a feature, then feature selection may be used to identify the most predictive signals. Once these signals have been identified causal relevance may then be investigated to try and identify the causal features. The Process Engineers may then use these signals to ensure a small scrap rate further downstream in the process, increase the throughput and reduce the per unit production costs. Working in partnership with industry we aim to address this complex problem as part of their process control engineering in the context of wafer fabrication production and enhance current business improvement techniques with the application of causal feature selection as an intelligent systems technique.

AB - A complex modern manufacturing process is normally under consistent surveillance via the monitoring of signals/variables collected from sensors. However, not all of these signals are equally valuable in a specific monitoring system. The measured signals contain a combination of useful information, irrelevant information as well as noise. It is often the case that useful information is buried in the latter two. Engineers typically have a much larger number of signals than are actually required. If we consider each type of signal as a feature, then feature selection may be used to identify the most predictive signals. Once these signals have been identified causal relevance may then be investigated to try and identify the causal features. The Process Engineers may then use these signals to ensure a small scrap rate further downstream in the process, increase the throughput and reduce the per unit production costs. Working in partnership with industry we aim to address this complex problem as part of their process control engineering in the context of wafer fabrication production and enhance current business improvement techniques with the application of causal feature selection as an intelligent systems technique.

M3 - Article

VL - 6

SP - 277

EP - 288

JO - Journal of Machine Learning Research

T2 - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

SN - 1532-4435

ER -