An improved features selection approach for control chart patterns recognition.
Control chart patterns (CCPs) are an essential diagnostic tool for process monitoring using statistical process control (SPC). CCPs are widely used to improve production quality in many engineering applications. The principle is to recognize the state of a process, either a stable process or a deter...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Advanced Engineering and Science
2023
|
Subjects: | |
Online Access: | http://eprints.utm.my/104978/1/NorHasrulAkhmalNgadiman2023_AnImprovedFeaturesSelectionApproachforControl.pdf http://eprints.utm.my/104978/ http://dx.doi.org/10.11591/ijeecs.v31.i2.pp734-746 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Malaysia |
Language: | English |
id |
my.utm.104978 |
---|---|
record_format |
eprints |
spelling |
my.utm.1049782024-04-01T06:38:51Z http://eprints.utm.my/104978/ An improved features selection approach for control chart patterns recognition. Alwan, Waseem Ngadiman, Nor Hasrul Akhmal Hassan, Adnan Mohd. Saufi, Mohd. Syahril Ramadhan Ma'aram, Azanizawati Masood, Ibrahim TJ Mechanical engineering and machinery Control chart patterns (CCPs) are an essential diagnostic tool for process monitoring using statistical process control (SPC). CCPs are widely used to improve production quality in many engineering applications. The principle is to recognize the state of a process, either a stable process or a deterioration to an unstable process. It is used to significantly narrow the set of possible assignable causes by shortening the diagnostic process to improve the quality. Machine learning techniques have been widely used in CCPs. Artificial neural networks with multilayer perceptron (ANN-MLP) are one of the standard tools used for this purpose. This paper proposes an improved features selection method to select the best features as input representation for control chart patterns recognition. The results demonstrate that the proposed approach can effectively recognize CCPs even for small patterns with a mean shift of less than 1.5 sigma. The dimensional reduction was achieved by employing Relief, correlation, and Fisher algorithms (RCF) for feature selection and (ANN-MLP) as a classifier (RCF-ANN). This study provides an experimental result that compares the performance before and after dimensional reduction. Institute of Advanced Engineering and Science 2023-08 Article PeerReviewed application/pdf en http://eprints.utm.my/104978/1/NorHasrulAkhmalNgadiman2023_AnImprovedFeaturesSelectionApproachforControl.pdf Alwan, Waseem and Ngadiman, Nor Hasrul Akhmal and Hassan, Adnan and Mohd. Saufi, Mohd. Syahril Ramadhan and Ma'aram, Azanizawati and Masood, Ibrahim (2023) An improved features selection approach for control chart patterns recognition. Indonesian Journal of Electrical Engineering and Computer Science, 31 (2). pp. 734-746. ISSN 2502-4752 http://dx.doi.org/10.11591/ijeecs.v31.i2.pp734-746 DOI: 10.11591/ijeecs.v31.i2.pp734-746 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
TJ Mechanical engineering and machinery |
spellingShingle |
TJ Mechanical engineering and machinery Alwan, Waseem Ngadiman, Nor Hasrul Akhmal Hassan, Adnan Mohd. Saufi, Mohd. Syahril Ramadhan Ma'aram, Azanizawati Masood, Ibrahim An improved features selection approach for control chart patterns recognition. |
description |
Control chart patterns (CCPs) are an essential diagnostic tool for process monitoring using statistical process control (SPC). CCPs are widely used to improve production quality in many engineering applications. The principle is to recognize the state of a process, either a stable process or a deterioration to an unstable process. It is used to significantly narrow the set of possible assignable causes by shortening the diagnostic process to improve the quality. Machine learning techniques have been widely used in CCPs. Artificial neural networks with multilayer perceptron (ANN-MLP) are one of the standard tools used for this purpose. This paper proposes an improved features selection method to select the best features as input representation for control chart patterns recognition. The results demonstrate that the proposed approach can effectively recognize CCPs even for small patterns with a mean shift of less than 1.5 sigma. The dimensional reduction was achieved by employing Relief, correlation, and Fisher algorithms (RCF) for feature selection and (ANN-MLP) as a classifier (RCF-ANN). This study provides an experimental result that compares the performance before and after dimensional reduction. |
format |
Article |
author |
Alwan, Waseem Ngadiman, Nor Hasrul Akhmal Hassan, Adnan Mohd. Saufi, Mohd. Syahril Ramadhan Ma'aram, Azanizawati Masood, Ibrahim |
author_facet |
Alwan, Waseem Ngadiman, Nor Hasrul Akhmal Hassan, Adnan Mohd. Saufi, Mohd. Syahril Ramadhan Ma'aram, Azanizawati Masood, Ibrahim |
author_sort |
Alwan, Waseem |
title |
An improved features selection approach for control chart patterns recognition. |
title_short |
An improved features selection approach for control chart patterns recognition. |
title_full |
An improved features selection approach for control chart patterns recognition. |
title_fullStr |
An improved features selection approach for control chart patterns recognition. |
title_full_unstemmed |
An improved features selection approach for control chart patterns recognition. |
title_sort |
improved features selection approach for control chart patterns recognition. |
publisher |
Institute of Advanced Engineering and Science |
publishDate |
2023 |
url |
http://eprints.utm.my/104978/1/NorHasrulAkhmalNgadiman2023_AnImprovedFeaturesSelectionApproachforControl.pdf http://eprints.utm.my/104978/ http://dx.doi.org/10.11591/ijeecs.v31.i2.pp734-746 |
_version_ |
1797905679510405120 |