{"id":{"repo_id":"uthm","oai_identifier":"oai:eprints.uthm.edu.my:1531"},"canonical_url":"https://search.dev.ndltd.org/etd/uthm/oai:eprints.uthm.edu.my:1531","repository":{"repo_id":"uthm","name":"Universiti Tun Hussein Onn Malaysia","base_url":"http://eprints.uthm.edu.my/cgi/oai2"},"display":{"title":"Study of artificial neural network scheme application in manufacturing industry for monitoring-diagnosis bivariate process variation","abstract":"In manufacturing industries, process variation is known to be a major source of poor quality. As such, process monitoring and diagnosis is critical towards continuous quality improvement. This becomes more challenging when involving two or more correlated variables (multivariate). Process monitoring refers to the identification of process status either it is running within a statistically in-control or out-of-control condition, whereas process diagnosis refers to the identification of the source variables of out-of-control process. The traditional statistical process control (SPC) charting schemes are known to be effective in monitoring aspect. Nevertheless, they are lack of diagnosis. In recent years, the artificial neural network (ANN) based pattern recognition schemes have been developed for solving this issue. The existing schemes are mainly designed for dealing with fully completed process data streams. In practice, however, there are cases that observation data are incomplete due to measurement error. In this research, an ensemble (combined) ANN model pattern recognizer will be investigated for recognizing data streams process. Each model consists of different input representation, namely, raw data and statistical features. The raw data of representation generate by manufacturing industry as a real data. The proposed ensemble ANN scheme would provide better perspective in this research area.","abstract_html":"In manufacturing industries, process variation is known to be a major source of poor quality. As such, process monitoring and diagnosis is critical towards continuous quality improvement. This becomes more challenging when involving two or more correlated variables (multivariate). Process monitoring refers to the identification of process status either it is running within a statistically in-control or out-of-control condition, whereas process diagnosis refers to the identification of the source variables of out-of-control process. The traditional statistical process control (SPC) charting schemes are known to be effective in monitoring aspect. Nevertheless, they are lack of diagnosis. In recent years, the artificial neural network (ANN) based pattern recognition schemes have been developed for solving this issue. The existing schemes are mainly designed for dealing with fully completed process data streams. In practice, however, there are cases that observation data are incomplete due to measurement error. In this research, an ensemble (combined) ANN model pattern recognizer will be investigated for recognizing data streams process. Each model consists of different input representation, namely, raw data and statistical features. The raw data of representation generate by manufacturing industry as a real data. The proposed ensemble ANN scheme would provide better perspective in this research area.","abstract_has_math":false,"creators":["Majid, Mariam"],"institution":"Universiti Tun Hussein Onn Malaysia","degree_name":"mphil","degree_level":"masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-12","date_published":"2014-12","updated_at":"2026-07-24T05:48:31Z","subjects":["TS Manufactures","TS155-194 Production management. Operations management"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Majid, Mariam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-12"]},{"key":"dc:date.issued","label":"Date","values":["2014-12"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Fakulti Kejuruteraan Mekanikal dan Pembuatan"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Universiti Tun Hussein Onn Malaysia"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://eprints.uthm.edu.my/1531/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["masters"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["mphil"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["TS Manufactures","TS155-194 Production management. Operations management"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://eprints.uthm.edu.my/1531/1/24p%20MARIAM%20MAJID.pdf","http://eprints.uthm.edu.my/1531/2/MARIAM%20MAJID%20COPYRIGHT%20DECLARATION.pdf","http://eprints.uthm.edu.my/1531/3/MARIAM%20MAJID%20WATERMARK.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In manufacturing industries, process variation is known to be a major source of poor quality. As such, process monitoring and diagnosis is critical towards continuous quality improvement. This becomes more challenging when involving two or more correlated variables (multivariate). Process monitoring refers to the identification of process status either it is running within a statistically in-control or out-of-control condition, whereas process diagnosis refers to the identification of the source variables of out-of-control process. The traditional statistical process control (SPC) charting schemes are known to be effective in monitoring aspect. Nevertheless, they are lack of diagnosis. In recent years, the artificial neural network (ANN) based pattern recognition schemes have been developed for solving this issue. The existing schemes are mainly designed for dealing with fully completed process data streams. In practice, however, there are cases that observation data are incomplete due to measurement error. In this research, an ensemble (combined) ANN model pattern recognizer will be investigated for recognizing data streams process. Each model consists of different input representation, namely, raw data and statistical features. The raw data of representation generate by manufacturing industry as a real data. The proposed ensemble ANN scheme would provide better perspective in this research area."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Study of artificial neural network scheme application in manufacturing industry for monitoring-diagnosis bivariate process variation"]}]}],"canonical_facts":{"dc:creator":["Majid, Mariam"],"dc:date":["2014-12"],"dc:date.issued":["2014-12"],"dc:description.abstract":["In manufacturing industries, process variation is known to be a major source of poor quality. As such, process monitoring and diagnosis is critical towards continuous quality improvement. This becomes more challenging when involving two or more correlated variables (multivariate). Process monitoring refers to the identification of process status either it is running within a statistically in-control or out-of-control condition, whereas process diagnosis refers to the identification of the source variables of out-of-control process. The traditional statistical process control (SPC) charting schemes are known to be effective in monitoring aspect. Nevertheless, they are lack of diagnosis. In recent years, the artificial neural network (ANN) based pattern recognition schemes have been developed for solving this issue. The existing schemes are mainly designed for dealing with fully completed process data streams. In practice, however, there are cases that observation data are incomplete due to measurement error. In this research, an ensemble (combined) ANN model pattern recognizer will be investigated for recognizing data streams process. Each model consists of different input representation, namely, raw data and statistical features. The raw data of representation generate by manufacturing industry as a real data. The proposed ensemble ANN scheme would provide better perspective in this research area."],"dc:format":["text"],"dc:identifier.uri":["http://eprints.uthm.edu.my/1531/1/24p%20MARIAM%20MAJID.pdf","http://eprints.uthm.edu.my/1531/2/MARIAM%20MAJID%20COPYRIGHT%20DECLARATION.pdf","http://eprints.uthm.edu.my/1531/3/MARIAM%20MAJID%20WATERMARK.pdf"],"dc:language":["en"],"dc:publisher.department":["Fakulti Kejuruteraan Mekanikal dan Pembuatan"],"dc:publisher.institution":["Universiti Tun Hussein Onn Malaysia"],"dc:relation.isreferencedby":["http://eprints.uthm.edu.my/1531/"],"dc:subject":["TS Manufactures","TS155-194 Production management. Operations management"],"dc:title":["Study of artificial neural network scheme application in manufacturing industry for monitoring-diagnosis bivariate process variation"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["masters"],"dc:type.qualificationname":["mphil"]},"updated_at":"2026-07-24T05:48:31Z"}