Improved Machine Learning for Multiclass Fault Classification in Industrial Processes
<p dir="ltr">Multiclass fault classification in complex processes is challenging due to many classes, nonlinear dynamics, overlapping fault signatures, and expanding fault taxonomies. Traditional machine learning models often struggle in such settings. The goal of this paper is to de...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513521694277632 |
|---|---|
| author | Khaled Dhibi (16891524) |
| author2 | Radhia Fezai (16869888) Nour Basha (21385547) Gasim Ibrahim (17032299) Hanif Ahmed Choudhury (23739939) Mohamed Sufiyan Challiwala (23739942) Byanne Malluhi (22963447) Hazem Nounou (16869900) Nimir Elbashir (5244551) Mohamed Nounou (3489386) |
| author2_role | author author author author author author author author author |
| author_facet | Khaled Dhibi (16891524) Radhia Fezai (16869888) Nour Basha (21385547) Gasim Ibrahim (17032299) Hanif Ahmed Choudhury (23739939) Mohamed Sufiyan Challiwala (23739942) Byanne Malluhi (22963447) Hazem Nounou (16869900) Nimir Elbashir (5244551) Mohamed Nounou (3489386) |
| author_role | author |
| dc.creator.none.fl_str_mv | Khaled Dhibi (16891524) Radhia Fezai (16869888) Nour Basha (21385547) Gasim Ibrahim (17032299) Hanif Ahmed Choudhury (23739939) Mohamed Sufiyan Challiwala (23739942) Byanne Malluhi (22963447) Hazem Nounou (16869900) Nimir Elbashir (5244551) Mohamed Nounou (3489386) |
| dc.date.none.fl_str_mv | 2025-12-19T15:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/access.2025.3633702 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Improved_Machine_Learning_for_Multiclass_Fault_Classification_in_Industrial_Processes/32033976 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Data management and data science Machine learning Mathematical sciences Statistics Anomaly detection Bayesian optimization binary decomposition condition monitoring fault diagnosis feature selection interval-valued data machine learning multiclass classification process monitoring |
| dc.title.none.fl_str_mv | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Multiclass fault classification in complex processes is challenging due to many classes, nonlinear dynamics, overlapping fault signatures, and expanding fault taxonomies. Traditional machine learning models often struggle in such settings. The goal of this paper is to develop a model-agnostic, extensible framework. The proposed methodology aims to boost any base classifier via optimization, interval-based feature selection, and intelligent binary decomposition. By restructuring a multiclass task into hierarchies of binary subproblems and linking each boundary to automatically selected statistical features, the developed method improves diagnostic accuracy and generalization. Experimental results on a large-scale dataset demonstrate improved performance compared to existing methods, achieving a high accuracy rate. Although the approach increases the computation time, the notable improvements in accuracy make the balance between precision and computation time advantageous for real-world use.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3633702" target="_blank">https://dx.doi.org/10.1109/access.2025.3633702</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_d40d87113d36f11f1c477d5ea79923be |
| identifier_str_mv | 10.1109/access.2025.3633702 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/32033976 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Improved Machine Learning for Multiclass Fault Classification in Industrial ProcessesKhaled Dhibi (16891524)Radhia Fezai (16869888)Nour Basha (21385547)Gasim Ibrahim (17032299)Hanif Ahmed Choudhury (23739939)Mohamed Sufiyan Challiwala (23739942)Byanne Malluhi (22963447)Hazem Nounou (16869900)Nimir Elbashir (5244551)Mohamed Nounou (3489386)Information and computing sciencesArtificial intelligenceData management and data scienceMachine learningMathematical sciencesStatisticsAnomaly detectionBayesian optimizationbinary decompositioncondition monitoringfault diagnosisfeature selectioninterval-valued datamachine learningmulticlass classificationprocess monitoring<p dir="ltr">Multiclass fault classification in complex processes is challenging due to many classes, nonlinear dynamics, overlapping fault signatures, and expanding fault taxonomies. Traditional machine learning models often struggle in such settings. The goal of this paper is to develop a model-agnostic, extensible framework. The proposed methodology aims to boost any base classifier via optimization, interval-based feature selection, and intelligent binary decomposition. By restructuring a multiclass task into hierarchies of binary subproblems and linking each boundary to automatically selected statistical features, the developed method improves diagnostic accuracy and generalization. Experimental results on a large-scale dataset demonstrate improved performance compared to existing methods, achieving a high accuracy rate. Although the approach increases the computation time, the notable improvements in accuracy make the balance between precision and computation time advantageous for real-world use.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3633702" target="_blank">https://dx.doi.org/10.1109/access.2025.3633702</a></p>2025-12-19T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3633702https://figshare.com/articles/journal_contribution/Improved_Machine_Learning_for_Multiclass_Fault_Classification_in_Industrial_Processes/32033976CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/320339762025-12-19T15:00:00Z |
| spellingShingle | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes Khaled Dhibi (16891524) Information and computing sciences Artificial intelligence Data management and data science Machine learning Mathematical sciences Statistics Anomaly detection Bayesian optimization binary decomposition condition monitoring fault diagnosis feature selection interval-valued data machine learning multiclass classification process monitoring |
| status_str | publishedVersion |
| title | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| title_full | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| title_fullStr | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| title_full_unstemmed | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| title_short | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| title_sort | Improved Machine Learning for Multiclass Fault Classification in Industrial Processes |
| topic | Information and computing sciences Artificial intelligence Data management and data science Machine learning Mathematical sciences Statistics Anomaly detection Bayesian optimization binary decomposition condition monitoring fault diagnosis feature selection interval-valued data machine learning multiclass classification process monitoring |