HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES
The main aim of predictive maintenance is to minimize downtime, failure risks and maintenance costs in manufacturing systems. Over the past few years, machine learning methods gained ground with diverse and successful applications in the area of predictive maintenance. This study shows that performi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Association for Knowledge Promotion
2023-06-01
|
| Series: | Applied Computer Science |
| Subjects: | |
| Online Access: | http://www.acs.pollub.pl/index.php?option=com_content&view=article&id=569:hybrid-feature-selection-and-support-vector-machine-framework-for-predicting-maintenance-failures&catid=97:vol-19-no-22023&Itemid=171 |
| _version_ | 1797782614885531648 |
|---|---|
| author | Mouna TARIK Ayoub MNIAI Khalid JEBARI |
| author_facet | Mouna TARIK Ayoub MNIAI Khalid JEBARI |
| author_sort | Mouna TARIK |
| collection | DOAJ |
| description | The main aim of predictive maintenance is to minimize downtime, failure risks and maintenance costs in manufacturing systems. Over the past few years, machine learning methods gained ground with diverse and successful applications in the area of predictive maintenance. This study shows that performing preprocessing techniques such as over¬sampling and feature selection for failure prediction is promising. For instance,
to handle imbalanced data, the SMOTE-Tomek method is used. For feature selection, three different methods can be applied: Recursive Feature Elimination, Random Forest and Variance Threshold. The data considered in this paper for simulation are used in literature. They are used to measure aircraft engine sensors to predict engine failures, while the prediction algorithm used is a Support Vector Machine. The results show that classification accuracy can be significantly boosted by using the preprocessing techniques.
|
| first_indexed | 2024-03-13T00:13:26Z |
| format | Article |
| id | doaj.art-5138918d6b604dd09dc0d9394af1e690 |
| institution | Directory Open Access Journal |
| issn | 1895-3735 2353-6977 |
| language | English |
| last_indexed | 2024-03-13T00:13:26Z |
| publishDate | 2023-06-01 |
| publisher | Polish Association for Knowledge Promotion |
| record_format | Article |
| series | Applied Computer Science |
| spelling | doaj.art-5138918d6b604dd09dc0d9394af1e6902023-07-12T05:51:43ZengPolish Association for Knowledge PromotionApplied Computer Science1895-37352353-69772023-06-0119211212410.35784/acs-2023-18HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURESMouna TARIK 0https://orcid.org/0009-0008-1603-0067Ayoub MNIAI 1Khalid JEBARI 2LMA, FSTT, Abdelmalek Essaadi University, Tetouan, Morocco, tarik.mouna@gmail.com, LMA, FSTT, Abdelmalek Essaadi University, Tetouan, Morocco, ayoubm.m@gmail.comLMA, FSTT, Abdelmalek Essaadi University, Tetouan, Morocco, ayoubm.m@gmail.comThe main aim of predictive maintenance is to minimize downtime, failure risks and maintenance costs in manufacturing systems. Over the past few years, machine learning methods gained ground with diverse and successful applications in the area of predictive maintenance. This study shows that performing preprocessing techniques such as over¬sampling and feature selection for failure prediction is promising. For instance, to handle imbalanced data, the SMOTE-Tomek method is used. For feature selection, three different methods can be applied: Recursive Feature Elimination, Random Forest and Variance Threshold. The data considered in this paper for simulation are used in literature. They are used to measure aircraft engine sensors to predict engine failures, while the prediction algorithm used is a Support Vector Machine. The results show that classification accuracy can be significantly boosted by using the preprocessing techniques. http://www.acs.pollub.pl/index.php?option=com_content&view=article&id=569:hybrid-feature-selection-and-support-vector-machine-framework-for-predicting-maintenance-failures&catid=97:vol-19-no-22023&Itemid=171predictive maintenancemachine learningfeatures selectionsmote-tomeksupport vector machine |
| spellingShingle | Mouna TARIK Ayoub MNIAI Khalid JEBARI HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES Applied Computer Science predictive maintenance machine learning features selection smote-tomek support vector machine |
| title | HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES |
| title_full | HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES |
| title_fullStr | HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES |
| title_full_unstemmed | HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES |
| title_short | HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES |
| title_sort | hybrid feature selection and support vector machine framework for predicting maintenance failures |
| topic | predictive maintenance machine learning features selection smote-tomek support vector machine |
| url | http://www.acs.pollub.pl/index.php?option=com_content&view=article&id=569:hybrid-feature-selection-and-support-vector-machine-framework-for-predicting-maintenance-failures&catid=97:vol-19-no-22023&Itemid=171 |
| work_keys_str_mv | AT mounatarik hybridfeatureselectionandsupportvectormachineframeworkforpredictingmaintenancefailures AT ayoubmniai hybridfeatureselectionandsupportvectormachineframeworkforpredictingmaintenancefailures AT khalidjebari hybridfeatureselectionandsupportvectormachineframeworkforpredictingmaintenancefailures |