Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes
In this study, a system for faults detection using a combination of Support Vector Data Description (SVDD) with metaheuristic algorithms is presented. The presented approach is applied to a real industrial process where the set of measured faults is scarce. The original contribution in this work is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/24/9145 |
| _version_ | 1797543943873757184 |
|---|---|
| author | Jesús Alejandro Navarro-Acosta Irma D. García-Calvillo Vanesa Avalos-Gaytán Edgar O. Reséndiz-Flores |
| author_facet | Jesús Alejandro Navarro-Acosta Irma D. García-Calvillo Vanesa Avalos-Gaytán Edgar O. Reséndiz-Flores |
| author_sort | Jesús Alejandro Navarro-Acosta |
| collection | DOAJ |
| description | In this study, a system for faults detection using a combination of Support Vector Data Description (SVDD) with metaheuristic algorithms is presented. The presented approach is applied to a real industrial process where the set of measured faults is scarce. The original contribution in this work is the industrial context of application and the comparison of swarm intelligence algorithms to optimize the SVDD hyper-parameters. Four recent metaheuristics are compared hereby to solve the corresponding optimization problem in an efficient manner. These optimization techniques are then implemented for fault detection in a multivariate industrial process with non-balanced data. The obtained numerical results seem to be promising when the considered optimization techniques are combined with SVDD. In particular, the Spotted Hyena algorithm outperforms other metaheuristics reaching values of F1 score near 100% in fault detection. |
| first_indexed | 2024-03-10T13:53:07Z |
| format | Article |
| id | doaj.art-cbe452ab5cd242a4b46897b723cedabd |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:53:07Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cbe452ab5cd242a4b46897b723cedabd2023-11-21T01:56:14ZengMDPI AGApplied Sciences2076-34172020-12-011024914510.3390/app10249145Metaheuristics and Support Vector Data Description for Fault Detection in Industrial ProcessesJesús Alejandro Navarro-Acosta0Irma D. García-Calvillo1Vanesa Avalos-Gaytán2Edgar O. Reséndiz-Flores3Research Center on Applied Mathematics, Autonomous University of Coahuila, Prolongación David Berlanga, Edificio S, Primer Piso, Camporredondo, Saltillo 25115, MexicoResearch Center on Applied Mathematics, Autonomous University of Coahuila, Prolongación David Berlanga, Edificio S, Primer Piso, Camporredondo, Saltillo 25115, MexicoResearch Center on Applied Mathematics, Autonomous University of Coahuila, Prolongación David Berlanga, Edificio S, Primer Piso, Camporredondo, Saltillo 25115, MexicoDivision of Postgraduate Studies and Research, Tecnológico Nacional de México/IT de Saltillo. Blvd. Venustiano Carranza 2400, Colonia Tecnológico, Saltillo 25280, MexicoIn this study, a system for faults detection using a combination of Support Vector Data Description (SVDD) with metaheuristic algorithms is presented. The presented approach is applied to a real industrial process where the set of measured faults is scarce. The original contribution in this work is the industrial context of application and the comparison of swarm intelligence algorithms to optimize the SVDD hyper-parameters. Four recent metaheuristics are compared hereby to solve the corresponding optimization problem in an efficient manner. These optimization techniques are then implemented for fault detection in a multivariate industrial process with non-balanced data. The obtained numerical results seem to be promising when the considered optimization techniques are combined with SVDD. In particular, the Spotted Hyena algorithm outperforms other metaheuristics reaching values of F1 score near 100% in fault detection.https://www.mdpi.com/2076-3417/10/24/9145support vector data descriptionmetaheuristicsfault detectionone class classification |
| spellingShingle | Jesús Alejandro Navarro-Acosta Irma D. García-Calvillo Vanesa Avalos-Gaytán Edgar O. Reséndiz-Flores Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes Applied Sciences support vector data description metaheuristics fault detection one class classification |
| title | Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes |
| title_full | Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes |
| title_fullStr | Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes |
| title_full_unstemmed | Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes |
| title_short | Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes |
| title_sort | metaheuristics and support vector data description for fault detection in industrial processes |
| topic | support vector data description metaheuristics fault detection one class classification |
| url | https://www.mdpi.com/2076-3417/10/24/9145 |
| work_keys_str_mv | AT jesusalejandronavarroacosta metaheuristicsandsupportvectordatadescriptionforfaultdetectioninindustrialprocesses AT irmadgarciacalvillo metaheuristicsandsupportvectordatadescriptionforfaultdetectioninindustrialprocesses AT vanesaavalosgaytan metaheuristicsandsupportvectordatadescriptionforfaultdetectioninindustrialprocesses AT edgaroresendizflores metaheuristicsandsupportvectordatadescriptionforfaultdetectioninindustrialprocesses |