Please use this identifier to cite or link to this item: http://dspace.ensta.edu.dz/jspui/handle/123456789/551
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLARIBI, Hadjer-
dc.contributor.authorMELIANI, Ouezna-
dc.contributor.authorBELAYADI, Djahida (Directeur de thèse)-
dc.date.accessioned2026-11-08T12:00:15Z-
dc.date.available2026-11-08T12:00:15Z-
dc.date.issued2023-
dc.identifier.urihttp://dspace.ensta.edu.dz/jspui/handle/123456789/551-
dc.descriptionMaster : Programme Complémentaire d'Ingéniorat: Génie industriel : Alger: Ecole Nationale Supérieure des Technologie Avancées: 2023en_US
dc.description.abstractPresently, the realm of research is witnessing a burgeoning interest in the utilization of Deep Learning (DL), a branch of machine learning (ML) and artificial intelligence (AI), within the domain of the Industrial Internet of Things. The prediction of failures of industrial equipment before their occurrence, referred to as Predictive Maintenance (PdM), is also a very trendy topic, primarily driven by its potential for cost-savings and numerous advantages over other maintenance types. DL techniques have the potential to provide significant benefices in the context of PdM applications, mainly with highly complex, non-linear, and unlabeled data in real-world scenarios. However, there are a variety of DL algorithms available, and each each possessing distinct characteristics and can be used in different cases. Therefore, choosing the best DL algorithm to resolve PdM issues is not not trivial. This paper aims to improve the performance of PdM by selecting the most suitable DL algorithms. By conducting a comparative study, three deep learning algorithms were chosen, using the criteria commonly utilized in research articles.en_US
dc.language.isoenen_US
dc.publisherENSTAen_US
dc.subjectDeep Learningen_US
dc.subject4.0en_US
dc.subjectAlgorithm Selectionen_US
dc.subjectNeural Networksen_US
dc.subjectPredictive Maintenanceen_US
dc.titleSelecting an appropriate deep learning algorithm for predictive maintenanceen_US
Appears in Collections:MFE- Génie Industriel (Génie Industriel)

Files in This Item:
File Description SizeFormat 
ART-GI 09-23 MFEART-GI 09-23 - LARIBI HADJER et MELIANI Ouazna.pdfMémoire de Master2.22 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.