Multi-criteria analysis of diagnostic and prognostic models for predictive maintenance
Predictive maintenance has made considerable progress within the framework of Industry 4.0, making this strategy an effective means of monitoring the proper functioning of industrial systems, which helps to make maintenance operations more environmentally friendly, for example reduction of any kind...
Gespeichert in:
Veröffentlicht in: | E3S web of conferences 2022-01, Vol.351, p.1041 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Predictive maintenance has made considerable progress within the framework of Industry 4.0, making this strategy an effective means of monitoring the proper functioning of industrial systems, which helps to make maintenance operations more environmentally friendly, for example reduction of any kind of failure that causes loss of production and energy. This strategy is implemented through a process of collecting data in online or offline mode of the industrial system whose purpose is to monitor and predict its future state. This article first presents the different single-model and multi-model approaches used for diagnostic and prognostic tasks. An analysis of these models is then carried out, based on a multi-criteria comparison, and highlights the performance of machine learning (ML) models in this context of current digitalization. These ML models can be more efficient by combining with the physicsbased models in multi-model approaches. The relevance of the comparative study is argued by criteria impacting performance, effectiveness, efficiency, the possibility of processing heterogeneous data and mutual cooperation between models. Conclusions are then drawn, in order to give a clear vision for the choice of the diagnostic and prognosis approach of predictive maintenance adapted to the industrial system. |
---|---|
ISSN: | 2267-1242 2555-0403 2267-1242 |
DOI: | 10.1051/e3sconf/202235101041 |