Health indicator for machine condition monitoring built in the latent space of a deep autoencoder

The construction of effective health indicators plays a key role in the engineering systems field: they reflect the degradation degree of the system under study, thus providing vital information for critical tasks ranging from anomaly detection to remaining useful life estimation, with benefits such...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Reliability engineering & system safety Jg. 224; S. 108482
Hauptverfasser: González-Muñiz, Ana, Díaz, Ignacio, Cuadrado, Abel A., García-Pérez, Diego
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Barking Elsevier Ltd 01.08.2022
Elsevier BV
Schlagworte:
Anomalies
Anomaly detection
Datasets
Deep autoencoder
Engineering systems
Health indicator
Latent space
Machinery condition monitoring
Maintenance costs
Reconstruction
Reliability engineering
System effectiveness
Latent space
Anomaly detection
Engineering systems
Health indicator
Deep autoencoder
ISSN:0951-8320, 1879-0836
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The construction of effective health indicators plays a key role in the engineering systems field: they reflect the degradation degree of the system under study, thus providing vital information for critical tasks ranging from anomaly detection to remaining useful life estimation, with benefits such as reduced maintenance costs, improved productivity or increased machine availability. The reconstruction error of deep autoencoders has been widely used in the literature for this purpose, but this approach does not fully exploit the hierarchical nature of deep models. Instead, we propose to take advantage of the disentangled representations of data that are available in the latent space of autoencoders, by using the latent reconstruction error as machine health indicator. We have tested our proposal on three different datasets, considering two types of autoencoders (deep autoencoder and variational autoencoder), and comparing its performance with that of state-of-the-art approaches in terms of well-known quality metrics. The results of the research demonstrate the capability of our health indicator to outperform conventional approaches, in the three datasets, and regardless of the type of autoencoder used to generate the residuals. In addition, we provide some intuition on the suitability of latent spaces for the monitoring of machinery condition. •Deep autoencoder is used for condition monitoring in engineering systems.•Health indicator built in the latent space of the autoencoder.•Evidence of the potential of latent spaces for the monitoring of machinery condition.•The proposal has been tested in three different engineering contexts.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0951-8320
1879-0836
DOI:10.1016/j.ress.2022.108482