Toward Explainable AutoEncoder-Based Diagnosis of Dynamical Systems

Autoencoders have been used widely for diagnosing devices, for example, faults in rotating machinery. However, autoencoder-based approaches lack explainability for their results and can be hard to tune. In this article, we propose an explainable method for applying autoencoders for diagnosis, where...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Algorithms Jg. 16; H. 4; S. 178
1. Verfasser: Provan, Gregory
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.04.2023
Schlagworte:
autoencoder
Behavior
Deep learning
diagnosis
Dynamical systems
Fault diagnosis
Fault location (Engineering)
Machinery
principal angle
Rotating machinery
Semantics
subspace projection
System theory
Ireland
ISSN:1999-4893, 1999-4893
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Autoencoders have been used widely for diagnosing devices, for example, faults in rotating machinery. However, autoencoder-based approaches lack explainability for their results and can be hard to tune. In this article, we propose an explainable method for applying autoencoders for diagnosis, where we use a metric that maximizes the diagnostics accuracy. Since an autoencoder projects the input into a reduced subspace (the code), we define a theoretically well-understood approach, the subspace principal angle, to define a metric over the possible fault labels. We show how this approach can be used for both single-device diagnostics (e.g., faults in rotating machinery) and complex (multi-device) dynamical systems. We empirically validate the theoretical claims using multiple autoencoder architectures.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1999-4893
1999-4893
DOI:10.3390/a16040178