Using an autoencoder in the design of an anomaly detector for smart manufacturing

•Our approach generality provides great effectiveness with different case studies.•Our approach provides smaller error and computational cost w.r.t. isolation forest.•The discriminator provides automatic and reliable anomaly score post-processing.•The discriminator improves the accuracy and precisio...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Pattern recognition letters Ročník 136; s. 272 - 278
Hlavní autori:	Alfeo, Antonio L., Cimino, Mario G.C.A., Manco, Giuseppe, Ritacco, Ettore, Vaglini, Gigliola
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Amsterdam Elsevier B.V 01.08.2020 Elsevier Science Ltd
Predmet:	Anomalies Anomaly detection Anomaly discriminator Artificial neural networks Autoencoder Fault detection Interpretable machine learning Laundry Learning algorithms Machine learning Manufacturing Neural networks Power consumption Problem solving Smart industry Smart manufacturing Time series Vibrations Fault detection Autoencoder Smart industry Interpretable machine learning Anomaly discriminator Anomaly detection Smart manufacturing
ISSN:	0167-8655, 1872-7344
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	•Our approach generality provides great effectiveness with different case studies.•Our approach provides smaller error and computational cost w.r.t. isolation forest.•The discriminator provides automatic and reliable anomaly score post-processing.•The discriminator improves the accuracy and precision of other approaches. According to the smart manufacturing paradigm, the analysis of assets’ time series with a machine learning approach can effectively prevent unplanned production downtimes by detecting assets’ anomalous operational conditions. To support smart manufacturing operators with no data science background, we propose an anomaly detection approach based on deep learning and aimed at providing a manageable machine learning pipeline and easy to interpret outcome. To do so we combine (i) an autoencoder, a deep neural network able to produce an anomaly score for each provided time series, and (ii) a discriminator based on a general heuristics, to automatically discern anomalies from regular instances. We prove the convenience of the proposed approach by comparing its performances against isolation forest with different case studies addressing industrial laundry assets’ power consumption and bearing vibrations.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	0167-8655 1872-7344
DOI:	10.1016/j.patrec.2020.06.008