Predictive Maintenance (PdM) is the newest strategy for maintenance management in industrial contexts. It aims to predict the occurrence of a failure to minimize unexpected downtimes and maximize the useful life of components. In data-driven approaches, PdM makes use of Machine Learning (ML) algorithms to extract relevant features from signals, identify and classify possible faults (diagnostics), and predict the components’ remaining useful life (prognostics). The major challenge lies in the high complexity of industrial plants, where both operational conditions change over time and a large number of unknown modes occur. A solution to this problem is offered by novelty detection, where a representation of the machinery normal operating state is learned and compared with online measurements to identify new operating conditions. In this paper, a systematic study of autoencoder-based methods for novelty detection is conducted. We introduce an architecture template, which includes a classification layer to detect and separate the operative conditions, and a localizer for identifying the most influencing signals. Four implementations, with different deep learning models, are described and used to evaluate the approach on data collected from a test rig. The evaluation shows the effectiveness of the architecture and that the autoencoders outperform the current baselines.

Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments / Del Buono, Francesco; Calabrese, Francesca; Baraldi, Andrea; Paganelli, Matteo; Guerra, Francesco. - In: APPLIED SCIENCES. - ISSN 2076-3417. - 12:10(2022), pp. N/A-N/A. [10.3390/app12104931]

Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments

Del Buono, Francesco;Baraldi, Andrea;Paganelli, Matteo;Guerra, Francesco
2022

Abstract

Predictive Maintenance (PdM) is the newest strategy for maintenance management in industrial contexts. It aims to predict the occurrence of a failure to minimize unexpected downtimes and maximize the useful life of components. In data-driven approaches, PdM makes use of Machine Learning (ML) algorithms to extract relevant features from signals, identify and classify possible faults (diagnostics), and predict the components’ remaining useful life (prognostics). The major challenge lies in the high complexity of industrial plants, where both operational conditions change over time and a large number of unknown modes occur. A solution to this problem is offered by novelty detection, where a representation of the machinery normal operating state is learned and compared with online measurements to identify new operating conditions. In this paper, a systematic study of autoencoder-based methods for novelty detection is conducted. We introduce an architecture template, which includes a classification layer to detect and separate the operative conditions, and a localizer for identifying the most influencing signals. Four implementations, with different deep learning models, are described and used to evaluate the approach on data collected from a test rig. The evaluation shows the effectiveness of the architecture and that the autoencoders outperform the current baselines.
2022
13-mag-2022
12
10
N/A
N/A
Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments / Del Buono, Francesco; Calabrese, Francesca; Baraldi, Andrea; Paganelli, Matteo; Guerra, Francesco. - In: APPLIED SCIENCES. - ISSN 2076-3417. - 12:10(2022), pp. N/A-N/A. [10.3390/app12104931]
Del Buono, Francesco; Calabrese, Francesca; Baraldi, Andrea; Paganelli, Matteo; Guerra, Francesco
File in questo prodotto:
File Dimensione Formato  
applsci-12-04931.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 1.9 MB
Formato Adobe PDF
1.9 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1276440
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 10
social impact