A Predictive Maintenance strategy for a complex machine requires a sophisticated and non-trivial analytical stage to provide accurate and trusted predictions. It must be planned and carried out carefully to maximise the information extracted from available data. The SERENA project provided an excellent methodological framework and a solid technical and software foundation to deliver a robust and applicable Predictive Maintenance solution for the White Goods industry. The proposed data-driven methodology was applied on a real use case, that is, estimating the degradation trend of industrial foaming machines and predicting their remaining useful life. The models were built based on historical data and are applied in real-time adjourning their predictions every time new data are collected. The results are promising and highlight how the proposed methodology can be used to achieve a fairly accurate estimate of machinery degradation and plan maintenance interventions accordingly, with significant savings in terms of costs and time.
Estimating Remaining Useful Life: A Data-Driven Methodology for the White Goods Industry / Petrali, Pierluigi; Cerquitelli, Tania; Bethaz, Paolo; Morra, Lia; Nikolakis, Nikolaos; DE VIZIA, Claudia; Macii, Enrico (INFORMATION FUSION AND DATA SCIENCE). - In: Predictive Maintenance in Smart Factories / Cerquitelli T., Nikolakis N., O’Mahony N., Macii E., Ippolito M., Makris S.. - STAMPA. - [s.l] : Springer, 2021. - ISBN 978-981-16-2939-6. - pp. 149-164 [10.1007/978-981-16-2940-2_7]
Estimating Remaining Useful Life: A Data-Driven Methodology for the White Goods Industry
Tania Cerquitelli;Paolo Bethaz;Lia Morra;Claudia De Vizia;Enrico Macii
2021
Abstract
A Predictive Maintenance strategy for a complex machine requires a sophisticated and non-trivial analytical stage to provide accurate and trusted predictions. It must be planned and carried out carefully to maximise the information extracted from available data. The SERENA project provided an excellent methodological framework and a solid technical and software foundation to deliver a robust and applicable Predictive Maintenance solution for the White Goods industry. The proposed data-driven methodology was applied on a real use case, that is, estimating the degradation trend of industrial foaming machines and predicting their remaining useful life. The models were built based on historical data and are applied in real-time adjourning their predictions every time new data are collected. The results are promising and highlight how the proposed methodology can be used to achieve a fairly accurate estimate of machinery degradation and plan maintenance interventions accordingly, with significant savings in terms of costs and time.File | Dimensione | Formato | |
---|---|---|---|
491743_1_En_7_Chapter_Proof.pdf
non disponibili
Descrizione: proof
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
669.3 kB
Formato
Adobe PDF
|
669.3 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2915154