Predictive maintenance is a strategic activity in the context of Industry 4.0 in order to maintain a certain level of quality production and to avoid unexpected equipment downtimes. In this scenario, the analysis of IIOT data is necessary to achieve prediction on the future machinery' status. The proposed approach relies on the use of Electronic Design Automation (EDA) techniques mapped from electronic domain to production line domain. These EDA techniques are combined with field knowledge, especially for Predictive Maintenance analysis. This presentation describes a methodology that allows to abstract raw data retrieved from IIOT sensors into a class of severity levels, core of the proposed methodology. For example, a class of severity level is reported in the ISO 10816 standard for vibration measurement, but similar concepts are proposed for other values. The methodology consists of two phases: first of all, traces of the nominal behavior are stored to be reused, then, such raw data are filtered with the nominal behavior and translated into severity levels. Such levels are then embedded into IIoT edge devices through the synthesis of the so-called Predictive Maintenance State Machines. The methodology has been validated on the model of a mechanical transmission system. Furthermore, the correctness of the strategy has been proved by injecting faults on the original model and by exploiting simulation procedures under different operational scenarios. This methodology gives to IIoT sensors their specific role in the software automation pyramid, by abstracting their data into levels used through the formalism of Predictive Maintenance State Machines (PMSM).

Industrial-IoT Data Analysis Exploiting Electronic Design Automation Techniques

Nicola Dall'Ora;Stefano Centomo;Franco Fummi
2019-01-01

Abstract

Predictive maintenance is a strategic activity in the context of Industry 4.0 in order to maintain a certain level of quality production and to avoid unexpected equipment downtimes. In this scenario, the analysis of IIOT data is necessary to achieve prediction on the future machinery' status. The proposed approach relies on the use of Electronic Design Automation (EDA) techniques mapped from electronic domain to production line domain. These EDA techniques are combined with field knowledge, especially for Predictive Maintenance analysis. This presentation describes a methodology that allows to abstract raw data retrieved from IIOT sensors into a class of severity levels, core of the proposed methodology. For example, a class of severity level is reported in the ISO 10816 standard for vibration measurement, but similar concepts are proposed for other values. The methodology consists of two phases: first of all, traces of the nominal behavior are stored to be reused, then, such raw data are filtered with the nominal behavior and translated into severity levels. Such levels are then embedded into IIoT edge devices through the synthesis of the so-called Predictive Maintenance State Machines. The methodology has been validated on the model of a mechanical transmission system. Furthermore, the correctness of the strategy has been proved by injecting faults on the original model and by exploiting simulation procedures under different operational scenarios. This methodology gives to IIoT sensors their specific role in the software automation pyramid, by abstracting their data into levels used through the formalism of Predictive Maintenance State Machines (PMSM).
Predictive maintenance, EDA techniques, IIOT sensors
File in questo prodotto:
File Dimensione Formato  
08791344.pdf

solo utenti autorizzati

Descrizione: Articolo principale
Tipologia: Versione dell'editore
Licenza: Accesso ristretto
Dimensione 6.74 MB
Formato Adobe PDF
6.74 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1011870
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact