In this paper the performances are evaluated of a condition monitoring system for classification of operating statuses of an automatic machine for processing of steel bars, when the characteristics of the system itself are made more and more simple. Standard solutions were adopted in terms of sensors, features and data processing algorithms, in order to achieve information of general applicability. Experimental results show that, if reduction is carried on according to physical and metrological motivations of good practice in condition monitoring, a very acceptable limited reduction of accuracy of results is achieved, even though a remarkable reduction of used resources is realized with reference to the number of sensors and to the data processing load. Guide lines for an effective reduction are also discussed, for purpose of generalizing the proposed solutions.
How simplifying a condition monitoring procedure affects its performances
D'Emilia G.;Gaspari A.;Natale E.
2021-01-01
Abstract
In this paper the performances are evaluated of a condition monitoring system for classification of operating statuses of an automatic machine for processing of steel bars, when the characteristics of the system itself are made more and more simple. Standard solutions were adopted in terms of sensors, features and data processing algorithms, in order to achieve information of general applicability. Experimental results show that, if reduction is carried on according to physical and metrological motivations of good practice in condition monitoring, a very acceptable limited reduction of accuracy of results is achieved, even though a remarkable reduction of used resources is realized with reference to the number of sensors and to the data processing load. Guide lines for an effective reduction are also discussed, for purpose of generalizing the proposed solutions.File | Dimensione | Formato | |
---|---|---|---|
pubblicato.pdf
non disponibili
Tipologia:
Documento in Versione Editoriale
Licenza:
Creative commons
Dimensione
2.35 MB
Formato
Adobe PDF
|
2.35 MB | 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.