In this paper a methodology for developing predictive maintenance decision support systems based on artificial intelligence will be presented. The formalised methodology is centred on the development of a diagnostic tool capable of drawing conclusions and making predictions about the product state starting from measurements monitored during the product working cycle. All these measurements are collected by sensors already installed on-board the products, meaning that no additional cost is imposed in order to get the desired result. The methodology has been applied to three different test cases in order to test the single macro-phases in which the methodology can be separeted. The cases regard three different products: a home boiler, a fridge and a range of sophisticated milling system. All the tests demonstrated how well the methodology can guide the user in the creation of a powerful predictive maintenance decision support system which proved to significantly outperform the techniques currently used by our application partners to estimate the ageing level of their goods.

Proposal for a Methodology for the Development of Predictive Maintenance Decision Support Systems Based on Artificial Intelligence

CASSINA, JACOPO;TAISCH, MARCO;GEROSA, MARCO
2009-01-01

Abstract

In this paper a methodology for developing predictive maintenance decision support systems based on artificial intelligence will be presented. The formalised methodology is centred on the development of a diagnostic tool capable of drawing conclusions and making predictions about the product state starting from measurements monitored during the product working cycle. All these measurements are collected by sensors already installed on-board the products, meaning that no additional cost is imposed in order to get the desired result. The methodology has been applied to three different test cases in order to test the single macro-phases in which the methodology can be separeted. The cases regard three different products: a home boiler, a fridge and a range of sophisticated milling system. All the tests demonstrated how well the methodology can guide the user in the creation of a powerful predictive maintenance decision support system which proved to significantly outperform the techniques currently used by our application partners to estimate the ageing level of their goods.
2009
Recent Advances in Maintenance and Infrastructure Management
9781848824881
Maintenance management; Product life cycle management
File in questo prodotto:
File Dimensione Formato  
Recent Advances in Maintenance and Infrastructure Management.PDF

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 1.48 MB
Formato Adobe PDF
1.48 MB Adobe PDF   Visualizza/Apri

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/11311/567659
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact