The Failure Mode, Effect and Criticality Analysis (FMECA) aims at individuating how a process might fail, estimating the effects of such failures and the related criticalities, in order to improve the reliability of the process. This methodology is surely useful in terms of identification of the actions to implement for avoiding the failures, but it is also important to have a broader knowledge of the environment in which the analysis is performed. Indeed, identifying the occurrence of common factors that may characterize risky situations can represent the key for a further improvement of process’ reliability, allowing the operators to anticipate and avoid hazardous events. In this perspective, this paper proposes an approach to deepen the study of the FMECA’s results through a data mining technique, the Association Rule Mining. The aim of the proposed approach is defining whether hidden relationships among the outcomes of the FMECA methodology exist and how they can affect the normal functioning of the process, also proposing monitoring or corrective strategies. The research approach is also applied to a case study in order to clarify its deployment.
Understanding failure modes, effects and criticality analysis through the association rule mining / Antomarioni, S.; Bevilacqua, M.; Ciarapica, F.; Mazzuto, G.. - In: ...SUMMER SCHOOL FRANCESCO TURCO. PROCEEDINGS. - ISSN 2283-8996. - Volume 2020-September, 2020:(2020). (Intervento presentato al convegno 25th Summer School Francesco Turco, 2020 tenutosi a University of Brescia nel 2020).
Understanding failure modes, effects and criticality analysis through the association rule mining
Antomarioni S.
;Bevilacqua M.;Ciarapica F.;Mazzuto G.
2020-01-01
Abstract
The Failure Mode, Effect and Criticality Analysis (FMECA) aims at individuating how a process might fail, estimating the effects of such failures and the related criticalities, in order to improve the reliability of the process. This methodology is surely useful in terms of identification of the actions to implement for avoiding the failures, but it is also important to have a broader knowledge of the environment in which the analysis is performed. Indeed, identifying the occurrence of common factors that may characterize risky situations can represent the key for a further improvement of process’ reliability, allowing the operators to anticipate and avoid hazardous events. In this perspective, this paper proposes an approach to deepen the study of the FMECA’s results through a data mining technique, the Association Rule Mining. The aim of the proposed approach is defining whether hidden relationships among the outcomes of the FMECA methodology exist and how they can affect the normal functioning of the process, also proposing monitoring or corrective strategies. The research approach is also applied to a case study in order to clarify its deployment.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.