A priori indicator identification to support predictive maintenance: application to machine tool

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 2, 2018
Thomas Laloix Hai Canh Vu Alexandre VOISIN Eric Romagne Benoît Iung

Abstract

Predictive maintenance requires the identification of the parameters to be monitored and sensors to be implemented on a system. In industrial companies, usually such goal is tackled by implementing sensor and after see if one can extract some indicators related to degradation. The lack of methodology makes the benefits of predictive maintenance to be lower than expected. Indeed, its implementation is done by “the rule of the thumb” using some metrics “a posteriori” in order to show the relevancy of the instrumentation. Hence, a structured approach is required in order to define “a priori” the most suitable indicators to be relevant for degradation monitoring and related instrumentation to be implemented. Thus, the paper presents a methodology based on a coupled approach of FMECA and Hazard Operability analysis (HAZOP) which aim is to contribute to the deployment of predictive maintenance strategies by clearly identify pertinent indicator. This approach is based on the formalization of concepts of knowledge which permit to constitute the first pillars of predictive maintenance approach. The formalization step leads to promote meta-model and reference model of knowledge. The feasibility and the interests of such approach are shown on the case of machine tool GROB G520 located in RENAULT Cléon Factory. It consists in particularizing the reference model proposed to identify automatically and in a more efficient the right indicators/parameters on which the predictive maintenance of this machine tool should be based.

How to Cite

Laloix, T., Vu, H. C., VOISIN, A., Romagne, E., & Iung, B. (2018). A priori indicator identification to support predictive maintenance: application to machine tool. PHM Society European Conference, 4(1). https://doi.org/10.36001/phme.2018.v4i1.420
Abstract 463 | PDF Downloads 418

##plugins.themes.bootstrap3.article.details##

Keywords

predictive maintenance; monitoring; machine tool

Section
Technical Papers