No abstract

This article proposes a preliminary diagnostic/prognostic method for the identification of a critical system, undergoing a continuous evolutionary degradation, in a production area, and the determination of the component responsible for its degradation, called the failing element. Using for this, a model based on learning  by multilayer perception (MLP). The purpose of this paper is to provide a modeling approach that makes it possible to determine the level of degradation reached by the system at any given point of time, in a precise way. Thus, the horizon of the failure will be produced with a minimum error compared to the discrete jump model used in the literature. The proposed approach consists of using a neural network with fewer layers and optimal computing time. We performed data learning (tests) in order to illustrate a regression of good correlation of these data (tests) on a centrifugal pump with satisfactory performance parameters and compared it with other commonly used methods.

No abstract

No abstract

In this article, we propose a prognosis model for estimating the remaining useful life (RUL) before the failure of a wear bearing to guide rotating trees in microwaves, in the company called (COSUMAR-Morocco). It is a matter of establishing a model of the degradation envisaged (deterioration by phenomenon of wear) during the favorable mission to the decrease of the reliability over time. The proposed approach is based mainly on the model of behavior of the system under predefined working conditions (Evolution of the degradation). This work consists in establishing an adaptive model for this phenomenon, an empirical law envisaged, a degradation based on the computation of the rate of wear by the formula of ARCHARD. This model helps us predict the remaining useful life (RUL) of the wear bearing before failure, the main objective of this law is to help the maintenance manager to take the action before the failure.