Résumé

Structural failures on the water pipeline network represent 53% of the causes of economic losses. To make the network profitable and minimize these losses, a diagnostic study is carried out based on the theory of conditional probabilities. A Bayesian probabilistic network is developed whose nodes represent the structural failures and their causes. In this study structural failures are considered as undesirable and dreaded events. From this study is easy to state that Bimetallic connections and degradation by aging of joints are the main causes of structural failures. An action plan is also determined from the inference in the developed Bayesian network. Actions are either: corrective actions, control and inspection actions, surveillance and monitoring. To show the effectiveness of the proposed tool, a case study on a water pipeline network is carried out. The actions taken in this paper\'s case study are: Remove or avoid metallic connections and Replace and repair joints, which represent mainly corrective actions. Other more complex probabilistic models will be developed in future work in order to take all failures on the water pipeline network.

Information

Item Type:	Conference
Divisions:	» Laboratoire de Recherche en Électromécanique et Sûreté de Fonctionnement » Faculté des Sciences et de la Technologie
ePrint ID:	4715
Date Deposited:	2023-12-15
Further Information:	Google Scholar
URI:	https://www.univ-soukahras.dz/fr/publication/article/4715

BibTex