Author(s): Ramon Perez; David Alcaraz; Bernardo Morcego; Josep Cuguero

Linked Author(s):

Keywords: Fault prediction; Machine Learning; Predictive Maintenance; Water Distribution Networks

Abstract: The progressive ageing of the water distribution network has significantly increased the frequency of failures in recent years, underscoring the need to develop predictive models capable of anticipating these failures and optimizing maintenance tasks. In this work, we evaluate the performance of various machine learning and artificial intelligence algorithms for early failure detection, incorporating a collaborative data‑sharing approach among operators. The use of data from different sources requires previous treatment for their homogenization. This treatment has been systematized allowing the generalization of the methodology. Three machine learning (ML) algorithms (Logistic Regression (LR), Random Forest (RF) and Artificial Neural Networks (ANN)) have been applied to the different data sets provided by the operators. The performances of these models are compared with state of the art and validated using data from the same company used for training and other companies for assessing their portability.

DOI:

Year: 2026