Enhanced gate-valve failure detection in water distribution networks using ML and pressure data
Authors:
Open Access
- 1 May 2024
- journal article
- research article
- Published by IWA Publishing in AQUA — Water Infrastructure, Ecosystems and Society
- Vol. 73 (5) , 969-979
Abstract
This study introduces an innovative diagnostic approach for identifying gate-valve failures in water distribution systems. By implementing high-frequency pressure sensors upstream and downstream of the gate valves, we obtained detailed pressure data that are pivotal for fault diagnosis. We explored three distinct machine-learning algorithms and two data-handling techniques to ensure optimal performance in real-world applications. In our methodology, supervised learning algorithms are used to analyze pressure differentials and predict valve behavior. We rigorously tested these algorithms using both raw and feature-engineered data, and the results indicated the effectiveness of the Gaussian-naïve Bayes model with six extracted features. This approach enhances the precision and reliability of diagnostics in water distribution networks.Keywords
Funding Information
- Ministry of the Interior and Safety (20025188)
This publication has 12 references indexed in Scilit:
- Consideration of Temperature Factors when Designing Butterfly Check Valves for Hazardous Production FacilitiesCivil Engineering Journal, 2023
- Operation Simulation for a Check Valve Used in High-Performance SystemsCivil Engineering Journal, 2023
- Multi-objective optimisation of K-shape notch multi-way spool valve using CFD analysis, discharge area parameter model, and NSGA-II algorithmEngineering Applications of Computational Fluid Mechanics, 2023
- Computational fluid dynamics analysis and extended adaptive hybrid functions model-based design optimization of an explosion-proof safety valveEngineering Applications of Computational Fluid Mechanics, 2022
- TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks2020
- Random forest versus logistic regression: a large-scale benchmark experimentBMC Bioinformatics, 2018
- cesium: Open-Source Platform for Time-Series Inference2016
- Occurrence of Transients in Water Distribution NetworksProcedia Engineering, 2015
- Pressure measurements with valve-induced transient flow in water pipelinesUrban Water Journal, 2013
- A time series forest for classification and feature extractionInformation Sciences, 2013