Simulation assisted leak detection in pressurized systems using machine learning
Authors
Mr. Ameer Mubaslat, Jordan University of Science and Technology, Irbid, Jordan Mr. Ahmad Al Haj, Jordan University of Science and Technology, Irbid, Jordan Prof. Saud Khashan, Jordan University of Science and Technology, Irbid, Jordan
Abstract
In this paper, we utilize Computational Fluid Dynamics (CFD) generated data to train a Recurrent Neural Network (RNN) for detecting leaks in pressurized fluid distribution systems. The obtained results support the validity of implementing Machine Learning techniques in approximating active leak locations in a single pipe setup. This paper also discusses the validity of implementing these techniques for implementation on a fluid distribution network.
Results obtained utilizing the RNN model show an adaptive behavior with the system’s consistent response to different configurations of pipes and boundary conditions. The predictions for the leak localities are more accurate and more economically feasible than those obtained with currently used methods.
1st International Conference on Mechanical Engineering and Technologies (MechaniTek 2020)
Congress
International Congress on Engineering Technologies (EngiTek 2020), 16-18 June 2020, ,
Pages
1-6
Topics
Experimental Fluid Flow and Heat Transfer Molecular Dynamic Simulations
ISSN
2227-331X
DOI
BibTeX
@inproceedings{17EngiTek2020,
title={Simulation assisted leak detection in pressurized systems using machine learning},
author={Ameer Mubaslat, and Ahmad Al Haj, and Saud Khashan},
booktitle={International Congress on Engineering Technologies (EngiTek 2020)},
year={2020},
pages={1-6},
doi={}},
organization={Mosharaka for Research and Studies}
}
