Model calibration to find leaks in water networks by desensitizing measurements to the model parameters using Artificial Neural Networks

ABSTRACT

This paper introduces a new method for model calibration. The model calibration procedure is applied on water networks for leak detection and can be used for other inverse and model calibration problems. The calibration process uses Artificial Neural Networks to transform the measurements to a fixed network. This technique is compared to the conventional strategy where Artificial Neural Networks are used to predict the model parameters. The two techniques are compared on three networks of increasing complexity. The first is a fundamental single pipe network, the second is a numerical distribution network simulated using EPANET and the third is an experimental network. The results show that the newly introduced approach outperforms the other techniques. The presented technique is shown to perform well for the calibration of models.

KEYWORDS:

• Model calibration
• artificial intelligence
• Artificial Neural Networks
• leak detection

Disclosure statement

No potential conflict of interest was reported by the author(s).