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.

摘要

本文介绍了一种新的模型标定方法。模型校准程序应用于水管网进行泄漏检测，并可用于其他逆和模型校准问题。校准过程使用人工神经网络将测量值转换为固定网络。将此技术与使用人工神经网络来预测模型参数的传统策略进行比较。这两种技术在三个日益复杂的网络上进行了比较。第一个是基本的单管网，第二个是使用 EPANET 模拟的数值分配网络，第三个是实验网络。结果表明，新引入的方法优于其他技术。所提出的技术被证明在模型校准方面表现良好。