Search for: All records

Leakages in water distribution networks (WDNs) are estimated to globally cost 39 billion USD per year and cause water and revenue losses, infrastructure degradation, and other cascading effects. Their impacts can be prevented and mitigated with prompt identification and accurate leak localization. In this work, we propose the leakage identification and localization algorithm (LILA), a pressure-based algorithm for data-driven leakage identification and model-based localization in WDNs. First, LILA identifies potential leakages via semi-supervised linear regression of pairwise sensor pressure data and provides the location of their nearest sensors. Second, LILA locates leaky pipes relying on an initial set of candidate pipes and a simulation-based optimization framework with iterative linear and mixed-integer linear programming. LILA is tested on data from the L-Town network devised for the Battle of Leakage Detection and Isolation Methods. Results show that LILA can identify all leakages included in the data set and locate them within a maximum distance of 374 m from their real location. Abrupt leakages are identified immediately or within 2 h, while more time is required to raise alarms on incipient leakages. 

Water distribution systems (WDSs) face a significant challenge in the form of pipe leaks. Pipe leaks can cause loss of a large amount of treated water, leading to pressure loss, increased energy costs, and contamination risks. Locating pipe leaks has been a constant challenge for water utilities and stakeholders due to the underground location of the pipes. Physical methods to detect leaks are expensive, intrusive, and heavily localized. Computational approaches provide an economical alternative to physical methods. Data-driven machine learning-based computational approaches have garnered growing interest in recent years to address the challenge of detecting pipe leaks in WDSs. While several studies have applied machine learning models for leak detection on single pipes and small test networks, their applicability to the real-world WDSs is unclear. Most of these studies simplify the leak characteristics and ignore modeling and measuring device uncertainties, which makes the scalability of their approaches questionable to real-world WDSs. Our study addresses this issue by devising four study cases that account for the realistic leak characteristics (multiple, multi-size, and randomly located leaks) and incorporating noise in the input data to account for the model- and measuring device- related uncertainties. A machine learning-based approach that uses simulated pressure as input to predict both location and size of leaks is proposed. Two different machine learning models: Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN), are trained and tested for the four study cases, and their performances are compared. The precision and recall results for the L-Town network indicate good accuracies for both the models for all study cases, with CNN generally outperforming MLP. 

The primary goal of the project is to leverage recent developments in smart water technologies to detect and reduce water leakages in large water distribution networks with the aid of neural networks. A cost effective non-invasive solution to detect leakages in transmission pipelines is needed by many water utilities as it will lead to significant water savings and reduced pipe breakage frequencies, especially in older infrastructure systems. The eventual goal of the project is to test the ANN model on a real network using field measured pressure and pipe breakage data after tuning and developing the model with simulated data. In this project we propose building a regression model, based on Multi-Layer Perceptron (MLP) algorithm, which is a class of feedforward Artificial Neural Networks (ANNs) to detect the leak locations within a proposed network. The model should be able to learn the structure, i.e. mapping of various leak nodes and sensor nodes in an area, such that it can detect the leak nodes based on the pressure values with significant accuracy.