Pipe bursts in water distribution networks lead to considerable water loss and pose risks of bacteria and pollutant contamination. Pipe burst localisation methods help water service providers repair the burst pipes and restore water supply timely and efficiently. Although methods have been reported on burst detection and localisation, there is a lack of studies on accurate localisation of a burst within a potential district by accessible meters. To address this, a novel Burst Location Identification Framework by Fully-linear DenseNet (BLIFF) is proposed. In this framework, additional pressure meters are placed at limited, optimised places for a short period (minutes to hours) to monitor system behaviour after the burst. The fully-linear DenseNet (FL-DenseNet) newly developed in this study modifies the state-of-the-art deep learning algorithm to effectively extract features in the limited pressure signals for accurate burst localisation. BLIFF was tested on a benchmark network with different parameter settings, which showed that accurate burst localisation results can be achieved even with high model uncertainties. The framework was also applied to a real-life network, in which 57 of the total 58 synthetic bursts in the potential burst district were correctly located when the top five most possible pipes are considered and among them, 37 were successfully located when considering only the top one. Only one failed because of the very small pipe diameter and remote location. Comparisons with DenseNet and the traditional fully linear neural network demonstrate that the framework can effectively narrow the potential burst district to one or several pipes with good robustness and applicability. Codes are available at https://github.com/wizard1203/waternn.

The problem of bursts and leakages in water distribution systems has received significantly increased attention over the past two decades. As they represent both an environmental and an economical issue, how to reduce water loss through bursts and leakages is a challenging task for water utilities. Consequently, various techniques have been developed to detect the location and size of leakages. The methods for bursts (or leaks) detection and location can be broadly divided into two main categories, one based on hardware and the other based on software. Hardware-based methods include (i) acoustic detection methods such as listening rods, leak correlators, leak noise loggers and (ii) non-acoustic detection methods such as gas injection, ground penetrating radar technology and infrared photography. Software-based methods make use of the data collected by real-time pressure and/or flow sensors and several artificial intelligence techniques and statistical data analysis tools, including (i) methods based on numerical modeling methods, such as inverse transient analysis, time domain analysis and frequency domain analysis, and (ii) some non-numerical modeling methods, such as artificial neural networks, Bayesian inference systems, the Golden section method, and Kalman filtering. In this article, the authors describe the methods for pipe network burst location and detection, summarize the features of each method, and propose a suggestion for future work.

In recent studies, deep reinforcement learning (RL) methods have been used for the real‐time control of urban drainage systems (UDSs). However, the training process of an RL agent is computationally expensive since collecting the training data requires multiple simulations of a UDS model. An effective solution to this issue is to replace the original UDS model with an emulator, a simpler model which emulates the specified output of the system. However, the adaptability and interpretability of the existing UDS emulators still require further improvements. To address these challenges, a new emulator with increased adaptability and interpretability, called Koopman emulator, was developed by using the Koopman operator and a deep learning technique in this study. Then, the Koopman emulator was used to replace the UDS model in RL to establish an emulator‐based RL framework for fast and efficient training. This framework was used to train emulator‐based RL agents for flooding and overflow mitigation in a UDS located in Eastern China. Baseline emulators were also employed for comparison. All the methods were evaluated through simulations. The following results were obtained: (a) The Koopman emulator demonstrated a better emulation performance than the baseline emulators. (b) The RL agents based on the Koopman emulator achieved a similar control effect with a faster training process and more efficient data usage compared with the RL agents based on the storm water management model. (c) The uncertainty analysis showed that the RL agents based on the Koopman emulator exhibited acceptable robustness when facing different rainfall events and input perturbations.