Abstract
Water losses through leakage represent a significant problem for asset management in water distribution systems. The interpretation of fluid transient pressure waves after the generation of a transient event has been previously used as a technique to locate and characterize leaks, but existing approaches are often both model-driven and limited to the existing knowledge of the system. The potential of using artificial neural networks (ANN) and fluid transient waves to detect, locate, and characterize anomalies in water pipelines has recently been proposed. However, its application in more realistic conditions (e.g., in the presence of background pressure fluctuations) has proven challenging. To address this, one alternative to enhance the response of any nonlinear system includes the introduction of artificial noise, a phenomenon known as stochastic resonance. In this paper, the enhanced detection of leaks in pressurized pipelines via the deployment of stochastic resonance is demonstrated. This paper harnesses this approach by presenting a methodology for the active inspection of pipelines using convolutional neural networks (CNNs). This methodology finds the optimal artificial noise intensity to be introduced into the training dataset for a set of CNNs. The methodology has been applied to a real pipeline in a laboratory at the University of Adelaide in which 14 transient experimental tests were conducted. The results indicated that the addition of noise to the transient pressure head training samples significantly enhances the CNN predictions for the leak location highlighting the existence of an optimum noise intensity to obtain both accurate and reliable results. When trained with the optimum noise intensity, the CNNs were able to locate leaks with an average error of 0.59% in terms of the actual location (in a 37.24-m long pipeline), demonstrating the promising potential of developing techniques based on CNNs to detect leaks and anomalies in water pipelines.
Highlights
Population growth and urban expansion are a challenge for water distribution systems (WDSs) because these systems are responsible for the supply of a vital resource to society
Different methodologies have been used to estimate, monitor, detect, and pinpoint the location of leaks as part of water loss management strategies (Mutikanga et al 2013). One of these methodologies includes the use of fluid transients for leak detection that usually involves the generation of a transient event that travels along the pipeline, allowing its inspection in a way that is similar to the functioning of radar and sonar techniques (Puust et al 2010)
This paper presents a methodology for the active inspection of pipelines as an important contribution to the development of a general technique to exploit convolutional neural networks (CNNs) for leak detection in pipelines using fluid transients
Summary
Population growth and urban expansion are a challenge for water distribution systems (WDSs) because these systems are responsible for the supply of a vital resource to society. In most cases, existing techniques are model-driven Such model-driven approaches usually require extensive and accurate numerical modeling, a priori estimation of certain pipe parameters assuming an intact or original condition, or long processing times to obtain an estimate of the leak characteristics. Frequency response methods have been combined with enumeration techniques for leak detection in pipelines with branches and loops by separating the effect of these known elements on the frequency response of the system and employing a GA-based optimization to find the leak characteristics (Duan 2017) This method has proven successful for a numerical application and has indicated the potential of transient-based methods for operation in more complex systems. Locating the generator close to the end of the pipeline can produce different transient traces for the same leak in terms of the initial pressure increase (Meniconi et al 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
