Sensor placement for classifier-based leak localization in water distribution networks using hybrid feature selection

Abstract

This paper presents a sensor placement approach for classier-based leak localization in water distribution networks. The proposed method is based on a hybrid feature selection algorithm that combines the use of a lter based on relevancy and redundancy with a wrapper based on genetic algorithms. This algorithm is applied to data generated by hydraulic simulation of the considered water distribution network and it determines the optimal location of a prespecied number of pressure sensors to be used by a leak localization method based on pressure models and classiers proposed in previous works by the authors. The method is applied to a small-size simplied network (Hanoi) to better analyze its computational performance and to a mediumsize network (Limassol) to demonstrate its applicability to larger real-size networks.

Leak Localization in Water Distribution Networks Using Pressure and Data-Driven Classifier Approach

“…The first step of the proposed approach is selecting of the nodes with pressure sensor installed based on the optimal sensor placement strategy generated by [24]. Afterwards, datasets are prepared which include historical data of DMA comprising pressure measurements with corresponding leak location labels and flows at the inlet node.…”

“…Practically, the performance of the leak localization methods is highly sensitive to the numbers of the installed sensors, as well as the placement of these sensors. In order to ensure the optimal performance of the proposed leak localization approaches, in this paper, the sensor placement strategies for a WDN from [24] are used directly without digging into this topic [24][25][26][27]. To estimate the nodes head where sensors are not placed, the Kriging spatial interpolation [20] with hydraulic topology of the network is used, which also generates a perfect no-leak scenario as a reference.…”

Estimation of Node Pressures in Water Distribution Networks by Gaussian Process Regression

“…. , N − d, as described from (12) to (16), were implemented in MATLAB using the built-in matrix operations and subroutines of the Statistics and Machine Learning Toolbox.…”

“…Although some leak location methods don't requiere the knowledge of all the node pressures, e.g. classifiers and other machine learning techniques [13]- [16], it is also essential to estimate the pressure in sensor-free nodes, which could help to determine if a leak or other failure causes that a pressure fall below the minimum or exceed a tolerable value.…”

Simultaneous Sensor Placement and Pressure Reducing Valve Localization for Pressure Control of Water Distribution Systems

“…In addition, an entropy-based approach was proposed for sensor placement in urban water distribution networks for the purpose of efficient and economically viable detection of water loss incidents [18]. In the study of Soldevila et al [19], the sensor placement task was formulated as an optimization problem with binary decision variables solved by a genetic algorithm (GA). Since these methods for sensor placement are mainly for the localization of leakage, they cannot be used for monitoring the real-time pressure aiming at closed-loop pressure control.…”