Optimal sensor placement for classifier-based leak localization in drinking water networks (original) (raw)
Related papers
Sensor Placement for Classifier-Based Leak Localization in Water Distribution Networks
Applied condition monitoring, 2017
This paper presents a sensor placement approach for classifier-based leak localization in water distribution networks. The proposed method is based on a hybrid feature selection algorithm that combines the use of a filter 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 prespecified number of pressure sensors to be used by a leak localization method based on pressure models and classifiers proposed in previous works by the authors. The method is applied to a small-size simplified network (Hanoi) to better analyze its computational performance and to a mediumsize network (Limassol) to demonstrate its applicability to larger real-size networks.
Computers & Chemical Engineering
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.
Optimal Sensor Placement for Leak Location in Water Distribution Networks Using Genetic Algorithms
Sensors, 2013
This paper proposes a new sensor placement approach for leak location in water distribution networks (WDNs). The sensor placement problem is formulated as an integer optimization problem. The optimization criterion consists in minimizing the number of non-isolable leaks according to the isolability criteria introduced. Because of the large size and non-linear integer nature of the resulting optimization problem, genetic algorithms (GAs) are used as the solution approach. The obtained results are compared with a semi-exhaustive search method with higher computational effort, proving that GA allows one to find near-optimal solutions with less computational load. Moreover, three ways of increasing the robustness of the GA-based sensor placement method have been proposed using a time horizon analysis, a distance-based scoring and considering different leaks sizes. A great advantage of the proposed methodology is that it does not depend on the isolation method chosen by the user, as long as it is based on leak sensitivity analysis. Experiments in two networks allow us to evaluate the performance of the proposed approach.
Sensor placement for leak detection and location in water distribution networks
Water Science & Technology: Water Supply, 2014
The performance of a leak detection and location algorithm depends on the set of measurements that are available in the network. This work presents an optimization strategy that maximizes the leak diagnosability performance of the network. The goal is to characterize and determine a sensor configuration that guarantees a maximum degree of diagnosability while the sensor configuration cost satisfies a budgetary constraint. To efficiently handle the complexity of the distribution network an efficient branch and bound search strategy based on a structural model is used. However, in order to reduce even more the size and the complexity of the problem the present work proposes to combine this methodology with clustering techniques. The strategy developed in this work is successfully applied to determine the optimal set of pressure sensors that should be installed to a District Metered Area in the Barcelona Water Distribution Network.
Water, 2015
In this paper, a sensor placement approach to improve the leak location in water distribution networks is proposed when the leak signature space (LSS) method is used. The sensor placement problem is formulated as an integer optimization problem where the criterion to be minimized is the number of overlapping signature domains computed from the original LSS representation. First, a semi-exhaustive search approach based on a lazy evaluation mechanism ensures optimal placement in the case of low complexity scenarios. For more complex cases, a stochastic optimization process is proposed, based on either the genetic algorithms (GAs) or particle swarm optimization (PSO). Experiments on two different networks are used to evaluate the performance of the resolution methods, as well as the efficiency achieved in the leak location when using the sensor placement results.
Leak Localization in Water Distribution Networks using Pressure Residuals and Classifiers
IFAC-PapersOnLine, 2015
In order to take into account the scarcity of the water resource and the increasing of the population, the management of drinking water networks has to be improved with the use of new tools and actions that allows fighting against wasting water. The monitoring of drinking water networks is based on the use of sensors to locate malfunctions (leaks, quality/contamination events, etc.). Practical implementation has to be carried out by optimizing the placement of the number of sensors and improving the detection and localization of malfunctions. Techniques for the detection and localization of leaks have been proposed in the last years based on the evaluation of residuals obtained by means of the comparison between the measurements obtained by the sensors and the values obtained by simulating the water network in a leak free scenario. In this paper, a data-driven approach based on the use of statistical classifiers working in the residual space is proposed for leak localization. The classifiers are trained using leak data scenarios in all the nodes of the network considering uncertainty in demand distribution, additive noise in sensors and leak magnitude. Finally, the proposed approach is tested using the well-known Hanoi network benchmark.
Leak localization in water distribution networks using Bayesian classifiers
Journal of Process Control, 2017
This paper presents a method for leak localization in Water Distribution Networks (WDNs) based on Bayesian classifiers. Probability density functions for pressure residuals are calibrated off-line for all the possible leak scenarios by using a hydraulic simulator, and considering the leak size uncertainty, demand uncertainty and sensor noise. A Bayesian classifier is applied on-line to the computed residuals to determine the location of leaks in the WDN. A time horizon based reasoning combined with the Bayesian classifier is also proposed to improve the localization accuracy. Two case studies based on the Hanoi and the Nova Icària networks are used to illustrate the performance of the proposed approach. Simulation results are presented for the Hanoi case study, whereas results for a real leak scenario are shown for the Nova Icària case study.
Sensor Placement for Leak Location in Water Distribution Networks using the Leak Signature Space
IFAC-PapersOnLine, 2015
In this paper, a sensor placement approach to improve the leak location in water distribution networks is proposed. The sensor placement problem is formulated as an integer optimization problem where the criterion to minimize is the number of overlapping signature domains computed from the leak signature space (LSS) representation. A stochastic optimization process is proposed to solve this problem, based on either a Genetic Algorithms (GA) or a Particle Swarm Optimization (PSO) approach. Experiments on two different DMAs are used to evaluate the performance of the resolution methods as well as the efficiency achieved in the leak location when using the sensor placement results.
Planning of a water distribution network sensors location for a leakage isolation
2014
The paper presents a method of water distribution system sensors placement. Location of sensors depends on the purpose of monitoring of a network. In this paper, this objective has been defined as the ability to detect network failures (leakages). Therefore, the location of monitoring points should be designed so as to maximize the effectiveness of the location method. The main objective of the algorithm deployment of sensors is to find a placement that minimizes the number of components for the largest collection of leakages (faults) with the same signature. The simplest way of determining the best sensors placement is to use an exhaustive search method. However, even a slight increase in the number of possible sensors locations makes exhaustive search very inefficient. Therefore, the selection of sensors placement was performed by optimization using evolutionary genetic algorithm. The computations were performed on the example of the water supply network in Glubczyce town in Polan...
Model-based Monitoring Techniques for Leakage Localization in Distribution Water Networks
Procedia Engineering, 2015
This paper describes an integrated model-based monitoring framework for leakage localization in district-metered areas (DMA) of water distribution networks, which takes advantage of the availability of a hydraulic model of the network. The leakage localization methodology is based on the use of flow and pressure sensors at the DMA inlets and a limited number of pressure sensors deployed inside the DMA. The placement of these sensors has been computed using an optimal sensor placement method based on a Genetic Algorithm optimization, which integrates the direct modelling approach (simulation) used to identify the location of leaks. The application of the resulting monitoring framework in a certain DMA of the Barcelona distribution network is provided and discussed using simulated leakage scenarios. The obtained results show that leakage detection and localization may be performed efficiently, reducing the required time for detection/localization, by following a simple procedure.