Rosa M. Fernández-Cantí - Academia.edu (original) (raw)

Papers by Rosa M. Fernández-Cantí

Water, Jul 19, 2019

This paper presents a new data-driven method for leak localization in water distribution networks... more This paper presents a new data-driven method for leak localization in water distribution networks. The proposed method relies on the use of available pressure measurements in some selected internal network nodes and on the estimation of the pressure at the remaining nodes using Kriging spatial interpolation. Online leak localization is attained by comparing current pressure values with their reference values. Supported by Kriging; this comparison can be performed for all the network nodes, not only for those equipped with pressure sensors. On the one hand, reference pressure values in all nodes are obtained by applying Kriging to measurement data previously recorded under network operation without leaks. On the other hand, current pressure values at all nodes are obtained by applying Kriging to the current measured pressure values. The node that presents the maximum difference (residual) between current and reference pressure values is proposed as a leaky node candidate. Thereafter, a time horizon computation based on Bayesian reasoning is applied to consider the residual time evolution, resulting in an improved leak localization accuracy. As a data-driven approach, the proposed method does not need a hydraulic model; only historical data from normal operation is required. This is an advantage with respect to most data-driven methods that need historical data for the considered leak scenarios. Since, in practice, the obtained leak localization results will strongly depend on the number of available pressure measurements and their location, an optimal sensor placement procedure is also proposed in the paper. Three different case studies illustrate the performance of the proposed methodologies.

IFAC-PapersOnLine, 2018

This paper presents a method for the detection of faults in electrical pumps. The method relies o... more This paper presents a method for the detection of faults in electrical pumps. The method relies on the computation of two features, the pump efficiency and the hydraulic balance, that present reference values during healthy pump operation and change when the pump is affected by a fault. In this paper, the CUSUM Change Detection Test and the Mann-Whitney Change Point Method are proposed as change detection algorithms to process both features. The method has been applied to a real installation with several pumps and the results are reported in the paper.

Applied condition monitoring, 2017

This paper presents a sensor placement approach for classifier-based leak localization in water d... more 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.

This paper presents a sensor placement method for classifier-based leak localization in Water Dis... more This paper presents a sensor placement method for classifier-based leak localization in Water Distribution Networks. The proposed approach consists in applying a Genetic Algorithm to decide the sensors to be used by a classifier (based on the k-Nearest Neighbor approach). The sensors are placed in an optimal way maximizing the accuracy of the leak localization. The results are illustrated by means of the application to the Hanoi District Metered Area and they are compared to the ones obtained by the Exhaustive Search Algorithm. A comparison with the results of a previous optimal sensor placement method is provided as well.

This paper presents a new method for leak localization in Water Distribution Networks that uses a... more This paper presents a new method for leak localization in Water Distribution Networks that uses a model-based approach combined with Bayesian reasoning. Probability density functions in model-based pressure residuals are calibrated off-line for all the possible leak scenarios by using a hydraulic simulator, being leak size uncertainty, demand uncertainty and sensor noise considered. A Bayesian reasoning is applied online to the available residuals to determine the location of leaks present in the Water Distribution Network. A time horizon method combined with the Bayesian reasoning is also proposed to improve the accuracy of the leak localization method. The Hanoi District Metered Area case study is used to illustrate the performance of the proposed approach.

International Journal of Hydrogen Energy, 2016

In this paper, the problem of robust fault diagnosis of proton exchange membrane (PEM) fuel cells... more In this paper, the problem of robust fault diagnosis of proton exchange membrane (PEM) fuel cells is addressed by introducing the Takagi-Sugeno (TS) interval observers that consider uncertainty in a bounded context, adapting TS observers to the so-called interval approach. Design conditions for the TS interval observer based on regional pole placement are also introduced to guarantee the fault detection and isolation (FDI) performance. The fault detection test is based on checking the consistency between the measurements and the output estimations provided by the TS observers. In presence of bounded uncertainty, this check relies on determining if all the measure

Control Engineering Practice, Oct 1, 2016

This paper proposes a new method for leak localization in water distribution networks (WDNs). In ... more This paper proposes a new method for leak localization in water distribution networks (WDNs). In a first stage, residuals are obtained by comparing pressure measurements with the estimations provided by a WDN model. In a second stage, a classifier is applied to the residuals with the aim of determining the leak location. The classifier is trained with data generated by simulation of the WDN under different leak scenarios and uncertainty conditions. The proposed method is tested both using synthetic and experimental data with real WDNs of different sizes. The comparison with the current existing approaches shows a performance improvement.

Journal of Process Control, Jul 1, 2017

This paper presents a method for leak localization in Water Distribution Networks (WDNs) based on... more 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.

Computers & Chemical Engineering, 2018

This paper presents a sensor placement approach for classier-based leak localization in water dis... more 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.

This paper deals with the problem of set-membership identification and fault detection using a Ba... more This paper deals with the problem of set-membership identification and fault detection using a Bayesian framework. The paper presents how the setmembership model estimation problem can be reformulated from a Bayesian viewpoint in order to, firstly, determine the feasible parameter set in the identification stage and, secondly, check the consistency between the measurement data and the model in the fault detection stage. The paper shows that, assuming uniform distributed measurement noise and uniform model prior probability distributions, the Bayesian approach leads to the same feasible parameter set than the well-known set-membership technique based on approximating the feasible parameter set using sets. Additionally, it can deal with models that are nonlinear in the parameters. The single output and multiple output cases are addressed as well. The procedure and results are illustrated by means of the application to a quadruple tank process.

IEEE Transactions on Control Systems and Technology, May 1, 2021

This article presents a new data-driven method for leak localization in water-distribution networ... more This article presents a new data-driven method for leak localization in water-distribution networks (WDNs). The method uses the information provided by a set of pressure sensors installed in some internal network nodes in addition to flow and pressure measurements from inlet nodes. Pressure measurements are recorded under leak-free network operation, and a WDN data-driven model of the pressure at each sensed node is adjusted. The pressure estimation from this model is complemented by a Kriging spatial interpolation technique to estimate the pressure in the nodes that are not sensed, leading to a pressure reference map. Leak localization is based on the comparison of this reference pressure map with the current pressure map that is obtained by applying Kriging directly to the pressure measurements provided by sensors. The key element in this comparison is the use of the Dempster-Shafer theory for reasoning under uncertainty. The successful application of the proposed methodology to two real-data case studies is presented.

Computers & Chemical Engineering, Feb 1, 2022

Annual Reviews in Control, 2015

This paper addresses the problem of fault detection and isolation of wind turbines using a mixed ... more This paper addresses the problem of fault detection and isolation of wind turbines using a mixed Bayesian/Setmembership approach. Modeling errors are assumed to be unknown but bounded, following the set-membership approach. On the other hand, measurement noise is also assumed to be bounded, but following a statistical distribution inside the bounds. To avoid false alarms, the fault detection problem is formulated in a set-membership context. Regarding fault isolation, a new fault isolation scheme that is inspired on the Bayesian fault isolation framework is developed. Faults are isolated by matching the fault detection test results, enhanced by a complementary consistency index that measures the certainty of not being in a fault situation, with the structural information about the faults stored in the theoretical fault signature matrix. The main difference with respect to the classical Bayesian approach is that only models of fault-free behavior are used. Finally, the proposed FDI method is assessed against the wind turbine FDI benchmark proposed in the literature, where a set of realistic fault scenarios in wind turbines are proposed.

Se presenta un laboratorio virtual autonomo y multiplataforma para docencia. La plataforma implem... more Se presenta un laboratorio virtual autonomo y multiplataforma para docencia. La plataforma implementada incluye un servidor con conexion SSH (Secure SHell) y un repositorio separado que contiene los experimentos virtuales. La programacion de los experimentos se ha realizado en Java usando la herramienta EJS (Easy Java Simulation) para entornos graficos y el programa Matlab como motor de calculo externo. El laboratorio virtual contiene experimentos de control a nivel universitario. Se presentan dos ejemplos de aplicacion, en concreto, un levitador magnetico y un sistema de pendulo invertido con carrito. El laboratorio virtual ha sido probado con exito en la formacion de estudiantes de Ingenieria Electronica. Se presentan y comentan los resultados de esta experiencia de e-learning. ABSTRACT An autonomous and multiplatform virtual laboratory for educational purposes is presented. The implemented platform includes a server with a SSH (Secure SHell) connection and a separated repository ...

In this paper, we deal with the problem of obtaining uncertainty models for designing linear loca... more In this paper, we deal with the problem of obtaining uncertainty models for designing linear local robust Hinfin controllers. Some issues about control experiments are exposed and an experimental prototype for uncertainty model validation and robust control design is presented. We consider the set membership and the stochastic embedding approaches to obtain and validate uncertainty models. We apply both techniques to the manipulator local modeling and present the results

This paper deals with the problem of nonlinear set-membership identification and fault detection ... more This paper deals with the problem of nonlinear set-membership identification and fault detection using a Bayesian framework. The paper presents how the set-membership model estimation can be reformulated from a Bayesian viewpoint in order to determine the feasible parameter set and, in a posterior fault detection stage, to check the consistency between the model and the data. The paper shows that the Bayesian approach, assuming uniform distributed measurement noise and flat model prior probability distribution, leads to the same feasible parameter set as the set-membership technique. To illustrate this point a comparison with the subpavings approach is included. Finally, by means of the application to the wind turbine benchmark problem, it is shown how the Bayesian fault detection test works successfully.

21st Mediterranean Conference on Control and Automation, 2013

ABSTRACT

Este articulo describe un sistema para sintonizar filtros de microondas de manera automatica. Se ... more Este articulo describe un sistema para sintonizar filtros de microondas de manera automatica. Se presentan los resultados obtenidos de la sintonizacion automatica de un resonador de microondas mediante un sistema disenado especificamente para tal proposito. Este sistema es extrapolable a filtros de microondas que requieren multiples tornillos de sintonizacion. El sistema disenado se encarga de pedir al usuario los datos necesarios, procesar las medidas realizadas y finalmente hacer girar un motor a pasos para conseguir el ajuste deseado de frecuencia de resonancia. El tornillo de sintonizacion esta unido al motor a pasos, y al girar el motor se hace variar la frecuencia del resonador. Dependiendo del paso del motor se podra conseguir mayor precision en el ajuste, pero lo que se mejora sustancialmente es el tiempo invertido en la sintonia y la velocidad a la que se puede cambiar la respuesta del dispositivo.