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

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 medium-size network (Limassol) to demonstrate its applicability to larger real-size networks.

[1]  Zheng Yi Wu,et al.  WATER LOSS DETECTION VIA GENETIC ALGORITHM OPTIMIZATION-BASED MODEL CALIBRATION , 2008 .

[2]  Mengjie Zhang,et al.  Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach , 2013, IEEE Transactions on Cybernetics.

[3]  Ahmad Taher Azar,et al.  Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis , 2014, Comput. Methods Programs Biomed..

[4]  Raymond Chiong,et al.  Hybrid filter-wrapper feature selection for short-term load forecasting , 2015, Eng. Appl. Artif. Intell..

[5]  Saurabh Amin,et al.  Sensor placement for fault location identification in water networks: A minimum test cover approach , 2015, Autom..

[6]  Huan Liu,et al.  Feature Selection for Classification: A Review , 2014, Data Classification: Algorithms and Applications.

[7]  Urmila M. Diwekar,et al.  Optimal sensor placement for water distribution network security , 2005 .

[8]  Vicenç Puig,et al.  Leak localization in water distribution networks using a mixed model-based/data-driven approach , 2016 .

[9]  Vicenç Puig,et al.  Sensor Placement for Classifier-Based Leak Localization in Water Distribution Networks , 2017 .

[10]  Ramon Sarrate Estruch,et al.  Sensor placement for leak detection and location in water distribution networks , 2013 .

[11]  Pablo A. Estévez,et al.  A review of feature selection methods based on mutual information , 2013, Neural Computing and Applications.

[12]  Stewart Burn,et al.  An Approach to Leak Detection in Pipe Networks Using Analysis of Monitored Pressure Values by Support Vector Machine , 2009, 2009 Third International Conference on Network and System Security.

[13]  Fatiha Nejjari,et al.  Robust sensor placement for leak location: analysis and design , 2016 .

[14]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Ni-Bin Chang,et al.  Optimal sensor deployment in a large-scale complex drinking water network: Comparisons between a rule-based decision support system and optimization models , 2012, Comput. Chem. Eng..

[16]  Joaquim Blesa Izquierdo,et al.  Optimal pressure sensor placement for leak localisation using a relaxed isolation index : application to the Barcelona water network , 2015 .

[17]  Vicenç Puig,et al.  Leak Localization in Water Distribution Networks using Pressure Residuals and Classifiers , 2015 .

[18]  Vicenç Puig,et al.  Pressure sensor distribution for leak detection in Barcelona water distribution network , 2009 .

[19]  Daniela Fuchs-Hanusch,et al.  Efficient Sensor Placement for Leak Localization Considering Uncertainties , 2016, Water Resources Management.

[20]  Vicenç Puig,et al.  Optimal pressure sensor placement and assessment for leak location using a relaxed isolation index: Application to the Barcelona water network , 2017 .

[21]  Zoran Kapelan,et al.  A review of methods for leakage management in pipe networks , 2010 .

[22]  Fatiha Nejjari,et al.  Optimal pressure sensor placement in water distribution networks minimizing leak location uncertainty , 2015 .

[23]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[24]  U. Diwekar,et al.  Water networks security: A two-stage mixed-integer stochastic program for sensor placement under uncertainty , 2005 .

[25]  Kusum Deep,et al.  A real coded genetic algorithm for solving integer and mixed integer optimization problems , 2009, Appl. Math. Comput..

[26]  Fatiha Nejjari,et al.  Robustness analysis of sensor placement for leak detection and location under uncertain operating conditions , 2014 .

[27]  Wojciech Moczulski,et al.  A Method of Leakage Location in Water Distribution Networks using Artificial Neuro-Fuzzy System , 2015 .

[28]  Byung Ro Moon,et al.  Hybrid Genetic Algorithms for Feature Selection , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Enrique Alba,et al.  Two hybrid wrapper-filter feature selection algorithms applied to high-dimensional microarray experiments , 2016, Appl. Soft Comput..

[30]  Christopher Buckley,et al.  Leak identification in a water distribution network using sparse flow measurements , 2014, Comput. Chem. Eng..

[31]  Vicenc Puig,et al.  Optimal sensor placement for classifier-based leak localization in drinking water networks , 2016, 2016 3rd Conference on Control and Fault-Tolerant Systems (SysTol).

[32]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[33]  Fatiha Nejjari,et al.  Clustering techniques applied to sensor placement for leak detection and location in water distribution networks , 2014, 22nd Mediterranean Conference on Control and Automation.

[34]  Huan Liu,et al.  Efficient Feature Selection via Analysis of Relevance and Redundancy , 2004, J. Mach. Learn. Res..

[35]  Vicenç Puig,et al.  Optimal Sensor Placement for Leak Location in Water Distribution Networks Using Genetic Algorithms , 2013, 2013 Conference on Control and Fault-Tolerant Systems (SysTol).

[36]  Verónica Bolón-Canedo,et al.  A review of feature selection methods on synthetic data , 2013, Knowledge and Information Systems.

[37]  Vicenç Puig,et al.  Leak localization in water distribution networks using Bayesian classifiers , 2017 .

[38]  Urmila M. Diwekar,et al.  Optimal sensor placement with mitigation strategy for water network systems under uncertainty , 2017, Comput. Chem. Eng..

[39]  Andrés R. Masegosa,et al.  Parallel Filter-Based Feature Selection Based on Balanced Incomplete Block Designs , 2016, ECAI.

[40]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[41]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[42]  Stjepan Oreski,et al.  Genetic algorithm-based heuristic for feature selection in credit risk assessment , 2014, Expert Syst. Appl..

[43]  Xin Yao,et al.  A Survey on Evolutionary Computation Approaches to Feature Selection , 2016, IEEE Transactions on Evolutionary Computation.

[44]  Zhang Kanjian,et al.  Mutual information based feature selection for multivariate time series forecasting , 2016, 2016 35th Chinese Control Conference (CCC).

[45]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[46]  Cynthia A. Phillips,et al.  Sensor Placement in Municipal Water Networks , 2003 .

[47]  Gerard Sanz,et al.  Assessment of a Leak Localization Algorithm in Water Networks under Demand Uncertainty , 2015 .

[48]  Jong Min Lee,et al.  Robust leak detection and its localization using interval estimation for water distribution network , 2016, Comput. Chem. Eng..