Two-Leak Isolation in Water Distribution Networks Based on k-NN and Linear Discriminant Classifiers

被引:4
作者
Rodriguez-Argote, Carlos Andres [1 ]
Begovich-Mendoza, Ofelia [1 ]
Navarro-Diaz, Adrian [2 ]
Santos-Ruiz, Ildeberto [3 ]
Puig, Vicenc [4 ]
Delgado-Aguinaga, Jorge Alejandro [5 ]
机构
[1] Cinvestav Guadalajara, Ctr Invest & Estudios Avanzados, Av Bosque 1145, El Bajio 45019, Zapopan, Mexico
[2] Tecnol Monterrey, Sch Sci & Engn, Av Gen Ramon Corona 2514, Zapopan 45138, Mexico
[3] Tecnol Nacl Mexico, Dynam Diag & Control Grp, IT Tuxtla Gutierrez, TURIX, Carretera Panamer S-N, Tuxtla Gutierrez 29050, Mexico
[4] Univ Politecn Cataluna, Inst Robot & Informat Ind, CSIC UPC, Parc Tecnol Barcelona,C Llorens & Artigas 4-6, Barcelona 08028, Spain
[5] Univ Valle Mexico, CIIDETEC UVM, Ctr Invest Innovac & Desarrollo Tecnol, Tlaquepaque 45604, Mexico
关键词
leak diagnosis; machine learning; k-NN classification; discriminant analysis; water distribution network; LEAK LOCALIZATION; MODEL; PIPELINES; DIAGNOSIS; LOCATION;
D O I
10.3390/w15173090
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In this paper, the two-simultaneous-leak isolation problem in water distribution networks is addressed. This methodology relies on optimal sensor placement together with a leak location strategy using two well-known classifiers: k-NN and discriminant analysis. First, zone segmentation of the water distribution network is proposed, aiming to reduce the computational cost that involves all possible combinations of two-leak scenarios. Each zone is composed of at least two consecutive nodes, which means that the number of zones is at most half the number of nodes. With this segmentation, the leak identification task is to locate the zones where the pair of leaks are occurring. To quantify the uncertainty degree, a relaxation node criterion is used. The simulation results evidenced that the outcomes are accurate in most cases by using one-relaxation-node and two-relaxation-node criteria.
引用
收藏
页数:26
相关论文
共 42 条
[1]  
Alkarkhi AFM, 2019, EASY STATISTICS FOR FOOD SCIENCE WITH R, P161, DOI 10.1016/B978-0-12-814262-2.00010-8
[2]  
Alves D., 2022, P 2 INT JOINT C WAT
[3]   Serious Sensor Placement-Optimal Sensor Placement as a Serious Game [J].
Arbesser-Rastburg, Georg ;
Fuchs-Hanusch, Daniela .
WATER, 2020, 12 (01)
[4]   Supervised Machine Learning Approaches for Leak Localization in Water Distribution Systems: Impact of Complexities of Leak Characteristics [J].
Basnet, Lochan ;
Brill, Downey ;
Ranjithan, Ranji ;
Mahinthakumar, Kumar .
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2023, 149 (08)
[5]  
Carreno-Alvarado E., 2017, P C NUM METH ENG CMN
[6]   Optimal Sensor Placement for Leak Location in Water Distribution Networks using Evolutionary Algorithms [J].
Casillas, Myrna V. ;
Garza-Castanon, Luis E. ;
Puig, Vicenc .
WATER, 2015, 7 (11) :6496-6515
[7]   Model-based leak detection and location in water distribution networks considering an extended-horizon analysis of pressure sensitivities [J].
Casillas Ponce, Myrna V. ;
Garza Castanon, Luis E. ;
Puig Cayuela, Vicenc .
JOURNAL OF HYDROINFORMATICS, 2014, 16 (03) :649-670
[8]   Multiple Leak Detection in Water Distribution Networks Following Seismic Damage [J].
Choi, Jeongwook ;
Jeong, Gimoon ;
Kang, Doosun .
SUSTAINABILITY, 2021, 13 (15)
[9]   Using artificial neural network models to assess water quality in water distribution networks [J].
Cordoba, G. A. Cuesta ;
Tuhovcak, L. ;
Taus, M. .
12TH INTERNATIONAL CONFERENCE ON COMPUTING AND CONTROL FOR THE WATER INDUSTRY, CCWI2013, 2014, 70 :399-408
[10]   EKF-based observers for multi-leak diagnosis in branched pipeline systems [J].
Delgado-Aguinaga, J. A. ;
Santos-Ruiz, I. ;
Besancon, G. ;
Lopez-Estrada, F. R. ;
Puig, V. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2022, 178