Case Study for Predicting Failures in Water Supply Networks Using Neural Networks

被引:1
|
作者
de Sousa Medeiros, Viviano [1 ]
dos Santos, Moises Dantas [2 ]
Brito, Alisson Vasconcelos [3 ]
机构
[1] Univ Fed Paraiba, Ctr Technol, Grad Program Mech Engn, TRIL Lab, BR-58058600 Joao Pessoa, Brazil
[2] Univ Fed Paraiba, Ctr Informat, Sci Comp Dept, TRIL Lab, BR-58058600 Joao Pessoa, Brazil
[3] Univ Fed Paraiba, Ctr Informat, Sci Comp Dept, LASER Lab, BR-58058600 Joao Pessoa, Brazil
关键词
fault prediction; water supply networks; machine learning; predictive modeling; infrastructure management; MODELS; RISK;
D O I
10.3390/w16101455
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study deals with the prediction of recurring failures in water supply networks, a complex and costly task, but essential for the effective maintenance of these vital infrastructures. Using historical failure data provided by Companhia de & Aacute;gua e Esgotos da Para & iacute;ba (CAGEPA), the research focuses on predicting the time until the next failure at specific points in the network. The authors divided the failures into two categories: Occurrences of New Faults (ONFs) and Recurrences of Faults (RFs). To perform the predictions, they used predictive models based on machine learning, more specifically on MLP (Multi-Layer Perceptron) neural networks. The investigation unveiled that through the analysis of historical failure data and the consideration of variables including altitude, number of failures on the same street, and days between failures, it is possible to achieve an accuracy greater than 80% in predicting failures within a 90-day interval. This demonstrates the feasibility of using fault history to predict future water supply outages with significant accuracy. These forecasts allow water utilities to plan and optimize their maintenance, minimizing inconvenience and losses. The article contributes significantly to the field of water infrastructure management by proposing the applicability of a data-driven approach in diverse urban settings and across various types of infrastructure networks, including those pertaining to energy or communication. These conclusions underscore the paramount importance of systematic data collection and analysis in both averting failures and optimizing the allocation of resources within water utilities.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Artificial Neural Networks to Forecast Failures in Water Supply Pipes
    Robles-Velasco, Alicia
    Ramos-Salgado, Cristobal
    Munuzuri, Jesus
    Cortes, Pablo
    [J]. SUSTAINABILITY, 2021, 13 (15)
  • [2] NEURAL NETWORKS - A NEW TOOL FOR PREDICTING THRIFT FAILURES
    SALCHENBERGER, LM
    CINAR, EM
    LASH, NA
    [J]. DECISION SCIENCES, 1992, 23 (04) : 899 - 916
  • [3] Predicting water demand of water supply systems in the alpine environment with recurrent neural networks
    Zanfei, Ariele
    Menapace, Andrea
    Brentan, Bruno Melo
    Righetti, Maurizio
    [J]. PROCEEDINGS OF THE 39TH IAHR WORLD CONGRESS, 2022, : 1922 - 1928
  • [4] DETECTION AND CLASSIFICATION OF WATER CHILLER FAILURES USING ARTIFICIAL NEURAL NETWORKS
    Cavalcanti, Andre Fonseca
    de Souza, Andreyvis Silva
    Vieira Pinto, Antonio Paulo
    Wanderley de Oliveira, Lucas Pereira
    Juliao, Rodrigo Bessa
    Leandro Cabral, Marco Antonio
    Matamoros, Efrain Pantaleon
    Rodrigues Seabra, Eurico Augusto
    [J]. 7TH INTERNATIONAL CONFERENCE INTEGRITY-RELIABILITY-FAILURE (IRF2020), 2020, : 91 - 92
  • [5] Predicting energy consumption using artificial neural networks: a case study of the UAE
    Eletter, Shorouq F.
    Elrefae, Ghaleb A.
    Belarbi, Abdelhafid K.
    Abu-Rashid, Jamal
    [J]. ELECTRONIC JOURNAL OF APPLIED STATISTICAL ANALYSIS, 2018, 11 (01) : 137 - 154
  • [6] Identification and Control of Water Supply Reservoirs by using Neural Networks
    Ghasemi, Mahdi Keshavarz
    Shoorehdeli, Mahdi Aliyari
    [J]. 2013 13TH IRANIAN CONFERENCE ON FUZZY SYSTEMS (IFSC), 2013,
  • [7] Towards Predicting Water Levels Using Artificial Neural Networks
    Londhe, Shreenivas N.
    [J]. OCEANS 2009 - EUROPE, VOLS 1 AND 2, 2009, : 1223 - 1228
  • [8] Predicting water saturation using artificial neural networks (ANNS)
    Al-Bulushi, Nabil
    Araujo, Mariela
    Kraaijveld, Martin
    [J]. PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND APPLICATIONS, 2007, : 57 - +
  • [9] Using neural networks to monitor for rare failures
    Hinton, GE
    Frey, BJ
    [J]. 37TH MECHANICAL WORKING AND STEEL PROCESSING CONFERENCE PROCEEDINGS, 1996, 33 : 545 - 548
  • [10] Predicting Hard Disk Failures in Data Centers Using Temporal Convolutional Neural Networks
    Burrello, Alessio
    Pagliari, Daniele Jahier
    Bartolini, Andrea
    Benini, Luca
    Macii, Enrico
    Poncino, Massimo
    [J]. EURO-PAR 2020: PARALLEL PROCESSING WORKSHOPS, 2021, 12480 : 277 - 289