Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Evaluation of ANN model for pipe status assessment in drinking water management

Sörensen, Johanna LU ; Nilsson, Erik LU ; Nilsson, Didrik ; Gröndahl, Ebba LU ; Rehn, David and Giertz, Tommy (2024) In Water Supply 24(5). p.1985-1998
Abstract

Non-revenue water due to pipe leakages presents a significant global challenge, impacting both the economy and environmental sustainability. The current approach to pipe management for water utilities in Sweden is mainly reactive; leaks are repaired when detected, sometimes with large costs if the leakage is extensive and critical. With this study, we want to focus on proactive pipe network management by using an Artificial Neural Network (ANN) model to estimate the probability of leakage in water pipes. The ANN model was trained on leaks that occurred over 10 years. A comparison with leaks reported after the training shows that the model succeeds in identifying groups of pipes with a higher leakage frequency. Evaluation of both new and... (More)

Non-revenue water due to pipe leakages presents a significant global challenge, impacting both the economy and environmental sustainability. The current approach to pipe management for water utilities in Sweden is mainly reactive; leaks are repaired when detected, sometimes with large costs if the leakage is extensive and critical. With this study, we want to focus on proactive pipe network management by using an Artificial Neural Network (ANN) model to estimate the probability of leakage in water pipes. The ANN model was trained on leaks that occurred over 10 years. A comparison with leaks reported after the training shows that the model succeeds in identifying groups of pipes with a higher leakage frequency. Evaluation of both new and historical leaks in four different water pipe networks in Sweden showed that a higher prediction value from the ANN model was linked to a higher occurrence of leakage. This indicates that the ANN model succeeds in identifying some of the combinations of attributes that lead to leakage. An evaluation of the input attributes in the ANN model found that the most important attributes for leakage prediction were pipe material, pipe age, adjacent problems on the pipe stretch, pipe length and pipe dimension.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
AI, artificial neural networks, asset management, pipe renewal, water mains, water supply
in
Water Supply
volume
24
issue
5
pages
14 pages
publisher
IWA Publishing
external identifiers
  • scopus:85195029740
ISSN
1606-9749
DOI
10.2166/ws.2024.104
project
RörANN – a smart artificial neural network modelfor minimizing leakages in water distributionsystems
language
English
LU publication?
yes
id
1e27d423-0102-4bf1-a31b-fda9a5c8b152
date added to LUP
2024-09-04 13:25:25
date last changed
2024-10-09 15:56:57
@article{1e27d423-0102-4bf1-a31b-fda9a5c8b152,
  abstract     = {{<p>Non-revenue water due to pipe leakages presents a significant global challenge, impacting both the economy and environmental sustainability. The current approach to pipe management for water utilities in Sweden is mainly reactive; leaks are repaired when detected, sometimes with large costs if the leakage is extensive and critical. With this study, we want to focus on proactive pipe network management by using an Artificial Neural Network (ANN) model to estimate the probability of leakage in water pipes. The ANN model was trained on leaks that occurred over 10 years. A comparison with leaks reported after the training shows that the model succeeds in identifying groups of pipes with a higher leakage frequency. Evaluation of both new and historical leaks in four different water pipe networks in Sweden showed that a higher prediction value from the ANN model was linked to a higher occurrence of leakage. This indicates that the ANN model succeeds in identifying some of the combinations of attributes that lead to leakage. An evaluation of the input attributes in the ANN model found that the most important attributes for leakage prediction were pipe material, pipe age, adjacent problems on the pipe stretch, pipe length and pipe dimension.</p>}},
  author       = {{Sörensen, Johanna and Nilsson, Erik and Nilsson, Didrik and Gröndahl, Ebba and Rehn, David and Giertz, Tommy}},
  issn         = {{1606-9749}},
  keywords     = {{AI; artificial neural networks; asset management; pipe renewal; water mains; water supply}},
  language     = {{eng}},
  month        = {{05}},
  number       = {{5}},
  pages        = {{1985--1998}},
  publisher    = {{IWA Publishing}},
  series       = {{Water Supply}},
  title        = {{Evaluation of ANN model for pipe status assessment in drinking water management}},
  url          = {{http://dx.doi.org/10.2166/ws.2024.104}},
  doi          = {{10.2166/ws.2024.104}},
  volume       = {{24}},
  year         = {{2024}},
}