TY - JOUR
T1 - Failure modeling of water distribution pipelines using meta-learning algorithms
AU - Almheiri, Zainab
AU - Meguid, Mohamed
AU - Zayed, Tarek
N1 - Funding Information:
This research is supported by the Natural Sciences and Engineering Research Council of Canada (NSERC). Financial support provided by McGill-UAE fellowships in Science and Engineering to the first author is highly appreciated.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/10/15
Y1 - 2021/10/15
N2 - Population growth and urbanization worldwide entail the need for continuous renewal plans for urban water distribution networks. Hence, understanding the long-term performance and predicting the service life of water pipelines are essential for facilitating early replacement, avoiding economic losses, and ensuring safe transportation of drinking water from treatment plants to consumers. However, developing a suitable model that can be used for cases where data are insufficient or incomplete remains challenging. Herein, a new advanced meta-learning paradigm based on deep neural networks is introduced. The developed model is used to predict the risk index of pipe failure. The effects of different factors that are considered essential for the deterioration modeling of water pipelines are first examined. The factors include seasonal climatic variation, chlorine content, traffic conditions, pipe material, and the spatial characteristics of water pipes. The results suggest that these factors contribute to estimating the likelihood of failure in water distribution pipelines. The presence of chlorine residual and the number of traffic lanes are the most critical factors, followed by road type, spatial characteristics, month index, traffic type, precipitation, temperature, number of breaks, and pipe depth. The proposed approach can accommodate limited, high-dimensional, and partially observed data and can be applied to any water distribution system.
AB - Population growth and urbanization worldwide entail the need for continuous renewal plans for urban water distribution networks. Hence, understanding the long-term performance and predicting the service life of water pipelines are essential for facilitating early replacement, avoiding economic losses, and ensuring safe transportation of drinking water from treatment plants to consumers. However, developing a suitable model that can be used for cases where data are insufficient or incomplete remains challenging. Herein, a new advanced meta-learning paradigm based on deep neural networks is introduced. The developed model is used to predict the risk index of pipe failure. The effects of different factors that are considered essential for the deterioration modeling of water pipelines are first examined. The factors include seasonal climatic variation, chlorine content, traffic conditions, pipe material, and the spatial characteristics of water pipes. The results suggest that these factors contribute to estimating the likelihood of failure in water distribution pipelines. The presence of chlorine residual and the number of traffic lanes are the most critical factors, followed by road type, spatial characteristics, month index, traffic type, precipitation, temperature, number of breaks, and pipe depth. The proposed approach can accommodate limited, high-dimensional, and partially observed data and can be applied to any water distribution system.
KW - Essential factors
KW - Failure
KW - Meta-learning
KW - Water pipelines
UR - http://www.scopus.com/inward/record.url?scp=85116378078&partnerID=8YFLogxK
U2 - 10.1016/j.watres.2021.117680
DO - 10.1016/j.watres.2021.117680
M3 - Journal article
C2 - 34619610
AN - SCOPUS:85116378078
SN - 0043-1354
VL - 205
JO - Water Research
JF - Water Research
M1 - 117680
ER -