Prediction of water main failures with the spatial clustering of breaks

Chen, Thomas Ying‐Jeh; Guikema, Seth D.

doi:10.1016/j.ress.2020.107108

Cited by 35 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, the implementation of artificial intelligence in water asset management planning has gained much attention in the last decade. Specifically, machine learning algorithms have been widely utilized to develop failure prediction models by using system‐specific data, such as pipe attributes, hydraulic condition, maintenance and failure history, combined with other supplemental data, such as climate information, environmental data and other (T. Y. J. Chen et al, 2021; T. Chen & Guikema, 2020; Konstantinou & Stoianov, 2020; Yazdekhasti et al, 2020). This approach is data‐intensive; however, the results are an unbiased evaluation of system‐specific data which provides more reliable results compared to a qualitative model.…”

Section: Risk Assessment Of Water Mainsmentioning

confidence: 99%

“…Specifically, machine learning algorithms have been widely utilized to develop failure prediction models by using system-specific data, such as pipe attributes, hydraulic condition, maintenance and failure history, combined with other supplemental data, such as climate information, environmental data and other (T. Y. J. Chen et al, 2021;T. Chen & Guikema, 2020;Konstantinou & Stoianov, 2020;Yazdekhasti et al, 2020).…”

Section: Article Impact Statementmentioning

confidence: 99%

“…These models are usually built using multi‐criteria decision‐making and generally do not require extensive historical or other system‐related data to obtain a risk metric. Compared to these models, quantitative data‐driven risk models have gained popularity during more recent years due to significant advancements in artificial intelligence models in evaluating probability of failure (T. Y. J. Chen & Guikema, 2020), that combined with a monetized consequence of failure evaluation (Ganjidoost et al, 2019; San Luis et al, 2019) provide a data driven and improved risk assessment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Leveraging risk and data analytics for sustainable management of buried water infrastructure

Ganjidoost¹,

Vladeanu

Daly

2022

AWWA Water Science

View full text Add to dashboard Cite

A proactive and sustainable asset management program is vital for utilities to maintain their capital assets at the required level of service, while ensuring that adequate funds are available for intervening when needed on their riskiest assets. One of the most popular methods for building such programs is by prioritizing capital investments based on the asset's risk of failure, which evaluates its likelihood or probability of failure and impact, or consequence of failure. This paper presents the application of a financial planning analysis using system dynamics to provide insights into quantifying more practical risk avoidance. This is exemplified through a 5-year budgetary planning scenario analysis for a large-sized US water utility to help the utility best plan for short and long-term capital operations and show the value of a data-driven and riskbased decision-making.

show abstract

Section: Risk Assessment Of Water Mainsmentioning

confidence: 99%

Section: Article Impact Statementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging risk and data analytics for sustainable management of buried water infrastructure

Ganjidoost¹,

Vladeanu

Daly

2022

AWWA Water Science

View full text Add to dashboard Cite

show abstract

“…The complicated and heterogeneous structure of the WDNs makes evaluating the effect of a pipe-burst a challenging task. In contrast, the previously developed central sections of the networks became older and more exposed to the randomly appearing pipe bursts, according to the work of [1].…”

Section: Introductionmentioning

confidence: 99%

Isolation Valve Placement Optimization of Water Distribution Networks to Reduce Vulnerability

Wéber

Huzsvár

Hős

2023

Period. Polytech. Mech. Eng.

View full text Add to dashboard Cite

Due to the growing pace of urbanization and the rapid expansion of the population, the utilities nowadays are facing a more challenging task than ever before, to maintain the functionality of their massive Water Distribution Networks. In this paper, three different techniques are presented for the maximization of network robustness against random pipe-bursts. This paper analyses the vulnerability of segments of WDNs from the viewpoint of the consumers that is the product of the failure rate and the relative demand loss. Topological parameters could approximate the vulnerability. During the investigation, 27 real-life WDNs were analyzed from the region of Western Hungary. In two networks, a complete isolation valve replacement optimization is presented using these low-cost topological parameters as fitness functions. It is proved that by rearranging the isolation valves of the WDN, using a standard genetic algorithm and a fast-evaluated fitness function, the nature of the vulnerability distribution can be changed to a more favorable one. This means that it is possible to increase the robustness of a WDN even without using a calibrated hydraulic model; since these topological parameters can be extracted from simple databases.

show abstract

“…Scheidegger et al [1] mention in their conclusions that faults on water pipes may have a spacial dependability and should be incorporated into failure prediction models. Further, Chen and Guikema [17] found that that use of spatial clusters, as an explanatory variable, can improve the accuracy of pipe break machine learning models. To take spacial dependability into account in fault prediction, a suitable segmentation of long transmission mains is needed.…”

Section: Introductionmentioning

confidence: 99%

Pipe Fault Prediction for Water Transmission Mains

Gorenstein

Kalech

Fuchs-Hanusch

et al. 2020

Water

View full text Add to dashboard Cite

Every network of supply waterlines experiences thousands of yearly bursts, breaks, leakages, and other failures. These failures waste a great amount of resources, as not only the waterlines need to be repaired, but also water is wasted and the distribution service is interrupted. For that reason, many water facilities employ proactive maintenance strategies in their networks, where they replace likely-to-fail pipes in advance to prevent the failures. In this paper, we aim to establish a reliable prediction model that can accurately predict faults in waterlines prior to their occurrence. We propose a specific segmentation method for long transmission mains, as well as three data-driven models and one rule-based prediction model. We evaluate a real world waterline network used in Israel, operated by Mekorot company, using three common metrics. The results show that the data-driven algorithms outperform the rule-based model by at least 5% in each of the metrics. Additionally, their prediction becomes more accurate as they are trained with more data, but enhancing these data with geographically related features does not improve the accuracy further.

show abstract

Prediction of water main failures with the spatial clustering of breaks

Cited by 35 publications

References 30 publications

Leveraging risk and data analytics for sustainable management of buried water infrastructure

Leveraging risk and data analytics for sustainable management of buried water infrastructure

Isolation Valve Placement Optimization of Water Distribution Networks to Reduce Vulnerability

Pipe Fault Prediction for Water Transmission Mains

Contact Info

Product

Resources

About