Predicting Water Pipe Failures with a Recurrent Neural Hawkes Process Model

Jeroen T. Verheugd, Paulo R. de O. da Costa, Reza Refaei Afshar, Yingqian Zhang, Sjoerd Boersma

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

96 Downloads (Pure)

Abstract

Water distribution networks have shown an increased rate of failure due to material deterioration. In this paper, we apply a Recurrent Neural Hawkes Process model to learn the failure intensity function of water pipes. The failure intensity function is learned based on two components: the base failure rate that is determined by the unique pipe profile attributes, and the effect of past failures. Compared to the existing solutions, our model is able to predict the time to next failure on an individual water pipe level. The learned failure intensity function is used to identify value points in the deterioration process of water pipes that represent their economical end-of-life. We use data from a Dutch water distribution network that consists of 49,600 km of pipelines to test the performance of the proposed model. We have made this dataset available online.
Original languageEnglish
Title of host publication2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PublisherInstitute of Electrical and Electronics Engineers
Pages2628-2633
Number of pages6
ISBN (Electronic)978-1-7281-8526-2
DOIs
Publication statusPublished - 14 Dec 2020
EventIEEE International Conference on Systems, Man, and Cybernetics - Virtual, Toronto, Canada
Duration: 11 Oct 202014 Oct 2020

Conference

ConferenceIEEE International Conference on Systems, Man, and Cybernetics
Abbreviated titleSMC2020
Country/TerritoryCanada
CityToronto
Period11/10/2014/10/20

Keywords

  • Intensity function
  • Point Process
  • Predictive maintenance
  • Recurrent Neural Networks
  • Water pipe failure

Fingerprint

Dive into the research topics of 'Predicting Water Pipe Failures with a Recurrent Neural Hawkes Process Model'. Together they form a unique fingerprint.

Cite this