Developing a hierarchical fuzzy rule-based model with weighted linguistic rules: A case study of water pipes condition prediction

Nasser M. Amaitik*, Christopher D. Buckingham

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Assessing the condition of water pipes is a complex task, partly due to scarcity of complete maintenance records and field observations. This makes it harder to identify the factors determining pipe condition and their probabilistic relationships with the deterioration process. A challenge facing water utilities is to find an effective and reliable tool for assessing their pipelines and taking prompt decisions regarding repair and maintenance to extend the service life and keep them safe from sudden failures. This paper presents research on a new fuzzy-based methodology for modelling water pipe condition prediction. It proposes a hierarchical fuzzy rule-based model that uses a simplified and effective method for supporting the elicitation of the fuzzy rules and adapting uncertainty propagation that can be intuitively understood by human experts. The results of applying the model to the water pipes domain shows the plausibility of extending the approach to other knowledge domains based on human expertise.

Original languageEnglish
Title of host publicationProceedings of Computing Conference 2017
PublisherIEEE
Pages30-40
Number of pages11
Volume2018-January
ISBN (Electronic)9781509054435
DOIs
Publication statusPublished - 8 Jan 2018
Event2017 SAI Computing Conference 2017 - London, United Kingdom
Duration: 18 Jul 201720 Jul 2017

Conference

Conference2017 SAI Computing Conference 2017
CountryUnited Kingdom
CityLondon
Period18/07/1720/07/17

Keywords

  • Fuzzy Inference
  • Fuzzy Modelling
  • Fuzzy Numbers
  • Hierarchical Fuzzy Rule-based Model
  • Water Pipe Condition Prediction

Fingerprint Dive into the research topics of 'Developing a hierarchical fuzzy rule-based model with weighted linguistic rules: A case study of water pipes condition prediction'. Together they form a unique fingerprint.

  • Cite this