Application of regression tress for prediction of water conduits failure rate

This paper presents the results of predicting the failure rate of water distribution pipes and house connections in a selected city in Poland by means of regression trees. Several regression tree models were built as part of modelling. Optimal models were selected (separately for each of the water c...

Full description

Bibliographic Details
Main Author: Kutyłowska Małgorzata
Format: Article
Language:English
Published: EDP Sciences 2017-01-01
Series:E3S Web of Conferences
Online Access:https://doi.org/10.1051/e3sconf/20172200097
_version_ 1818623195425538048
author Kutyłowska Małgorzata
author_facet Kutyłowska Małgorzata
author_sort Kutyłowska Małgorzata
collection DOAJ
description This paper presents the results of predicting the failure rate of water distribution pipes and house connections in a selected city in Poland by means of regression trees. Several regression tree models were built as part of modelling. Optimal models were selected (separately for each of the water conduit types) via an analysis of the so–called costs. The regression tree structure comprised independent variables, i.e. predictors (length, diameter, year of construction and material). The failure rates of the two types of water conduits were the dependent variable. The optimal models were characterized by the lowest costs and a relatively simple tree architecture. Operational data from the years 2001–2012 were used to determine the experimental (real) values of the failure rate and to build regression tree models. The optimal models included eight divided nodes and nine end nodes. The ranking of the significance of the parameters showed that length was the predictor responsible for division on the successive tree levels. The obtained high consistency (0.99) of the real data with the predicted ones indicates that the regression tree method can be used to analyze and assess the failure rate of water conduits.
first_indexed 2024-12-16T18:37:12Z
format Article
id doaj.art-4d664bfad0f049a1970c9b4af727c3ff
institution Directory Open Access Journal
issn 2267-1242
language English
last_indexed 2024-12-16T18:37:12Z
publishDate 2017-01-01
publisher EDP Sciences
record_format Article
series E3S Web of Conferences
spelling doaj.art-4d664bfad0f049a1970c9b4af727c3ff2022-12-21T22:21:08ZengEDP SciencesE3S Web of Conferences2267-12422017-01-01220009710.1051/e3sconf/20172200097e3sconf_asee2017_00097Application of regression tress for prediction of water conduits failure rateKutyłowska MałgorzataThis paper presents the results of predicting the failure rate of water distribution pipes and house connections in a selected city in Poland by means of regression trees. Several regression tree models were built as part of modelling. Optimal models were selected (separately for each of the water conduit types) via an analysis of the so–called costs. The regression tree structure comprised independent variables, i.e. predictors (length, diameter, year of construction and material). The failure rates of the two types of water conduits were the dependent variable. The optimal models were characterized by the lowest costs and a relatively simple tree architecture. Operational data from the years 2001–2012 were used to determine the experimental (real) values of the failure rate and to build regression tree models. The optimal models included eight divided nodes and nine end nodes. The ranking of the significance of the parameters showed that length was the predictor responsible for division on the successive tree levels. The obtained high consistency (0.99) of the real data with the predicted ones indicates that the regression tree method can be used to analyze and assess the failure rate of water conduits.https://doi.org/10.1051/e3sconf/20172200097
spellingShingle Kutyłowska Małgorzata
Application of regression tress for prediction of water conduits failure rate
E3S Web of Conferences
title Application of regression tress for prediction of water conduits failure rate
title_full Application of regression tress for prediction of water conduits failure rate
title_fullStr Application of regression tress for prediction of water conduits failure rate
title_full_unstemmed Application of regression tress for prediction of water conduits failure rate
title_short Application of regression tress for prediction of water conduits failure rate
title_sort application of regression tress for prediction of water conduits failure rate
url https://doi.org/10.1051/e3sconf/20172200097
work_keys_str_mv AT kutyłowskamałgorzata applicationofregressiontressforpredictionofwaterconduitsfailurerate