{"id":{"repo_id":"zulu","oai_identifier":"oai:uzspace.unizulu.ac.za:10530/2299"},"canonical_url":"https://search.dev.ndltd.org/etd/zulu/oai:uzspace.unizulu.ac.za:10530/2299","repository":{"repo_id":"zulu","name":"University of Zululand","base_url":"https://uzspace.unizulu.ac.za/server/oai/request"},"display":{"title":"Active leakage management with bayesian networks","abstract":"Despite the existence of different active leakage management methods and models, their implementation in most developing countries’ Water distribution systems (WDS’s) remain limited. This is attributed to some limiting challenges to leakage management faced by these WDS. Some of these include; financial constraints, poor record-keeping systems, and inadequate technicalskillsandtechnology. Thisleadsthesedistributionsystemstoadopt passive leakage management approaches that increase water losses and risk the destruction of neighboring infrastructure and water contamination. This study therefore presents a pipe leak monitoring and optimal maintenance sequencedeterminingmodellingframeworkthatisapplicableevenindistribution systems with limited data. The framework comprises of three models: a data adaptive Bayesian network(BN)modelforpredictingpipeleakprobabilitiesusedforleakagemonitoring, a water loss estimation model for estimating pipe leak water losses and a linear programming model in which water loss estimates and pipe leak predictions are used to determine the optimal pipe leak maintenance sequence. Fromtheassessmentandimplementationexampleofthemodelingframework which used simulated data, results indicate that the modeling framework is suitable for WDS with limited data.","abstract_html":"Despite the existence of different active leakage management methods and models, their implementation in most developing countries’ Water distribution systems (WDS’s) remain limited. This is attributed to some limiting challenges to leakage management faced by these WDS. Some of these include; financial constraints, poor record-keeping systems, and inadequate technicalskillsandtechnology. Thisleadsthesedistributionsystemstoadopt passive leakage management approaches that increase water losses and risk the destruction of neighboring infrastructure and water contamination. This study therefore presents a pipe leak monitoring and optimal maintenance sequencedeterminingmodellingframeworkthatisapplicableevenindistribution systems with limited data. The framework comprises of three models: a data adaptive Bayesian network(BN)modelforpredictingpipeleakprobabilitiesusedforleakagemonitoring, a water loss estimation model for estimating pipe leak water losses and a linear programming model in which water loss estimates and pipe leak predictions are used to determine the optimal pipe leak maintenance sequence. Fromtheassessmentandimplementationexampleofthemodelingframework which used simulated data, results indicate that the modeling framework is suitable for WDS with limited data.","abstract_has_math":false,"creators":["Silwimba, Felix"],"institution":"University of Zululand","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021","date_published":"2021","updated_at":"2026-07-24T06:16:55Z","subjects":["Leakage Management","Bayesian Networks"],"languages":[],"rights":[],"rights_urls":["https://devspace.unizulu.ac.za/bitstreams/62e70dba-2075-45d9-9457-7844ddc89397/download"],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Silwimba, Felix"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2021"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Zululand"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://devspace.unizulu.ac.za/handle/10530/2299"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Leakage Management","Bayesian Networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["https://devspace.unizulu.ac.za/bitstreams/62e70dba-2075-45d9-9457-7844ddc89397/download"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://devspace.unizulu.ac.za/bitstreams/5a54694b-dc61-4205-b8e7-2e836809cf56/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Despite the existence of different active leakage management methods and models, their implementation in most developing countries’ Water distribution systems (WDS’s) remain limited. This is attributed to some limiting challenges to leakage management faced by these WDS. Some of these include; financial constraints, poor record-keeping systems, and inadequate technicalskillsandtechnology. Thisleadsthesedistributionsystemstoadopt passive leakage management approaches that increase water losses and risk the destruction of neighboring infrastructure and water contamination. This study therefore presents a pipe leak monitoring and optimal maintenance sequencedeterminingmodellingframeworkthatisapplicableevenindistribution systems with limited data. The framework comprises of three models: a data adaptive Bayesian network(BN)modelforpredictingpipeleakprobabilitiesusedforleakagemonitoring, a water loss estimation model for estimating pipe leak water losses and a linear programming model in which water loss estimates and pipe leak predictions are used to determine the optimal pipe leak maintenance sequence. Fromtheassessmentandimplementationexampleofthemodelingframework which used simulated data, results indicate that the modeling framework is suitable for WDS with limited data."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["37afc306eacc5f96cf55eece204cd73f","6902ca3e46d320497f8d16156d4de47d","b3c6a6f3e3deaca4a2726e3dab91a034"]},{"key":"dc:title","label":"Title","values":["Active leakage management with bayesian networks"]}]}],"canonical_facts":{"dc:creator":["Silwimba, Felix"],"dc:date.issued":["2021"],"dc:description.abstract":["Despite the existence of different active leakage management methods and models, their implementation in most developing countries’ Water distribution systems (WDS’s) remain limited. This is attributed to some limiting challenges to leakage management faced by these WDS. Some of these include; financial constraints, poor record-keeping systems, and inadequate technicalskillsandtechnology. Thisleadsthesedistributionsystemstoadopt passive leakage management approaches that increase water losses and risk the destruction of neighboring infrastructure and water contamination. This study therefore presents a pipe leak monitoring and optimal maintenance sequencedeterminingmodellingframeworkthatisapplicableevenindistribution systems with limited data. The framework comprises of three models: a data adaptive Bayesian network(BN)modelforpredictingpipeleakprobabilitiesusedforleakagemonitoring, a water loss estimation model for estimating pipe leak water losses and a linear programming model in which water loss estimates and pipe leak predictions are used to determine the optimal pipe leak maintenance sequence. Fromtheassessmentandimplementationexampleofthemodelingframework which used simulated data, results indicate that the modeling framework is suitable for WDS with limited data."],"dc:format.checksum.md5":["37afc306eacc5f96cf55eece204cd73f","6902ca3e46d320497f8d16156d4de47d","b3c6a6f3e3deaca4a2726e3dab91a034"],"dc:identifier.uri":["https://devspace.unizulu.ac.za/bitstreams/5a54694b-dc61-4205-b8e7-2e836809cf56/download"],"dc:publisher.institution":["University of Zululand"],"dc:relation.isreferencedby":["https://devspace.unizulu.ac.za/handle/10530/2299"],"dc:rights":["https://devspace.unizulu.ac.za/bitstreams/62e70dba-2075-45d9-9457-7844ddc89397/download"],"dc:subject":["Leakage Management","Bayesian Networks"],"dc:title":["Active leakage management with bayesian networks"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T06:16:55Z"}