{"id":{"repo_id":"cork","oai_identifier":"oai:cora.ucc.ie:10468/15007"},"canonical_url":"https://search.dev.ndltd.org/etd/cork/oai:cora.ucc.ie:10468/15007","repository":{"repo_id":"cork","name":"University College Cork","base_url":"https://cora.ucc.ie/server/oai/request"},"display":{"title":"Development and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial setting","abstract":"This research explores the transition to proactive maintenance of HVAC equipment, specifically AHUs in industrial facilities, to make progress towards climate goals. HVAC systems account for 14% of global energy consumption, with the potential to increase efficiency by 20% by addressing energy-wasting faults according to Roth et al. However, these faults are difficult to detect due to their compensating control logic. This research highlights the potential of digitalisation techniques, particularly AI, to identify and rectify these faults, which would contribute to an approximate 2.8% global efficiency improvement. Notably, the study focuses on the nuances of industrial facilities, which have received limited attention compared to other building types. The research identifies several gaps in existing literature, including the knowledge gap between proactive data analysis and reactive engineering mind-sets, the data gap between high-quality experimental datasets and poor-quality industrial datasets, the operational gap between known baselines in experimental studies and unknown baselines in industrial settings, and the practice-theory gap between data-driven approaches in the literature and rule-based approaches in commercial tools. To address the knowledge gap, this thesis presents the IDAIC framework, a domain knowledge integration-type adaptation of the CRISP-DM process model. The implementation of the framework in an industrial facility to curate a dataset and develop a data assessment decision tree has contributed towards closing the data gap. Additionally, the study proposes extensions to the APAR ruleset and a practical data-driven fault detection method to address the operational gap. The deployment of the IDAIC framework as a tool leverages the UML modelling language to address practical considerations and demonstrate the approach's flexibility. Therefore, the main research outputs include the IDAIC framework, an industrial AHU dataset, a data assessment decision tree, an extension to the APAR ruleset, and a proactive maintenance decision support tool. Notably, this research unveils a fault in which the outside air damper is stuck in the fully open position, leading to estimated annual savings of €60,000. These findings validate the effectiveness of a human-centric, domain expertise-integrated approach that is resilient to industrial challenges, contributing to sustainable energy efficiency improvements and the achievement of climate targets using the best available solutions.","abstract_html":"This research explores the transition to proactive maintenance of HVAC equipment, specifically AHUs in industrial facilities, to make progress towards climate goals. HVAC systems account for 14% of global energy consumption, with the potential to increase efficiency by 20% by addressing energy-wasting faults according to Roth et al. However, these faults are difficult to detect due to their compensating control logic. This research highlights the potential of digitalisation techniques, particularly AI, to identify and rectify these faults, which would contribute to an approximate 2.8% global efficiency improvement. Notably, the study focuses on the nuances of industrial facilities, which have received limited attention compared to other building types. The research identifies several gaps in existing literature, including the knowledge gap between proactive data analysis and reactive engineering mind-sets, the data gap between high-quality experimental datasets and poor-quality industrial datasets, the operational gap between known baselines in experimental studies and unknown baselines in industrial settings, and the practice-theory gap between data-driven approaches in the literature and rule-based approaches in commercial tools. To address the knowledge gap, this thesis presents the IDAIC framework, a domain knowledge integration-type adaptation of the CRISP-DM process model. The implementation of the framework in an industrial facility to curate a dataset and develop a data assessment decision tree has contributed towards closing the data gap. Additionally, the study proposes extensions to the APAR ruleset and a practical data-driven fault detection method to address the operational gap. The deployment of the IDAIC framework as a tool leverages the UML modelling language to address practical considerations and demonstrate the approach's flexibility. Therefore, the main research outputs include the IDAIC framework, an industrial AHU dataset, a data assessment decision tree, an extension to the APAR ruleset, and a proactive maintenance decision support tool. Notably, this research unveils a fault in which the outside air damper is stuck in the fully open position, leading to estimated annual savings of €60,000. These findings validate the effectiveness of a human-centric, domain expertise-integrated approach that is resilient to industrial challenges, contributing to sustainable energy efficiency improvements and the achievement of climate targets using the best available solutions.","abstract_has_math":false,"creators":["Ahern, Michael"],"institution":"University College Cork","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Bruton, Ken","O'Sullivan, Dominic"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-24T01:48:18Z","subjects":["Data analytics","Data mining","Fault detection and diagnostics","Industrial AI","Data quality","Building AFDD"],"languages":["en"],"rights":["© 2023, Michael Ahern."],"rights_urls":["https://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10468/15007","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Bruton, Ken","O'Sullivan, Dominic"]},{"key":"dc:creator","label":"Author","values":["Ahern, Michael"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-09-20T08:21:38Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-09-20T08:21:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:publisher","label":"Institution","values":["University College Cork"]},{"key":"dc:type","label":"Dc Type","values":["Doctoral thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["PhD - Doctor of Philosophy"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Data analytics","Data mining","Fault detection and diagnostics","Industrial AI","Data quality","Building AFDD"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["© 2023, Michael Ahern."]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10468/15007"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This research explores the transition to proactive maintenance of HVAC equipment, specifically AHUs in industrial facilities, to make progress towards climate goals. HVAC systems account for 14% of global energy consumption, with the potential to increase efficiency by 20% by addressing energy-wasting faults according to Roth et al. However, these faults are difficult to detect due to their compensating control logic. This research highlights the potential of digitalisation techniques, particularly AI, to identify and rectify these faults, which would contribute to an approximate 2.8% global efficiency improvement. Notably, the study focuses on the nuances of industrial facilities, which have received limited attention compared to other building types. The research identifies several gaps in existing literature, including the knowledge gap between proactive data analysis and reactive engineering mind-sets, the data gap between high-quality experimental datasets and poor-quality industrial datasets, the operational gap between known baselines in experimental studies and unknown baselines in industrial settings, and the practice-theory gap between data-driven approaches in the literature and rule-based approaches in commercial tools. To address the knowledge gap, this thesis presents the IDAIC framework, a domain knowledge integration-type adaptation of the CRISP-DM process model. The implementation of the framework in an industrial facility to curate a dataset and develop a data assessment decision tree has contributed towards closing the data gap. Additionally, the study proposes extensions to the APAR ruleset and a practical data-driven fault detection method to address the operational gap. The deployment of the IDAIC framework as a tool leverages the UML modelling language to address practical considerations and demonstrate the approach's flexibility. Therefore, the main research outputs include the IDAIC framework, an industrial AHU dataset, a data assessment decision tree, an extension to the APAR ruleset, and a proactive maintenance decision support tool. Notably, this research unveils a fault in which the outside air damper is stuck in the fully open position, leading to estimated annual savings of €60,000. These findings validate the effectiveness of a human-centric, domain expertise-integrated approach that is resilient to industrial challenges, contributing to sustainable energy efficiency improvements and the achievement of climate targets using the best available solutions."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Development and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial setting"]}]}],"canonical_facts":{"dc:contributor.advisor":["Bruton, Ken","O'Sullivan, Dominic"],"dc:creator":["Ahern, Michael"],"dc:date.accessioned":["2023-09-20T08:21:38Z"],"dc:date.available":["2023-09-20T08:21:38Z"],"dc:date.issued":["2023"],"dc:description.abstract":["This research explores the transition to proactive maintenance of HVAC equipment, specifically AHUs in industrial facilities, to make progress towards climate goals. HVAC systems account for 14% of global energy consumption, with the potential to increase efficiency by 20% by addressing energy-wasting faults according to Roth et al. However, these faults are difficult to detect due to their compensating control logic. This research highlights the potential of digitalisation techniques, particularly AI, to identify and rectify these faults, which would contribute to an approximate 2.8% global efficiency improvement. Notably, the study focuses on the nuances of industrial facilities, which have received limited attention compared to other building types. The research identifies several gaps in existing literature, including the knowledge gap between proactive data analysis and reactive engineering mind-sets, the data gap between high-quality experimental datasets and poor-quality industrial datasets, the operational gap between known baselines in experimental studies and unknown baselines in industrial settings, and the practice-theory gap between data-driven approaches in the literature and rule-based approaches in commercial tools. To address the knowledge gap, this thesis presents the IDAIC framework, a domain knowledge integration-type adaptation of the CRISP-DM process model. The implementation of the framework in an industrial facility to curate a dataset and develop a data assessment decision tree has contributed towards closing the data gap. Additionally, the study proposes extensions to the APAR ruleset and a practical data-driven fault detection method to address the operational gap. The deployment of the IDAIC framework as a tool leverages the UML modelling language to address practical considerations and demonstrate the approach's flexibility. Therefore, the main research outputs include the IDAIC framework, an industrial AHU dataset, a data assessment decision tree, an extension to the APAR ruleset, and a proactive maintenance decision support tool. Notably, this research unveils a fault in which the outside air damper is stuck in the fully open position, leading to estimated annual savings of €60,000. These findings validate the effectiveness of a human-centric, domain expertise-integrated approach that is resilient to industrial challenges, contributing to sustainable energy efficiency improvements and the achievement of climate targets using the best available solutions."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10468/15007"],"dc:language.iso":["en"],"dc:publisher":["University College Cork"],"dc:rights":["© 2023, Michael Ahern."],"dc:rights.uri":["https://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Data analytics","Data mining","Fault detection and diagnostics","Industrial AI","Data quality","Building AFDD"],"dc:title":["Development and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial setting"],"dc:type":["Doctoral thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["PhD - Doctor of Philosophy"]},"updated_at":"2026-07-24T01:48:18Z"}