Development and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial setting

Simple item page
dc.contributor.advisorBruton, Ken
dc.contributor.advisorO'Sullivan, Dominic
dc.contributor.authorAhern, Michaelen
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2023-09-20T08:21:38Z
dc.date.available2023-09-20T08:21:38Z
dc.date.issued2023
dc.date.submitted2023
dc.description.abstractThis 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.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationAhern, M. 2023. Development and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial setting. PhD Thesis, University College Cork.
dc.identifier.endpage216
dc.identifier.urihttps://hdl.handle.net/10468/15007
dc.language.isoenen
dc.publisherUniversity College Corken
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres Programme::Phase 2/12/RC/2302_P2/IE/MAREI_Phase 2/en
dc.rights© 2023, Michael Ahern.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectData analytics
dc.subjectData mining
dc.subjectFault detection and diagnostics
dc.subjectIndustrial AI
dc.subjectData quality
dc.subjectBuilding AFDD
dc.titleDevelopment and implementation of a framework to aid the transition to proactive maintenance approaches on air handling units in the industrial settingen
dc.typeDoctoral thesisen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD - Doctor of Philosophyen
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
AhernMD_PhD2023.docx
Size:
8.51 MB
Format:
Microsoft Word XML
Description:
Full Text E-thesis (Word)
Thumbnail Image
Name:
AhernMD_PhD2023.pdf
Size:
7.43 MB
Format:
Adobe Portable Document Format
Description:
Full Text E-thesis
Download
Thumbnail Image
Name:
Submission for Examination Form
Size:
1.71 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
5.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Theses
Centre for Marine and Renewable Energy (MaREI) - Doctoral Theses
Civil and Environmental Engineering - Doctoral Theses
College of Science, Engineering and Food Science - Doctoral Theses