https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DATA-DRIVEN DETECTION OF LEAKING VALVES IN AIR HANDLING UNITS (AHUS)
Mälardalen University, School of Innovation, Design and Engineering.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 40 credits / 60 HE creditsStudent thesis
Abstract [en]

Air Handling Units (AHUs) are critical for maintaining indoor air quality and energy efficiency in buildings. A common but often undetected fault in AHUs is valve leakage, which can lead to significant energy losses, reduced thermal comfort, and increased operational costs. This thesis investigates a datadriven approach to detecting valve leakage using machine learning, with the goal of developing models that can generalize from controlled experimental conditions to real-world installations.

The work involved designing and executing 80 controlled experiments on a laboratory AHU test rig, simulating both normal and leakage conditions using temperature, flow, and pressure sensors. The collected dataset was used to train and evaluate several machine learning algorithms, with a focus on XGBoost models using both manually engineered and AutoFeat-generated features. A dedicated preprocessing pipeline was created to adapt and align field AHU operational data with the lab dataset, enabling real-world validation despite limited metadata.

Results show that the XGBoost models could identify leakage patterns with high accuracy (97.41%) in lab conditions and retain detection capability when tested on real-life field data, even with only partial operational context. Cross-verification with coil temperature differentials supported the validity of the predictions. The findings demonstrate that machine learning can detect subtle operational anomalies indicative of leakage, offering a foundation for predictive maintenance in HVAC systems. However, larger volumes of domain-labeled operational data are needed before large-scale deployment.

Place, publisher, year, edition, pages
2025. , p. 62
National Category
Software Engineering
Identifiers
URN: urn:nbn:se:mdh:diva-73501OAI: oai:DiVA.org:mdh-73501DiVA, id: diva2:2001993
Available from: 2025-09-29 Created: 2025-09-29 Last updated: 2025-10-15Bibliographically approved

Open Access in DiVA

fulltext(3087 kB)209 downloads
File information
File name FULLTEXT01.pdfFile size 3087 kBChecksum SHA-512
2574263017acc6abaa66d8893d63df0787085a180b4eae2198bb01034af27b980c8b86fbcc18c015dca72e8497796e5447933e77c2fe20b372f0c1af63e20517
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Ghani, Maheen Abdul
By organisation
School of Innovation, Design and Engineering
Software Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 3806 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf