University of Twente Student Theses
Automated detection of hidden failures in heating and photovoltaic systems of ‘Nul-op-de-meter’-housing Projects
Harmsma, W.H. (2022) Automated detection of hidden failures in heating and photovoltaic systems of ‘Nul-op-de-meter’-housing Projects.
|
PDF
14MB |
| Abstract: | In this thesis we tackle the problem of not meeting energy requirements stated in service level agreements of 'Nul-op-de-meter'-housing projects. To tackle this, we aim to reduce delays in the detection of faults in photovoltaic and heating systems. We find that failures in the heat pump and PV systems are an unlikely cause for not meeting the energy requirements in the SLAs. Regardless, we attempt to reduce fault detection delay by introducing a classification model based on principle component regression and a classification model called 'SolarClique' (Iyengar et al., 2018). Neither model is found to perform sufficiently. Future efforts should be put in the collection of reliable data on the state of the monitored systems, including data on precisely when these systems where in fault. |
| Item Type: | Essay (Master) |
| Clients: | Bouwgroep Dijkstra-Draisma, Dokkum, the Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 43 environmental science, 54 computer science, 58 process technology |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/89351 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page