Tools
Tools
Sen, A. 
ORCID: 0000-0001-8967-9475,
2021.
Novel assessment of wall insulation in buildings using mathematical modelling, infrared thermography and artificial intelligence.
PhD, Nottingham Trent University.
|
Text
Arijit Sen 2021.pdf - Published version Download (9MB) | Preview |
Abstract
The high energy consumption for space heating in buildings and the need to reduce carbon emission point out the need for enhancing thermal insulation in buildings. Modern buildings normally have a good standard of insulation and the focus should be given to existing buildings towards enhancing the energy performance via retrofitting of buildings with upgradation of wall insulation. This thesis suggests and examines three different novel approaches towards measuring wall insulation and energy losses as well as estimating the benefits of retrofitting.
The three approaches are:
• Estimating energy losses due to working from home during Covid-19 pandemic and the difference between a poorly insulated house and a modern well-insulated house in terms of energy costings.
• Estimating heat loss through external walls and benefits of retrofitting via the use of infrared thermography and Artificial Neural Networks (ANN).
• Estimating the in-situ U-value of walls using a novel new device which combines infrared thermography with artificial neural networks.
In the first approach, a mathematical model is developed which suggests that energy bills and CO2 emission during winter will be significantly higher in a poorly insulated house than that in a modern house when working from home due to Covid-19 pandemic situation and the lockdown. The findings also show that a family living in a well-insulated modern house and commute to work would make financial savings due to working from home as the commuting cost will be eliminated and the additional energy cost for heating and other daytime daily requirements will be minimal.
In the second approach, two case studies are presented which demonstrate the suitability of combining ANN with infrared thermography, the optimum ANN architecture and the practical minimum monitoring period required for ANN to predict future heat losses through walls in buildings in quick time with a reasonable accuracy. A mathematical model is also developed to realize the theoretical monitoring period for this purpose.
In the third approach, a novel product has been developed to estimate the in-situ U-value of buildings’ walls. The product can be calibrated by training an ANN with temperature profiles generated from infrared images which are obtained from monitoring sample walls under point heat in the laboratory environment. The results of the experimental work show the new device combined with ANN could provide a reasonable estimation of the U value.
In general, the suggested three techniques have been found to be beneficial to estimate energy losses in buildings and evaluate thermal insulation to provide households with estimations of energy savings and payback period towards enhancing sustainability in buildings. In the first approach, heat loss in a building is estimated considering the U-value of walls; in the second approach, the heat loss is estimated from thermography and ANN without considering the U-value of wall; and in the third approach, the U-value of a building’s wall is determined with the help of thermography and ANN.
| Item Type: | Thesis |
|---|---|
| Creators: | Sen, A. |
| Date: | January 2021 |
| Rights: | This work is the intellectual property of the author. You may copy up to 5% of this thesis for private study, or personal, non-commercial research. Any re-use of the information contained within this document should be fully referenced, quoting the author, title, University, degree level and pagination. Queries or requests for any other use, or if a more substantial copy is required, should be directed in the first instance to the author of the Intellectual Property Rights. |
| Divisions: | Schools > School of Architecture, Design and the Built Environment |
| Record created by: | Linda Sullivan |
| Date Added: | 08 Sep 2021 13:23 |
| Last Modified: | 08 Sep 2021 13:23 |
| URI: | https://irep.ntu.ac.uk/id/eprint/44143 |
Actions (login required)
 |
Edit View |
Views
Views per month over past year
Downloads
Downloads per month over past year
