Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
A physics-informed neural network modelling methodology to analyse integrated thermofluid systems
Physics-informed neural networks (PINNs) were developed to overcome the limitations of acquiring large training datasets that are commonly encountered when using purely data-driven machine learning methods. This study explores a PINN modelling methodology to analyse steady-state integrated thermoflu...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English English |
| Published: |
Department of Mechanical Engineering
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613248176521217 |
|---|---|
| access_status_str | Open Access |
| author | Laugksch, Kristina Karli |
| author2 | Rousseau, Pieter |
| author_browse | Laugksch, Kristina Karli Rousseau, Pieter |
| author_facet | Rousseau, Pieter Laugksch, Kristina Karli |
| author_sort | Laugksch, Kristina Karli |
| collection | Thesis |
| description | Physics-informed neural networks (PINNs) were developed to overcome the limitations of acquiring large training datasets that are commonly encountered when using purely data-driven machine learning methods. This study explores a PINN modelling methodology to analyse steady-state integrated thermofluid systems based on the mass, energy, and momentum balance equations, combined with the relevant component characteristics and fluid property relationships. The PINN methodology is applied to three thermofluid systems that encapsulate important phenomena typically encountered in integrated thermofluid systems modelling, namely: (i) a heat exchanger network with two different fluid streams and components linked in series and parallel; (ii) a recuperated closed Brayton cycle containing various turbomachines and heat exchangers, and (iii) a simplified boiler consisting of a furnace and radiative convective superheater. The predictions of the three PINN models were compared to benchmark solutions generated via conventional, physics-based thermofluid process models. The largest average relative error across all three models is only 0.93%, indicating that the PINN methodology can successfully be implemented to generate accurate solutions using the non-dimensionalised forms of the balance equations. Furthermore, it was shown that the trained PINN models provided a significant increase in inference speed compared to the conventional process models. The PINN modelling methodology was then extended to develop a surrogate model for the heat exchanger network. An additional surrogate model was developed for comparison using a data-driven multilayer perceptron (MLP) neural network. The MLP surrogate model was able to interpolate accurately. However, its predictive performance declined when making predictions for samples that fell outside of the range of training data. Despite various refinements, the PINN surrogate model could only be trained successfully for datasets that contained up to five unique samples. This limitation could not be resolved within the scope of the present study and should be investigated further. The accuracy of the PINN surrogate model degraded significantly when used to extrapolate beyond the training envelope. Due to the constraint on the number of training samples, it is impossible to draw a general conclusion regarding the extrapolation ability of the PINN concept. In spite of its current limitations, the significant increase in computational speed offered by the PINN modelling methodology when used to analyse integrated thermofluid systems suggests that this is a promising modelling technique that should be explored further. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/41003 |
| institution | University of Cape Town (South Africa) |
| language | English eng |
| last_indexed | 2026-06-10T12:33:07.122Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Department of Mechanical Engineering |
| publisherStr | Department of Mechanical Engineering |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/41003 A physics-informed neural network modelling methodology to analyse integrated thermofluid systems Laugksch, Kristina Karli Rousseau, Pieter Laubscher, Ryno Engineering Physics-informed neural networks (PINNs) were developed to overcome the limitations of acquiring large training datasets that are commonly encountered when using purely data-driven machine learning methods. This study explores a PINN modelling methodology to analyse steady-state integrated thermofluid systems based on the mass, energy, and momentum balance equations, combined with the relevant component characteristics and fluid property relationships. The PINN methodology is applied to three thermofluid systems that encapsulate important phenomena typically encountered in integrated thermofluid systems modelling, namely: (i) a heat exchanger network with two different fluid streams and components linked in series and parallel; (ii) a recuperated closed Brayton cycle containing various turbomachines and heat exchangers, and (iii) a simplified boiler consisting of a furnace and radiative convective superheater. The predictions of the three PINN models were compared to benchmark solutions generated via conventional, physics-based thermofluid process models. The largest average relative error across all three models is only 0.93%, indicating that the PINN methodology can successfully be implemented to generate accurate solutions using the non-dimensionalised forms of the balance equations. Furthermore, it was shown that the trained PINN models provided a significant increase in inference speed compared to the conventional process models. The PINN modelling methodology was then extended to develop a surrogate model for the heat exchanger network. An additional surrogate model was developed for comparison using a data-driven multilayer perceptron (MLP) neural network. The MLP surrogate model was able to interpolate accurately. However, its predictive performance declined when making predictions for samples that fell outside of the range of training data. Despite various refinements, the PINN surrogate model could only be trained successfully for datasets that contained up to five unique samples. This limitation could not be resolved within the scope of the present study and should be investigated further. The accuracy of the PINN surrogate model degraded significantly when used to extrapolate beyond the training envelope. Due to the constraint on the number of training samples, it is impossible to draw a general conclusion regarding the extrapolation ability of the PINN concept. In spite of its current limitations, the significant increase in computational speed offered by the PINN modelling methodology when used to analyse integrated thermofluid systems suggests that this is a promising modelling technique that should be explored further. 2025-02-25T07:40:35Z 2025-02-25T07:40:35Z 2024 2025-02-25T07:36:38Z Thesis / Dissertation Masters MSc http://hdl.handle.net/11427/41003 en eng application/pdf Department of Mechanical Engineering Faculty of Engineering and the Built Environment University of Cape Town |
| spellingShingle | Engineering Laugksch, Kristina Karli A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| thesis_degree_str | Master's |
| title | A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| title_full | A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| title_fullStr | A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| title_full_unstemmed | A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| title_short | A physics-informed neural network modelling methodology to analyse integrated thermofluid systems |
| title_sort | physics informed neural network modelling methodology to analyse integrated thermofluid systems |
| topic | Engineering |
| url | http://hdl.handle.net/11427/41003 |
| work_keys_str_mv | AT laugkschkristinakarli aphysicsinformedneuralnetworkmodellingmethodologytoanalyseintegratedthermofluidsystems AT laugkschkristinakarli physicsinformedneuralnetworkmodellingmethodologytoanalyseintegratedthermofluidsystems |