Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Application of probabilistic deep learning models to simulate thermal power plant processes
Deep learning has gained traction in thermal engineering due to its applications to process simulations, the deeper insights it can provide and its abilities to circumvent the shortcomings of classic thermodynamic simulation approaches by capturing complex inter-dependencies. This works sets out to...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Mechanical Engineering
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613292578471936 |
|---|---|
| access_status_str | Open Access |
| author | Raidoo, Renita Anand |
| author2 | Laubscher, Ryno |
| author_browse | Laubscher, Ryno Raidoo, Renita Anand |
| author_facet | Laubscher, Ryno Raidoo, Renita Anand |
| author_sort | Raidoo, Renita Anand |
| collection | Thesis |
| description | Deep learning has gained traction in thermal engineering due to its applications to process simulations, the deeper insights it can provide and its abilities to circumvent the shortcomings of classic thermodynamic simulation approaches by capturing complex inter-dependencies. This works sets out to apply probabilistic deep learning to power plant operations using historic plant data. The first study presented, entails the development of a steady-state mixture density network (MDN) capable of predicting effective heat transfer coefficients (HTC) for the various heat exchanger components inside a utility scale boiler. Selected directly controllable input features, including the excess air ratio, steam temperatures, flow rates and pressures are used to predict the HTCs. In the second case study, an encoder-decoder mixturedensity network (MDN) is developed using recurrent neural networks (RNN) for the prediction of utility-scale air-cooled condenser (ACC) backpressure. The effects of ambient conditions and plant operating parameters, such as extraction flow rate, on ACC performance is investigated. In both case studies, hyperparameter searches are done to determine the best performing architectures for these models. Comparisons are drawn between the MDN model versus standard model architecture in both case studies. The HTC predictor model achieved 90% accuracy which equates to an average error of 4.89 W m2K across all heat exchangers. The resultant time-series ACC model achieved an average error of 3.14 kPa, which translate into a model accuracy of 82%. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/37790 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:33:49.949Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| 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:11427/37790 Application of probabilistic deep learning models to simulate thermal power plant processes Raidoo, Renita Anand Laubscher, Ryno Air-cooled condensers Natural convection boilers Time-series prediction Deep learning Mixture density networks Recurrent neural networks Deep learning has gained traction in thermal engineering due to its applications to process simulations, the deeper insights it can provide and its abilities to circumvent the shortcomings of classic thermodynamic simulation approaches by capturing complex inter-dependencies. This works sets out to apply probabilistic deep learning to power plant operations using historic plant data. The first study presented, entails the development of a steady-state mixture density network (MDN) capable of predicting effective heat transfer coefficients (HTC) for the various heat exchanger components inside a utility scale boiler. Selected directly controllable input features, including the excess air ratio, steam temperatures, flow rates and pressures are used to predict the HTCs. In the second case study, an encoder-decoder mixturedensity network (MDN) is developed using recurrent neural networks (RNN) for the prediction of utility-scale air-cooled condenser (ACC) backpressure. The effects of ambient conditions and plant operating parameters, such as extraction flow rate, on ACC performance is investigated. In both case studies, hyperparameter searches are done to determine the best performing architectures for these models. Comparisons are drawn between the MDN model versus standard model architecture in both case studies. The HTC predictor model achieved 90% accuracy which equates to an average error of 4.89 W m2K across all heat exchangers. The resultant time-series ACC model achieved an average error of 3.14 kPa, which translate into a model accuracy of 82%. 2023-04-20T11:13:20Z 2023-04-20T11:13:20Z 2022 2023-04-18T09:33:03Z Master Thesis Masters MSc http://hdl.handle.net/11427/37790 eng application/pdf Department of Mechanical Engineering Faculty of Engineering and the Built Environment |
| spellingShingle | Air-cooled condensers Natural convection boilers Time-series prediction Deep learning Mixture density networks Recurrent neural networks Raidoo, Renita Anand Application of probabilistic deep learning models to simulate thermal power plant processes |
| thesis_degree_str | Master's |
| title | Application of probabilistic deep learning models to simulate thermal power plant processes |
| title_full | Application of probabilistic deep learning models to simulate thermal power plant processes |
| title_fullStr | Application of probabilistic deep learning models to simulate thermal power plant processes |
| title_full_unstemmed | Application of probabilistic deep learning models to simulate thermal power plant processes |
| title_short | Application of probabilistic deep learning models to simulate thermal power plant processes |
| title_sort | application of probabilistic deep learning models to simulate thermal power plant processes |
| topic | Air-cooled condensers Natural convection boilers Time-series prediction Deep learning Mixture density networks Recurrent neural networks |
| url | http://hdl.handle.net/11427/37790 |
| work_keys_str_mv | AT raidoorenitaanand applicationofprobabilisticdeeplearningmodelstosimulatethermalpowerplantprocesses |