Computationally efficient optimisation of elbow-type draft tube using neural network surrogates
This study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms for the design of an elbow-type draft tube, as well as to introduce a computationally efficient optimisation workflow. The proposed workflow leverages deep neural network surrogates...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S111001682400084X |
| _version_ | 1797302487212883968 |
|---|---|
| author | Ante Sikirica Ivana Lučin Marta Alvir Lado Kranjčević Zoran Čarija |
| author_facet | Ante Sikirica Ivana Lučin Marta Alvir Lado Kranjčević Zoran Čarija |
| author_sort | Ante Sikirica |
| collection | DOAJ |
| description | This study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms for the design of an elbow-type draft tube, as well as to introduce a computationally efficient optimisation workflow. The proposed workflow leverages deep neural network surrogates trained on data obtained from numerical simulations. The use of surrogates allows for a more flexible and faster evaluation of novel designs. The success history-based adaptive differential evolution with linear reduction and the multi-objective evolutionary algorithm based on decomposition were identified as the best-performing algorithms and used to determine the influence of different objectives in the single-objective optimisation and their combined impact on the draft tube design in the multi-objective optimisation. The results for the single-objective algorithm are consistent with those of the multi-objective algorithm when the objectives are considered separately. Multi-objective approach, however, should typically be chosen, especially for computationally inexpensive surrogates. A multi-criteria decision analysis method was used to obtain optimal multi-objective results, showing an improvement of 1.5% and 17% for the pressure recovery factor and drag coefficient, respectively. The difference between the predictions and the numerical results is less than 0.5% for the pressure recovery factor and 3% for the drag coefficient. As the demand for renewable energy continues to increase, the relevance of data-driven optimisation workflows, as discussed in this study, will become increasingly important, especially in the context of global sustainability efforts. |
| first_indexed | 2024-03-07T23:39:34Z |
| format | Article |
| id | doaj.art-a0519fa9dd354914b18138b7b4d7a1ce |
| institution | Directory Open Access Journal |
| issn | 1110-0168 |
| language | English |
| last_indexed | 2024-03-07T23:39:34Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj.art-a0519fa9dd354914b18138b7b4d7a1ce2024-02-20T04:18:45ZengElsevierAlexandria Engineering Journal1110-01682024-03-0190129152Computationally efficient optimisation of elbow-type draft tube using neural network surrogatesAnte Sikirica0Ivana Lučin1Marta Alvir2Lado Kranjčević3Zoran Čarija4Center for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, Rijeka, 51000 Rijeka, Croatia; Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, CroatiaFaculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, CroatiaFaculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, CroatiaCenter for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, Rijeka, 51000 Rijeka, Croatia; Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, Croatia; Corresponding author at: Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, Croatia.Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000 Rijeka, CroatiaThis study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms for the design of an elbow-type draft tube, as well as to introduce a computationally efficient optimisation workflow. The proposed workflow leverages deep neural network surrogates trained on data obtained from numerical simulations. The use of surrogates allows for a more flexible and faster evaluation of novel designs. The success history-based adaptive differential evolution with linear reduction and the multi-objective evolutionary algorithm based on decomposition were identified as the best-performing algorithms and used to determine the influence of different objectives in the single-objective optimisation and their combined impact on the draft tube design in the multi-objective optimisation. The results for the single-objective algorithm are consistent with those of the multi-objective algorithm when the objectives are considered separately. Multi-objective approach, however, should typically be chosen, especially for computationally inexpensive surrogates. A multi-criteria decision analysis method was used to obtain optimal multi-objective results, showing an improvement of 1.5% and 17% for the pressure recovery factor and drag coefficient, respectively. The difference between the predictions and the numerical results is less than 0.5% for the pressure recovery factor and 3% for the drag coefficient. As the demand for renewable energy continues to increase, the relevance of data-driven optimisation workflows, as discussed in this study, will become increasingly important, especially in the context of global sustainability efforts.http://www.sciencedirect.com/science/article/pii/S111001682400084XHydropower turbineDraft tubeMulti-objective optimisationSurrogate modellingMachine learning |
| spellingShingle | Ante Sikirica Ivana Lučin Marta Alvir Lado Kranjčević Zoran Čarija Computationally efficient optimisation of elbow-type draft tube using neural network surrogates Alexandria Engineering Journal Hydropower turbine Draft tube Multi-objective optimisation Surrogate modelling Machine learning |
| title | Computationally efficient optimisation of elbow-type draft tube using neural network surrogates |
| title_full | Computationally efficient optimisation of elbow-type draft tube using neural network surrogates |
| title_fullStr | Computationally efficient optimisation of elbow-type draft tube using neural network surrogates |
| title_full_unstemmed | Computationally efficient optimisation of elbow-type draft tube using neural network surrogates |
| title_short | Computationally efficient optimisation of elbow-type draft tube using neural network surrogates |
| title_sort | computationally efficient optimisation of elbow type draft tube using neural network surrogates |
| topic | Hydropower turbine Draft tube Multi-objective optimisation Surrogate modelling Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S111001682400084X |
| work_keys_str_mv | AT antesikirica computationallyefficientoptimisationofelbowtypedrafttubeusingneuralnetworksurrogates AT ivanalucin computationallyefficientoptimisationofelbowtypedrafttubeusingneuralnetworksurrogates AT martaalvir computationallyefficientoptimisationofelbowtypedrafttubeusingneuralnetworksurrogates AT ladokranjcevic computationallyefficientoptimisationofelbowtypedrafttubeusingneuralnetworksurrogates AT zorancarija computationallyefficientoptimisationofelbowtypedrafttubeusingneuralnetworksurrogates |