Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers
The present paper proposes a new mixed-fidelity method to optimize the shape of ships using genetic algorithms (GA) and potential flow codes to evaluate the hydrodynamics of variant hull forms, enhanced by a surrogate model based on an Artificial Neural Network (ANN) to account for viscous effects....
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/35f24b0a67fe4ea7ab000ea241ddc0f7 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:35f24b0a67fe4ea7ab000ea241ddc0f7 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:35f24b0a67fe4ea7ab000ea241ddc0f72021-11-25T18:04:35ZMixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers10.3390/jmse91112342077-1312https://doaj.org/article/35f24b0a67fe4ea7ab000ea241ddc0f72021-11-01T00:00:00Zhttps://www.mdpi.com/2077-1312/9/11/1234https://doaj.org/toc/2077-1312The present paper proposes a new mixed-fidelity method to optimize the shape of ships using genetic algorithms (GA) and potential flow codes to evaluate the hydrodynamics of variant hull forms, enhanced by a surrogate model based on an Artificial Neural Network (ANN) to account for viscous effects. The performance of the variant hull forms generated by the GA is evaluated for calm water resistance using potential flow methods which are quite fast when they run on modern computers. However, these methods do not take into account the viscous effects which are dominant in the stern region of the ship. Solvers of the Reynolds-Averaged Navier-Stokes Equations (RANS) should be used in this respect, which, however, are too time-consuming to be used for the evaluation of some hundreds of variants within the GA search. In this study, a RANS solver is used prior to the execution of the GA to train an ANN in modeling the effect of stern design geometrical parameters only. Potential flow results, accounting for the geometrical design parameters of the rest of the hull, are combined with the aforementioned trained meta-model for the final hull form evaluation. This work concentrates on the provision of a more reliable framework for the evaluation of hull form performance in calm water without a significant increase of the computing time.Gregory J. GrigoropoulosChristos BakirtzoglouGeorge PapadakisDimitrios NtourasMDPI AGarticleoptimizationgenetic algorithmsartificial neural networksmeta-modelsmultilevel optimizationpotential flowNaval architecture. Shipbuilding. Marine engineeringVM1-989OceanographyGC1-1581ENJournal of Marine Science and Engineering, Vol 9, Iss 1234, p 1234 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
optimization genetic algorithms artificial neural networks meta-models multilevel optimization potential flow Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 |
spellingShingle |
optimization genetic algorithms artificial neural networks meta-models multilevel optimization potential flow Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Gregory J. Grigoropoulos Christos Bakirtzoglou George Papadakis Dimitrios Ntouras Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
description |
The present paper proposes a new mixed-fidelity method to optimize the shape of ships using genetic algorithms (GA) and potential flow codes to evaluate the hydrodynamics of variant hull forms, enhanced by a surrogate model based on an Artificial Neural Network (ANN) to account for viscous effects. The performance of the variant hull forms generated by the GA is evaluated for calm water resistance using potential flow methods which are quite fast when they run on modern computers. However, these methods do not take into account the viscous effects which are dominant in the stern region of the ship. Solvers of the Reynolds-Averaged Navier-Stokes Equations (RANS) should be used in this respect, which, however, are too time-consuming to be used for the evaluation of some hundreds of variants within the GA search. In this study, a RANS solver is used prior to the execution of the GA to train an ANN in modeling the effect of stern design geometrical parameters only. Potential flow results, accounting for the geometrical design parameters of the rest of the hull, are combined with the aforementioned trained meta-model for the final hull form evaluation. This work concentrates on the provision of a more reliable framework for the evaluation of hull form performance in calm water without a significant increase of the computing time. |
format |
article |
author |
Gregory J. Grigoropoulos Christos Bakirtzoglou George Papadakis Dimitrios Ntouras |
author_facet |
Gregory J. Grigoropoulos Christos Bakirtzoglou George Papadakis Dimitrios Ntouras |
author_sort |
Gregory J. Grigoropoulos |
title |
Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
title_short |
Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
title_full |
Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
title_fullStr |
Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
title_full_unstemmed |
Mixed-Fidelity Design Optimization of Hull Form Using CFD and Potential Flow Solvers |
title_sort |
mixed-fidelity design optimization of hull form using cfd and potential flow solvers |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/35f24b0a67fe4ea7ab000ea241ddc0f7 |
work_keys_str_mv |
AT gregoryjgrigoropoulos mixedfidelitydesignoptimizationofhullformusingcfdandpotentialflowsolvers AT christosbakirtzoglou mixedfidelitydesignoptimizationofhullformusingcfdandpotentialflowsolvers AT georgepapadakis mixedfidelitydesignoptimizationofhullformusingcfdandpotentialflowsolvers AT dimitriosntouras mixedfidelitydesignoptimizationofhullformusingcfdandpotentialflowsolvers |
_version_ |
1718411671460904960 |