Please use this identifier to cite or link to this item: http://theses.ncl.ac.uk/jspui/handle/10443/5721
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Peng-
dc.date.accessioned2023-02-22T10:36:49Z-
dc.date.available2023-02-22T10:36:49Z-
dc.date.issued2022-
dc.identifier.urihttp://hdl.handle.net/10443/5721-
dc.descriptionPhD Thesisen_US
dc.description.abstractFloating Offshore Wind Turbines (FOWTs) have shown a promising future due to the goal of Net Zero emissions by 2050. However, the highly coupled nonlinear performances of FOWTs bring many challenges to the implementation of numerical and basin experimental methods in design and optimisation. This PhD project proposes an innovative method, named SADA (Software-in-the-Loop combined Artificial Intelligence Method for Dynamic Analysis of Floating Wind Turbines), to optimise the design and predict dynamic performances of FOWTs. SADA is built based on a coupled aero-hydro-servo-elastic programme DARwind and Machine Learning Algorithms. Firstly, the concept of Key Disciplinary Parameters (KDPs) is inspired by FOWT-related disciplinary theories. Secondly, DARwind will take continuous action through the Software-in-the-Loop (SIL) model to obtain more accurate prediction results. Thirdly, SADA can build data sets and analyse deep-seated physical laws of FOWTs. Then, case studies were conducted to prove the feasibility of the SADA method on the basin experiment data. The results show that the mean values of some physical quantities can be predicted by SADA with higher accuracy than the original DARwind simulation results. In addition, full-scale case studies were conducted by extending SADA to engineering applications, though some design parameters are not accessible. Furthermore, other physical quantities that cannot be obtained directly in full-scale measurement easily but are of great concern to industry can also be obtained from a more credible perspective. The proposed SADA method could benefit the wind industry by taking advantage of the numerical analysis method and AI technology. This brings a new and promising solution for overcoming the handicap impeding direct use of traditional basin experimental technology or full-scale measurement. Therefore, designers in the wind industry can optimise FOWTs designs to a higher level, thereby achieving a better method of and maintaining safe operation of FOWTs in a complex sea state.en_US
dc.language.isoenen_US
dc.publisherNewcastle Universityen_US
dc.titleSoftware-in-the-Loop combined Artificial Intelligence for Optimised Design and Dynamic Performance Prediction of Floating Offshore Wind Turbinesen_US
dc.typeThesisen_US
Appears in Collections:School of Engineering

Files in This Item:
File Description SizeFormat 
ChenP2022.pdfThesis11.97 MBAdobe PDFView/Open
dspacelicence.pdfLicence43.82 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.