DC Field | Value | Language |
---|---|---|
dc.contributor.author | Woo, Seongcheol | ko |
dc.contributor.author | Park, Junyoung | ko |
dc.contributor.author | Park, Jinkyoo | ko |
dc.contributor.author | Manuel, Lance | ko |
dc.date.accessioned | 2020-01-03T09:20:05Z | - |
dc.date.available | 2020-01-03T09:20:05Z | - |
dc.date.created | 2019-12-31 | - |
dc.date.created | 2019-12-31 | - |
dc.date.created | 2019-12-31 | - |
dc.date.created | 2019-12-31 | - |
dc.date.issued | 2020-10 | - |
dc.identifier.citation | IEEE Transactions on Sustainable Energy, v.11, no.4, pp.2294 - 2304 | - |
dc.identifier.issn | 1949-3029 | - |
dc.identifier.uri | http://hdl.handle.net/10203/270848 | - |
dc.description.abstract | Predicting a wind turbine's responses that correspond to a complex wind field is challenging because the responses are caused by the complex interaction between a dynamically operating mechanical system and a spatially and temporally coupled stochastic wind field. We propose a physics-inspired, data-driven prediction model called stacked dilated convolutional LSTMs (SDCL) that uses a sequence of wind fields (snapshots) as an input to predict future wind turbine responses. A SDCL is composed of a set of dilated convolutional neural networks (CNNs) combined with a long short-term memory (LSTM) to capture the spatial and temporal evolution of the turbulence structure in the input wind field. Notably, a dilated CNN with different dilation ratios along with a corresponding LSTM module, a single component of SDCL, is designed to capture the evolution of an eddy of a certain size in the turbulent wind field. Then SDCL effectively models the evolution of multiple eddies of different sizes. Through a simulation study, we have demonstrated that such a physics-inspired network architecture is effective in processing a complex wind field and thus predicting two representative future wind turbine responses, energy generation and blade root out-of-plane bending moment, more accurately than other standard deep learning architectures. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Wind Field-Based Short-Term Turbine Response Forecasting by Stacked Dilated Convolutional LSTMs | - |
dc.type | Article | - |
dc.identifier.wosid | 000571777300023 | - |
dc.identifier.scopusid | 2-s2.0-85093521286 | - |
dc.type.rims | ART | - |
dc.citation.volume | 11 | - |
dc.citation.issue | 4 | - |
dc.citation.beginningpage | 2294 | - |
dc.citation.endingpage | 2304 | - |
dc.citation.publicationname | IEEE Transactions on Sustainable Energy | - |
dc.identifier.doi | 10.1109/TSTE.2019.2954107 | - |
dc.contributor.localauthor | Park, Jinkyoo | - |
dc.contributor.nonIdAuthor | Manuel, Lance | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Wind turbines | - |
dc.subject.keywordAuthor | Predictive models | - |
dc.subject.keywordAuthor | Wind speed | - |
dc.subject.keywordAuthor | Wind forecasting | - |
dc.subject.keywordAuthor | Load modeling | - |
dc.subject.keywordAuthor | Wind power generation | - |
dc.subject.keywordAuthor | Atmospheric modeling | - |
dc.subject.keywordAuthor | Wind turbine responses | - |
dc.subject.keywordAuthor | turbulent wind field | - |
dc.subject.keywordAuthor | inductive biases | - |
dc.subject.keywordAuthor | neural networks | - |
dc.subject.keywordAuthor | spatio-temporal analysis | - |
dc.subject.keywordPlus | ENERGY-STORAGE SYSTEM | - |
dc.subject.keywordPlus | NEURAL-NETWORK | - |
dc.subject.keywordPlus | SPEED | - |
dc.subject.keywordPlus | MODEL | - |
dc.subject.keywordPlus | PREDICTION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.