Forecasting design values of tidal/ocean power generator in the strait with unidirectional flow by deep learning

Autor: Ryo Fujiwara, Ryoma Fukuhara, Tsubasa Ebiko, Makoto Miyatake
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Intelligent Systems with Applications, Vol 14, Iss , Pp 200067- (2022)
Druh dokumentu: article
ISSN: 2667-3053
DOI: 10.1016/j.iswa.2022.200067
Popis: Renewable energy is an essential factor in guaranteeing the sustainability of society. In Japan, there have been developments to harness energy from the ocean. The Tsugaru strait, in the northern region of Japan, is an area that has attracted attention for this purpose. We propose a tidal/ocean power generator utilizing a Flaring Flanged Diffuser (FFD) to harness the power. However, for the power generators utilizing FFD to generate power at the optimal condition, design values based on the stream regimes need to be determined. In this paper, the objective is to forecast the design values of tidal/ocean power generators utilizing FFD. We are especially interested in the dimensions of the diffuser shape that relate to effective factors for increasing flow velocity. Fluid field data around FFD is obtained by experimentation. The fluid field data is measured by particle image velocimetry (PIV). The trained deep neural network can forecast design values from a given fluid field. Moreover, we can recognize correlations between the changes in design values and the increase of fluid velocity.
Databáze: Directory of Open Access Journals