STUDY ON PREDICTION OF TIDE AND OCEAN CURRENT BY DATA-DRIVEN MODEL

摘要：

Tide and ocean current are the major dynamic factors for ocean engineering. The insufficiency of tidal level and ocean current data near the ocean engineering waters may bring uncertainty for ocean engineering design and numerical model. A data-driven model is presented to solve this problem based on Artificial Neural Network (ANN), one site and multi-sites data-driven models are established. Field data under complex geography and hydrodynamic condition are used to validate the performance of the present data-driven models, the nonlinear mapping relation among tidal level and ocean current is reproduced by these models. Comparisons and errors analysis between the numerical results and field-data are satisfactory, which shows the simple structure and good precision of the present models. Furthermore, the data-driven model can be widely useful for solving this ocean engineering problem.

关键词： data-driven model artificial neural network ocean engineering tide ocean current

作者: Zhaochen Sun Mingchang Li Shuxiu Liang

作者单位: State Key Lab.of Coastal and Offshore Eng., Dalian Univ.of Technol., Dalian 116024, China

会议类型: 国际会议

会议名称: 第16届亚太地区国际水利学大会暨第3届水工水力学国际研讨会(16th IAHR-APD Congress and 3rd Symoposium of IAHR-ISHS)

会议地点: 南京

会议语种:英文

页码: 1163-1168

在线出版日期: 2008-10-20（万方平台首次上网日期，不代表论文的发表时间）