BP neural network applied to ADCP wave measurement when background current exists

摘要：

　　New ADCP(Acoustic Doppler current profiler)can estimate surface wave based on current measurement.Now existing background correction algorithm only considers current amplitude,TRDI ADCP commercial software WAVESMON suggest if current amplitude is greater than 0.75m/s,wave estimation should be corrected for background current.The research shows that when background exists,background current amplitude,background current direction,main wave direction,water depth should be considered.Considering the existing background current is not accurate,the BP neural network is used to find nonlinear relationship between wave estimation error and various influencing factors,the research content of the paper is of important significance,which can be used as new background current correction algorithm basis.

关键词： wave estimation background current correction BP neural network

作者: Wei Zheng Zhi Wang Xiangtao Ran Mingyang Fu Shukai yang Shibo Chu Li Hui Ying Yang

作者单位: Institute of Oceanographic Instrumentation,Shandong Academy of Sciences Shandong Provincial Key Laboratory of Ocean Environmental Monitoring Technology Qingdao,China

会议类型: 国际会议

会议名称: 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference(ITOEC2017)(2017 IEEE 第3届信息技术与机电一体化工程国际学术会议)

会议地点: 重庆

会议语种:英文

页码: 55-58

在线出版日期: 2017-10-03（万方平台首次上网日期，不代表论文的发表时间）