基于BP神经网络模型的ADCP倾斜条件下的修正算法研究

doi:10.3976/j.issn.1002-4026.2018.03.001

山东科学

• 海洋科技与装备 • 下一篇

基于BP神经网络模型的ADCP倾斜条件下的修正算法研究

郑威, 杨英，惠力, 鲁成杰，赵彬，杨立

齐鲁工业大学（山东省科学院），山东省科学院海洋仪器仪表研究所，山东省海洋环境监测技术重点实验室，国家海洋监测设备工程技术研究中心，山东青岛 266001

收稿日期:2017-08-30 出版日期:2018-06-20 发布日期:2018-06-20
作者简介:郑威（1983—），男，博士，副研究员，研究方向为ADCP波流测量。E-mail：honestzheng123@163.com
基金资助:
山东省自然科学基金（ZR2015YL022）;国家重点研发计划（2016YFC1400403）;海洋公益性行业科研专项(201505007-3);山东省重点研发计划（2016GGH4501）;山东省科学院青年基金(2014QN037)

The analysis between wave estimation error and influencing factors based on BP model when ADCP tilts

ZHENG Wei,YANG Ying,HUI Li, LU Cheng-jie,ZHAO Bin,YANG Li

Shandong Provincial Key Laboratory of Ocean Environmental Monitoring Techno1ogy，National Engineering and Technological Research Center of Marine Monitoring Equipment, Institute of Oceanographic Instrumentation，Qilu University of Technology (Shandong Academy of Sciences)，Qingdao 266001, China

Received:2017-08-30 Online:2018-06-20 Published:2018-06-20

摘要/Abstract

摘要：

针对现有ADCP倾斜条件下修正算法不准确的问题，将BP神经网络模型应用于分析倾斜条件下波浪估计误差与影响因素ADCP俯仰角、横滚角以及安放深度之间的非线性关系。结果表明，BP神经网络模型的预测值和实测值吻合较好，能够提升波浪估计的准确性。

关键词: 声学多普勒流速剖面仪, 倾斜修正, 海洋表面波浪测量, 波浪估计, BP神经网络模型

Abstract:

Considering that the existing tilt correction is not accurate when ADCP is tilted, the BP neural network model is used to analyze the nonlinear relationship between wave estimation error and various influencing factors such as ADCP pitching angle, roll angle and setting depth. The result shows that real wave directional spectrum and wave directional spectrum that BP neural network predicts are in good agreement. BP neural network model can improve wave estimation accuracy.

Key words: ADCP, tilt correction, wave estimation, BP neural network model, ocean surface wave measurement

中图分类号:

TB556

郑威, 杨英，惠力, 鲁成杰，赵彬，杨立. 基于BP神经网络模型的ADCP倾斜条件下的修正算法研究[J]. 山东科学, 2018, 31(3): 1-7.

ZHENG Wei,YANG Ying,HUI Li, LU Cheng-jie,ZHAO Bin,YANG Li. The analysis between wave estimation error and influencing factors based on BP model when ADCP tilts[J]. SHANDONG SCIENCE, 2018, 31(3): 1-7.

参考文献

［1］刘彦祥.ADCP技术发展及其应用综述[J]. 海洋测绘, 2016, 36(2): 4549.
［2］周庆伟，张松，武贺，等. 海洋波浪观测技术综述[J]. 海洋测绘，2016, 36(2): 3944.
［3］DALLY W R, OSIECKI D A. Comparison of deepwater ADCP and NDBC buoy measurements to hindcast parameters[EB/OL]. [20170305]. http://www.waveworkshop.org/8thWaves/Papers/N3.pdf.
［4］WORK P A. Nearshore directional wave measurements by surfacefollowing buoy and acoustic Doppler current profiler[J]. Ocean Engineering, 2008,35(8/9): 727737.
［5］Teledyne RD Instruments. WaveMon v3.06 User’s Guide[EB/OL]. [20170305]. http://new.commtec.com/Docs/Manuali/RDI/WavesMon%20Users%20Guide.pdf.
［6］郑威，杨立，惠力，等. ADCP方向谱估计的倾斜修正算法研究[ J]. 山东科学，2014,27（4）: 17.
［7］郑威，张殿伦，孙大军. 姿态传感器在坐底式ADCP波阵列中的应用[J]. 传感器与微系统，2011，30（6）: 119125.
［8］BRUMLEY B H,TERRAY E A,STRONG B S. System and method for measuring wave directional spectrum and wave height：US，6052334 [P]. 20000418.
［9］KROGSTAD H E. Maximum likelihood estimation of ocean wave spectra from general arrays of wave gauges[J]. Modeling, Identification and Control. 1988, 9(2): 8197.
［10］SCOTTI A,BUTMAN B, BEARDSLEY R C.et al. A modified beamtoearth transformation to measure shortwavelength internal waves with an acoustic Doppler current profiler(ADCP)[J]. Journal of Atmospheric and Oceanic Technology, 2005,22(5):583.
［11］RD instruments. ADCP coordinatetransformation: Formulas and calculations[EB/OL]. [20170305]. https://wiki.oceannetworks.ca/download/attachments/20480039/adcp%20coordinate%20transformation_Jan10.pdf?api=v2.
［12］杨茜.BP神经网络预测方法的改进及其在隧道长期沉降预测中的应用[J]. 北京工业大学学报，2011, 37(1): 9297.
［13］崔东文.多隐含层BP神经网络模型在径流预测中的应用[J]. 水文, 2013, 33(1): 6872.

基于BP神经网络模型的ADCP倾斜条件下的修正算法研究

The analysis between wave estimation error and influencing factors based on BP model when ADCP tilts

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

Metrics

本文评价

推荐阅读 0