Exploring representative samples for modeling of wave buoy motion behavior

被引:0
作者
Deng, Hongying [1 ]
Zhu, Jialiang [1 ]
Li, Xintian [2 ,3 ]
Liu, Yi [1 ]
机构
[1] Zhejiang Univ Technol, Inst Proc Equipment & Control Engn, Hangzhou 310023, Peoples R China
[2] Hangzhou Appl Acoust Res Inst, Hangzhou 310023, Peoples R China
[3] Hangzhou Ruili Marine Equipment Co LTD, Hangzhou 310023, Peoples R China
基金
中国国家自然科学基金;
关键词
Buoy motion behavior; Ocean environment; Sample exploring; Probabilistic information; Gaussian process regression; POWER;
D O I
10.1016/j.oceaneng.2024.117259
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
To collect sufficient data to describe buoy motion behavior in extreme environment conditions is intractable. The conventional data-driven models constructed with randomly selected and limited training samples are unable to perform adequately for exhibiting complex dynamic characteristics. In this work, an active sample exploring strategy is developed to build a reliable prediction model with limited samples. First, an evaluated index is designed to depict both the data distribution characteristics and estimation uncertainty of all test data using a probabilistic model. The representative data are then captured and integrated into the initial training set based on this index, and the updated uncertainty information is used as the criterion to judge the exploring termination. Finally, the initial training set is supplemented to enhance the model performance. Experimental and comparative results demonstrate the superiority of the proposed sample exploring strategy.
引用
收藏
页数:10
相关论文
共 35 条
  • [1] Numerical studies on CALM buoy motion responses and the effect of buoy geometry cum skirt dimensions with its hydrodynamic waves-current interactions
    Amaechi, Chiemela Victor
    Wang, Facheng
    Ye, Jianqiao
    [J]. OCEAN ENGINEERING, 2022, 244
  • [2] Machine learning for characterizing tropical tuna aggregations under Drifting Fish Aggregating Devices (DFADs) from commercial echosounder buoys data
    Baidai, Y.
    Dagorn, L.
    Amande, M. J.
    Gaertner, D.
    Capello, M.
    [J]. FISHERIES RESEARCH, 2020, 229
  • [3] Influence of the shape of a buoy on the efficiency of its dual-motion wave energy conversion
    Berenjkoob, Mahdi Nazari
    Ghiasi, Mahmoud
    Soares, C. Guedes
    [J]. ENERGY, 2021, 214
  • [4] Impact of heavy biofouling on a nearshore heave-pitch-roll wave buoy performance
    Campos, Ricardo M.
    Islam, Hafizul
    Ferreira, Tobias R. S.
    Soares, C. Guedes
    [J]. APPLIED OCEAN RESEARCH, 2021, 107
  • [5] Transfer learning for modeling and prediction of marine buoy motion characteristics
    Deng, Hongying
    Li, Xintian
    Zhu, Jialiang
    Liu, Yi
    [J]. OCEAN ENGINEERING, 2022, 266
  • [6] Multistage hybrid model for performance prediction of centrifugal pump
    Deng, Hongying
    Xia, Zhaoshun
    Sun, Zenan
    Zheng, Shuihua
    Liu, Yi
    [J]. ADVANCES IN ENGINEERING SOFTWARE, 2022, 174
  • [7] Actively Exploring Informative Data for Smart Modeling of Industrial Multiphase Flow Processes
    Deng, Hongying
    Yang, Keyun
    Liu, Yi
    Zhang, Shengchang
    Yao, Yuan
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (12) : 8357 - 8366
  • [8] Active learning for modeling and prediction of dynamical fluid processes
    Deng, Hongying
    Liu, Yi
    Li, Ping
    Zhang, Shengchang
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2018, 183 : 11 - 22
  • [9] Oceanographic wave buoy motion as a 3D-vector field: Spectra, linear components and bound harmonics
    Ding, Yue
    Taylor, Paul H.
    Zhao, Wenhua
    Dory, Jean-Noel
    Hlophe, Thobani
    Draper, Scott
    [J]. APPLIED OCEAN RESEARCH, 2023, 141
  • [10] Active label distribution learning via kernel maximum mean discrepancy
    Dong, Xinyue
    Luo, Tingjin
    Fan, Ruidong
    Zhuge, Wenzhang
    Hou, Chenping
    [J]. FRONTIERS OF COMPUTER SCIENCE, 2023, 17 (04)