Chinese Journal of Ship Research, Volume. 19, Issue 6, 82(2024)

Research on multi-fidelity surrogate modeling method for non-hierarchical low-fidelity analysis model problem

Meng CHENG1... Qi ZHOU2, Xiao WEI1, Jian WANG1 and Wei CHEN1 |Show fewer author(s)
Author Affiliations
  • 1China Ship Development and Design Center, Wuhan 430064, China
  • 2School of Aerospace Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
  • show less
    Figures & Tables(21)
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    • Table 1. Prediction accuracy comparison of different MFS modeling methods

      View table
      View in Article

      Table 1. Prediction accuracy comparison of different MFS modeling methods

      方法eMAEeRMSE
      VWS-MFS1.411 20.441 8
      VWS-HK3.654 51.495 6
      LR-MFS2.315 20.702 1
      MLMF-CK7.418 62.552 6
      IHK5.788 32.208 8
    • Table 2. Features of eight numerical examples

      View table
      View in Article

      Table 2. Features of eight numerical examples

      序号维度低精度分析模型数目非线性程度样本点配置
      1d=125H/10L1/10L2
      2d=2210H/20L1/20L2
      3d=2310H/30L1/30L2
      4d=4220H/30L1/30L2
      5d=4340H/80L1/80L2/80L3
      6d=6360H/120L1/120L2/120L3
      7d=82150H/300L1/300L2
      8d=103200H/400L1/400L2/400L3
    • Table 3. Prediction accuracy comparison of different MFS modeling methods

      View table
      View in Article

      Table 3. Prediction accuracy comparison of different MFS modeling methods

      算例序号参数VWS-MFSVWS-HKLR-MFSMLMF-CK
      1eMAE0.1931.0272.9751.792
      eRMSE0.0490.3500.9451.278
      2eMAE2.2244.4324.81925.066
      eRMSE0.7111.1200.9696.605
      3eMAE0.0030.0150.0910.150
      eRMSE0.0010.0030.1060.040
      4eMAE0.4980.5581.1026.453
      eRMSE0.0780.0950.1991.211
      5eMAE16 169.53535 696.463102 872.46496 953.487
      eRMSE2 704.8724 534.14519 979.14220 271.358
      6eMAE1.0202.6228.16511.309
      eRMSE0.1970.2992.1842.047
      7eMAE619.427726.884840.1494 987.921
      eRMSE58.82069.50191.237191.103
      8eMAE8.501×1073.300×1087.128×1096.028×1011
      eRMSE7.851×1063.157×1078.909×1076.972×1010
    • Table 4. Value ranges of design variables

      View table
      View in Article

      Table 4. Value ranges of design variables

      设计变量物理意义取值范围/m
      X1斜臂长度L[0.015 0, 0.020 0]
      X2竖梁厚度Th[0.005 0, 0.010 0]
      X3斜梁厚度Tl[0.003 5, 0.010 0]
    • Table 5. Relevance between HF/LF analysis models

      View table
      View in Article

      Table 5. Relevance between HF/LF analysis models

      性能分析模型相关度
      HF-LF1HF-LF2
      最大应变0.998 30.998 7
    • Table 6. Prediction accuracy comparison of different MFS models

      View table
      View in Article

      Table 6. Prediction accuracy comparison of different MFS models

      方法eMAEeRMSE
      VWS-MFS0.013 10.002 6
      VWS-HK0.016 00.005 1
      LR-MFS0.024 50.008 3
      MLMF-CK0.041 3*0.012 2*
    Tools

    Get Citation

    Copy Citation Text

    Meng CHENG, Qi ZHOU, Xiao WEI, Jian WANG, Wei CHEN. Research on multi-fidelity surrogate modeling method for non-hierarchical low-fidelity analysis model problem[J]. Chinese Journal of Ship Research, 2024, 19(6): 82

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Theory and Method of Intelligent Design for Ship and Ocean Engineering

    Received: May. 30, 2024

    Accepted: --

    Published Online: Mar. 14, 2025

    The Author Email:

    DOI:10.19693/j.issn.1673-3185.03980

    Topics