Chinese Journal of Ship Research, Volume. 19, Issue 6, 108(2024)

Topology optimization analysis of VLCC transverse web based on UNet deep learning

Zhenrong LI1,2, Lijuan XIA1,2, and Shuo FENG1,2
Author Affiliations
  • 1State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • 2School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • show less
    Figures & Tables(17)
    [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. Composition of the dataset

      View table
      View in Article

      Table 1. Composition of the dataset

      分类数量比例/%
      训练集19 20080
      验证集2 40010
      测试集2 40010
    • Table 2. IoU evaluation of partial test data

      View table
      View in Article

      Table 2. IoU evaluation of partial test data

      SIMP法获得的拓扑构型真实结果UNet 预测结果IoU评估
    • Table 3. Comparison of topology configurations of UNet and SIMP method

      View table
      View in Article

      Table 3. Comparison of topology configurations of UNet and SIMP method

      体积分数约束值拓扑构型
      SIMP法UNet法
      13%
      22%
      27%
    • Table 4. Dataset creation time

      View table
      View in Article

      Table 4. Dataset creation time

      单个算例SIMP拓扑优化时长/s算例个数生成数据集总时长/h
      1786 000297
    • Table 5. The comparison of computational time between UNet and SIMP methods in the application scenarios

      View table
      View in Article

      Table 5. The comparison of computational time between UNet and SIMP methods in the application scenarios

      方法静力计算时长/s拓扑优化计算时长/s计算总时长/s
      SIMP178178
      UNet50.75.7
    Tools

    Get Citation

    Copy Citation Text

    Zhenrong LI, Lijuan XIA, Shuo FENG. Topology optimization analysis of VLCC transverse web based on UNet deep learning[J]. Chinese Journal of Ship Research, 2024, 19(6): 108

    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: Sep. 11, 2023

    Accepted: --

    Published Online: Mar. 14, 2025

    The Author Email:

    DOI:10.19693/j.issn.1673-3185.03553

    Topics