Journal of Applied Optics, Volume. 43, Issue 3, 532(2022)

Morphology identification of dendrites of laser cladding layer based on deep learning

Shirui GUO... Kaixiang WANG, Lujun CUI, Xiaolei LI, Bo ZHENG and Yongqian CHEN |Show fewer author(s)
Author Affiliations
  • School of Mechanical and Electrical Engineering, Zhongyuan University of Technology, Zhengzhou 450007, China
  • show less
    Figures & Tables(7)
    Structure diagram of BNC-Unet network
    Structure diagram of serial attention model
    Data set
    Schematic diagram of confusion matrix
    Comparison graphics of each network output
    • Table 1. Feature map indexes

      View table
      View in Article

      Table 1. Feature map indexes

      组别通道数大小 /(像素×像素)
      116128×128
      23264×64
      36432×32
      412816×16
    • Table 2. Comparison of Loss and IoU network results of different improved methods

      View table
      View in Article

      Table 2. Comparison of Loss and IoU network results of different improved methods

      网络架构LossIoU/%
      Unet0.066 675.23
      BN-Unet0.065 881.05
      CBAM-Unet0.066 275.37
      BNC-Unet0.059 184.20
    Tools

    Get Citation

    Copy Citation Text

    Shirui GUO, Kaixiang WANG, Lujun CUI, Xiaolei LI, Bo ZHENG, Yongqian CHEN. Morphology identification of dendrites of laser cladding layer based on deep learning[J]. Journal of Applied Optics, 2022, 43(3): 532

    Download Citation

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

    Category: LASER TECHNOLOGY

    Received: Nov. 26, 2021

    Accepted: --

    Published Online: Jun. 7, 2022

    The Author Email:

    DOI:10.5768/JAO202243.0307001

    Topics