Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 60, Issue 23, 2314009(2023)

MLP Neural Network-Based Detection System for Rust Removal by Laser

Rui Yi1, Chunming Wang1, Wei Zhang2, and Jun Wang3、*
Author Affiliations
  • 1School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, Hubei, China
  • 2School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, Hubei, China
  • 3School of Mechanical Engineering and Automation, Wuhan Textile University, Wuhan 430200, Hubei, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (7)
    References (23)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    Schematic diagram of laser derusting computer vision detection system

    Fig. 1. Schematic diagram of laser derusting computer vision detection system

    Download full size
    Structure of neural network

    Fig. 2. Structure of neural network

    Download full size
    Training process and results of MLP network with different number of hidden layers. (a) Error curves; (b) training results

    Fig. 3. Training process and results of MLP network with different number of hidden layers. (a) Error curves; (b) training results

    Download full size
    Single galvanometer beam scanning system

    Fig. 4. Single galvanometer beam scanning system

    Download full size
    Image processing results. (a) ROI before opening-operation; (b) ROI after opening-operation

    Fig. 5. Image processing results. (a) ROI before opening-operation; (b) ROI after opening-operation

    Download full size
    Rust samples in different states (left) and base plate samples (right)

    Fig. 6. Rust samples in different states (left) and base plate samples (right)

    Download full size
    Different rust images. (a) Sample A taken under professional LED light source; (b) sample B taken under professional LED light source; (c) sample B taken under natural light; (d) sample B taken under uneven light

    Fig. 7. Different rust images. (a) Sample A taken under professional LED light source; (b) sample B taken under professional LED light source; (c) sample B taken under natural light; (d) sample B taken under uneven light

    Download full size
    Image processing results of different rusts. (a1)‒(d1) are MLP rust identification results of Fig. 7(a)‒(d), respectively; (a2)‒(d2) are ROI of (a1)‒(d1), respectively

    Fig. 8. Image processing results of different rusts. (a1)‒(d1) are MLP rust identification results of Fig. 7(a)‒(d), respectively; (a2)‒(d2) are ROI of (a1)‒(d1), respectively

    Download full size
    Results of laser cleaning. (a) Sample A; (b) sample B

    Fig. 9. Results of laser cleaning. (a) Sample A; (b) sample B

    Download full size

    • Table 1. Chemical composition of Q345 steel

      View table

      Table 1. Chemical composition of Q345 steel

      ElementCMnSiPSV
      Mass fraction /%<0.2<1.7<0.55<0.045<0.045<0.15

    • Table 2. Coverage and misrecognition rate of rust identification results

      View table

      Table 2. Coverage and misrecognition rate of rust identification results

      GroupCoverage rate /%Misrecognition rate /%
      a99.391.03
      b96.870.13
      c95.052.03
      d98.025.96
    Tools

    Get Citation

    Copy Citation Text

    Rui Yi, Chunming Wang, Wei Zhang, Jun Wang. MLP Neural Network-Based Detection System for Rust Removal by Laser[J]. Laser & Optoelectronics Progress, 2023, 60(23): 2314009

    Download Citation

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

    Category: Lasers and Laser Optics

    Received: Oct. 26, 2022

    Accepted: Dec. 12, 2022

    Published Online: Dec. 11, 2023

    The Author Email: Wang Jun (wangjunwuhan@163.com)

    DOI:10.3788/LOP222896

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology