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

Acta Optica Sinica, Volume. 40, Issue 22, 2212004(2020)

Crack Diagnosis Method of Wind Turbine Blade Based on Convolution Neural Network with 3D Vibration Information Fusion

Yingfu Guo1, Weiming Quan1, Wenyun Wang2、*, Hao Zhou1, and Longzhou Zou1
Author Affiliations
  • 1Electromechanic Engineering College, Hunan University of Science and Technology, Xiangtan, Hunan 411201, China
  • 2Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Xiangtan, Hunan 411201, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (0)
    References (23)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    Binocular stereo imaging model

    Fig. 1. Binocular stereo imaging model

    Download full size
    Flow chart for making samples

    Fig. 2. Flow chart for making samples

    Download full size
    Improved CNN model

    Fig. 3. Improved CNN model

    Download full size
    Photogrammetry experiment chart. (a) Binocular high-speed camera measuring instrument; (b) wind turbine blade; (c) labels for different cracks; (d) code identification map

    Fig. 4. Photogrammetry experiment chart. (a) Binocular high-speed camera measuring instrument; (b) wind turbine blade; (c) labels for different cracks; (d) code identification map

    Download full size
    Vibration displacement curves of No.5 coded marker. (a) X direction; (b) Y direction; (c) Z direction

    Fig. 5. Vibration displacement curves of No.5 coded marker. (a) X direction; (b) Y direction; (c) Z direction

    Download full size
    Image samples. (a) YPA; (b) YPB; (c) YPC; (d) YPD; (e) YPE; (f) YPF; (g) YPG; (h) YPH

    Fig. 6. Image samples. (a) YPA; (b) YPB; (c) YPC; (d) YPD; (e) YPE; (f) YPF; (g) YPG; (h) YPH

    Download full size
    Image samples. (a) YPA; (b) YPB; (c) YPC; (d) YPD; (e) YPE; (f) YPF; (g) YPG; (h) YPH

    Fig. 7. Image samples. (a) YPA; (b) YPB; (c) YPC; (d) YPD; (e) YPE; (f) YPF; (g) YPG; (h) YPH

    Download full size
    Train accuracy. (a) Experiment 1; (b) experiment 2; (c) experiment 3

    Fig. 8. Train accuracy. (a) Experiment 1; (b) experiment 2; (c) experiment 3

    Download full size
    Confusion matrix for experiment 1. (a) Method 1; (b) method 2; (c) method 7

    Fig. 9. Confusion matrix for experiment 1. (a) Method 1; (b) method 2; (c) method 7

    Download full size

    • Table 1. Structural parameters of the proposed CNN model

      View table

      Table 1. Structural parameters of the proposed CNN model

      LayerKernel or filter size, output channelOutput size
      Convolution1×1, 24294×294×24
      Convolution11×11, 2459×59×24
      Max pooling3×3, 2430×30×24
      Convolution5×5, 6430×30×64
      Max pooling3×3, 6415×15×64
      Convolution3×3, 6415×15×96
      Convolution3×3, 9615×15×96
      Convolution3×3, 9615×15×64
      Max pooling2×2, 648×8×64
      Fully connected,dropout512, 0.564
      Fully connected,dropout512, 0.564
      Fully connected, SoftMax88

    • Table 2. Contrast results of experiments

      View table

      Table 2. Contrast results of experiments

      MethodMean accuracy /%Training time /s
      CNN (unfusion-signal)76.62323.45
      CNN (fusion-signal)89.54327.82
      LeNet-5 (fusion-signal)89.16423.59
      VGG11 (fusion-signal)92.271162.19
      Proposed-CNN (fusion-signal_A)93.24548.27
      Proposed-CNN (fusion-signal_B)93.32552.36
      Proposed-CNN (fusion-signal)93.41559.21
    Tools

    Get Citation

    Copy Citation Text

    Yingfu Guo, Weiming Quan, Wenyun Wang, Hao Zhou, Longzhou Zou. Crack Diagnosis Method of Wind Turbine Blade Based on Convolution Neural Network with 3D Vibration Information Fusion[J]. Acta Optica Sinica, 2020, 40(22): 2212004

    Download Citation

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

    Category: Instrumentation, Measurement and Metrology

    Received: Jun. 23, 2020

    Accepted: Aug. 3, 2020

    Published Online: Oct. 25, 2020

    The Author Email: Wang Wenyun (wwy73210693@163.com)

    DOI:10.3788/AOS202040.2212004

    Topics

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