• Acta Photonica Sinica
  • Vol. 50, Issue 12, 1212004 (2021)
Li ZHENG, Chuang LIU*, Jiaojiao REN, Dandan ZHANG, Lijuan LI, and Jisheng XU
Author Affiliations
  • Key Laboratory of Optoelectronic Measurement and Control and Optical Information Transmission Technology of Ministry of Education, College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun 130022, China
  • show less
    DOI: 10.3788/gzxb20215012.1212004 Cite this Article
    Li ZHENG, Chuang LIU, Jiaojiao REN, Dandan ZHANG, Lijuan LI, Jisheng XU. Debonding Defect Identification Method for Multi-layer Bonded Structures Based on LDA-CPSO-SVM Optimization[J]. Acta Photonica Sinica, 2021, 50(12): 1212004 Copy Citation Text show less
    Design drawings of multilayer bonded structure samplesⅠand Ⅱ
    Fig. 1. Design drawings of multilayer bonded structure samplesⅠand Ⅱ
    Experimental terahertz time domain spectral system
    Fig. 2. Experimental terahertz time domain spectral system
    Terahertz time domain waveform of different regions of multilayer adhesive structure
    Fig. 3. Terahertz time domain waveform of different regions of multilayer adhesive structure
    Subject operating curves of different sample types
    Fig. 4. Subject operating curves of different sample types
    Classification rate fitness curve of adhesive layer I data
    Fig. 5. Classification rate fitness curve of adhesive layer I data
    Classification rate fitness curve of adhesive layer data
    Fig. 6. Classification rate fitness curve of adhesive layer data
    Terahertz single feature image of multi-bonded structural adhesive layer
    Fig. 7. Terahertz single feature image of multi-bonded structural adhesive layer
    Imaging image of multi-bonded structural adhesive layer based on LDA-CPSO-SVM algorithm
    Fig. 8. Imaging image of multi-bonded structural adhesive layer based on LDA-CPSO-SVM algorithm
    Sample typeThe accuracy of different kernel function types
    Liner SVMQuadratic SVMCubic SVMFine Gaussian SVMMedium Gaussian SVMCoarse Gaussian SVM
    Layer I normal85.22%86.51%84.34%88.95%96.13%94.66%
    Layer I defect86.45%87.36%89.65%88.39%99.43%98.9%
    Layer I edge85.85%86.37%89.32%89.67%98.34%97.67%
    LayerⅡnormal86.27%87.57%90.34%91.98%95.14%97.66%
    LayerⅡdefect83.42%89.35%88.66%90.38%98.49%98.96%
    LayerⅡedge81.84%86.2%88.33%91.66%96.3%97.37%
    Table 1. Classification rate of different kernel function types
    Li ZHENG, Chuang LIU, Jiaojiao REN, Dandan ZHANG, Lijuan LI, Jisheng XU. Debonding Defect Identification Method for Multi-layer Bonded Structures Based on LDA-CPSO-SVM Optimization[J]. Acta Photonica Sinica, 2021, 50(12): 1212004
    Download Citation