• Acta Photonica Sinica
  • Vol. 51, Issue 4, 0430001 (2022)
Cheng XU1, Fang LI1、*, Feng CHEN2, Deng ZHANG2, Fan DENG3, and Lianbo GUO3
Author Affiliations
  • 1Hubei Key Laboratory of Optical Information and Pattern Recognition,School of Mechanical and Electrical Engineering,Wuhan Institute of Technology,Wuhan 430205,China
  • 2Wuhan National Laboratory for Optoelectronics,Huazhong University of Science and Technology,Wuhan 430074,China
  • 3College of Optical and Electronic Information,Huazhong University of Science and Technology,Wuhan 430074,China
  • show less
    DOI: 10.3788/gzxb20225104.0430001 Cite this Article
    Cheng XU, Fang LI, Feng CHEN, Deng ZHANG, Fan DENG, Lianbo GUO. Rapid Classification of Laser Induced Breakdown Spectroscopy of Titanium Alloys[J]. Acta Photonica Sinica, 2022, 51(4): 0430001 Copy Citation Text show less
    Diagram of experimental setup
    Fig. 1. Diagram of experimental setup
    Picture of TC4 titanium alloy
    Fig. 2. Picture of TC4 titanium alloy
    The change of peak intensity and signal to noise ratio with unit pulse energy
    Fig. 3. The change of peak intensity and signal to noise ratio with unit pulse energy
    The change of peak intensity and signal to noise ratio with trigger delay
    Fig. 4. The change of peak intensity and signal to noise ratio with trigger delay
    TC4-1 full spectrum
    Fig. 5. TC4-1 full spectrum
    Confusion matrix of training set of original spectrums after weighted KNN classification and confusion matrix of test set classification result
    Fig. 6. Confusion matrix of training set of original spectrums after weighted KNN classification and confusion matrix of test set classification result
    Confusion matrix of weighted KNN classification for spectral training set after data processing and confusion matrix of test set classification result
    Fig. 7. Confusion matrix of weighted KNN classification for spectral training set after data processing and confusion matrix of test set classification result
    Optimization results of three parameters
    Fig. 8. Optimization results of three parameters
    Training set confusion matrix of final classification result and confusion matrix of test set classification result
    Fig. 9. Training set confusion matrix of final classification result and confusion matrix of test set classification result
    MaterialNumberConcentration of element/%
    AlVFeSiCTi
    TC4-1GBW025033.905.560.390.280.1689.62
    TC4-2GBW025044.675.010.310.200.1289.69
    TC4-3GBW025055.383.410.240.120.1090.75
    TC4-4GBW025076.783.850.130.090.0289.13
    TC4KY-6.244.080.050.020.0189.60
    Table 1. Titanium alloy number and element content
    ElementWavelength/nmAk/S-1E1/eVE2/eV
    Al I394.4014.99×10703.14
    Al I396.1529.85×10703.14
    V II311.0711.58×1080.354.33
    V II355.6806.40×1071.134.61
    Ti I395.8204.88×1070.053.18
    Ti I399.8644.81×1070.053.15
    Table 2. Spectral wavelength,transition probability and energy level
    ElementAl IAl IIV IV IIFe II
    Wavelength/nm

    226.90

    396.15

    281.62

    411.15

    439.55

    268.87

    310.23

    319.07

    238.24

    259.99

    Table 3. Characteristic lines for spectral screening
    K-meansDecision treeNBCSVMKNN
    Training time/s43.8679.2878.9591.1883.91
    Training set cross validation accuracy/%53.3481.697.998.498.64
    Test set classification accuracy/%58.3182.9196.7998.599.14
    Table 4. Comparison of results between different algorithms
    Raw dataData processingKNN model optimization
    Training time/s1 232.4184.7983.91
    Training set cross validation accuracy/%81.4094.0098.64
    Test set classification accuracy/%84.2095.9299.14
    Table 5. Comparison of optimization results
    Cheng XU, Fang LI, Feng CHEN, Deng ZHANG, Fan DENG, Lianbo GUO. Rapid Classification of Laser Induced Breakdown Spectroscopy of Titanium Alloys[J]. Acta Photonica Sinica, 2022, 51(4): 0430001
    Download Citation