• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 8, 2638 (2021)
Wen-xin LI1、*, Guang-hui CHEN1、1; 3;, Qing-dong ZENG1、1; 2; *;, Meng-tian YUAN1、1; 3;, Wu-guang HE1、1;, Ze-fang JIANG1、1;, Yang LIU1、1;, Chang-jiang NIE1、1;, Hua-qing YU1、1;, and Lian-bo GUO2、2;
Author Affiliations
  • 11. School of Physics and Electronic-Information Engineering, Hubei Engineering University, Xiaogan 432000, China
  • 22. Wuhan National Laboratory for Optoelectronics (WNLO), Huazhong University of Science and Technology, Wuhan 430074, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)08-2638-06 Cite this Article
    Wen-xin LI, Guang-hui CHEN, Qing-dong ZENG, Meng-tian YUAN, Wu-guang HE, Ze-fang JIANG, Yang LIU, Chang-jiang NIE, Hua-qing YU, Lian-bo GUO. Rapid Classification of Steel by a Mobile Laser-Induced Breakdown Spectroscopy Based on Optical Fiber Delivering Laser Energy[J]. Spectroscopy and Spectral Analysis, 2021, 41(8): 2638 Copy Citation Text show less
    LIBS system(a): Schematic; (b): Prototype
    Fig. 1. LIBS system
    (a): Schematic; (b): Prototype
    The emission spectra of 14 types of special steel samples
    Fig. 2. The emission spectra of 14 types of special steel samples
    The prediction results by SVM
    Fig. 3. The prediction results by SVM
    The prediction results of normalized spectra by SVM
    Fig. 4. The prediction results of normalized spectra by SVM
    The SVM prediction results using selecting 6 special spectral lines
    Fig. 5. The SVM prediction results using selecting 6 special spectral lines
    编号CMnSiPCrNiMoVCu
    10.090.440.330.0078.640.20.90.190.11
    20.120.500.260.0061.100.180.270.20.09
    30.200.250.290.0052.570.20.350.020.07
    40.160.930.370.0070.241.120.310.0040.58
    50.410.540.190.0190.940.020.170.0060.03
    60.380.770.240.0211.020.020.20.0050.02
    70.110.470.370.0052.130.150.9400
    80.260.650.220.01800000
    90.191.570.310.0210000.0020
    100.3740.3720.2920.00531.5241.4190.25100.074
    110.4220.660.3490.0211.050.0660.1950.0120.063
    120.3990.36510.0135.020.2811.140.7890.094
    130.151.050.3770.010.1171.170.38400.605
    140.1070.3330.3270.0088.220.1230.90.2360.115
    Table 1. The concentration information of each element in 14 types of steel samples
    ElementWavelength(λ/nm)
    Ni300.249, 301.200, 305.082, 310.156, 313.410, 341.476, 344.626, 345.846, 346.165, 349.296, 351.505, 352.454, 356.637, 361.939
    Cr357.868, 359.348, 425.433, 427.481, 428.973
    Mn380.672, 403.176, 403.307, 403.449, 404.136
    Mo315.817, 317.034, 319.398, 320.884, 344.712, 378.825, 386.410, 390.295, 406.988, 418.832, 441.169, 550.649, 553.303, 557.044
    V318.341, 318.399, 318.538, 370.357, 385.584, 390.226, 411.518, 412.806, 413.199, 437.923, 438.471, 439.522, 440.850
    Table 2. The selected emission lines
    ElementWavelength(λ/nm)
    Mn403.307
    Mo386.410
    V385.584
    Cr427.481, 357.868
    Ni352.454
    Table 3. The 6 spectral lines with SVM prediction accuracy of 100%
    InputAverage prediction
    accuracy/%
    Mean
    modeling time/s
    Preselected spectral data11.430.0173 23
    Normalized data95.710.018 579
    Optimal data of traversal1000.0108 56
    Table 4. The average prediction accuracy and mean modeling time of SVM with different inputs
    Wen-xin LI, Guang-hui CHEN, Qing-dong ZENG, Meng-tian YUAN, Wu-guang HE, Ze-fang JIANG, Yang LIU, Chang-jiang NIE, Hua-qing YU, Lian-bo GUO. Rapid Classification of Steel by a Mobile Laser-Induced Breakdown Spectroscopy Based on Optical Fiber Delivering Laser Energy[J]. Spectroscopy and Spectral Analysis, 2021, 41(8): 2638
    Download Citation