Spectroscopy and Spectral Analysis, Volume. 41, Issue 8, 2638(2021)
Rapid Classification of Steel by a Mobile Laser-Induced Breakdown Spectroscopy Based on Optical Fiber Delivering Laser Energy
Figures & Tables(9)
Fig. 5. The SVM prediction results using selecting 6 special spectral lines
Table 1. The concentration information of each element in 14 types of steel samples
View tableView in ArticleTable 1. The concentration information of each element in 14 types of steel samples
编号 C Mn Si P Cr Ni Mo V Cu 1 0.09 0.44 0.33 0.007 8.64 0.2 0.9 0.19 0.11 2 0.12 0.50 0.26 0.006 1.10 0.18 0.27 0.2 0.09 3 0.20 0.25 0.29 0.005 2.57 0.2 0.35 0.02 0.07 4 0.16 0.93 0.37 0.007 0.24 1.12 0.31 0.004 0.58 5 0.41 0.54 0.19 0.019 0.94 0.02 0.17 0.006 0.03 6 0.38 0.77 0.24 0.021 1.02 0.02 0.2 0.005 0.02 7 0.11 0.47 0.37 0.005 2.13 0.15 0.94 0 0 8 0.26 0.65 0.22 0.018 0 0 0 0 0 9 0.19 1.57 0.31 0.021 0 0 0 0.002 0 10 0.374 0.372 0.292 0.0053 1.524 1.419 0.251 0 0.074 11 0.422 0.66 0.349 0.021 1.05 0.066 0.195 0.012 0.063 12 0.399 0.365 1 0.013 5.02 0.281 1.14 0.789 0.094 13 0.15 1.05 0.377 0.01 0.117 1.17 0.384 0 0.605 14 0.107 0.333 0.327 0.008 8.22 0.123 0.9 0.236 0.115
Table 2. The selected emission lines
View tableView in ArticleTable 2. The selected emission lines
Element Wavelength(λ/nm) Ni 300.249, 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 Cr 357.868, 359.348, 425.433, 427.481, 428.973 Mn 380.672, 403.176, 403.307, 403.449, 404.136 Mo 315.817, 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 V 318.341, 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 3. The 6 spectral lines with SVM prediction accuracy of 100%
View tableView in ArticleTable 3. The 6 spectral lines with SVM prediction accuracy of 100%
Element Wavelength(λ/nm) Mn 403.307 Mo 386.410 V 385.584 Cr 427.481, 357.868 Ni 352.454
Table 4. The average prediction accuracy and mean modeling time of SVM with different inputs
View tableView in ArticleTable 4. The average prediction accuracy and mean modeling time of SVM with different inputs
Input Average prediction
accuracy/%Mean
modeling time/sPreselected spectral data 11.43 0.0173 23 Normalized data 95.71 0.018 579 Optimal data of traversal 100 0.0108 56
Tools
Get Citation
Copy Citation Text
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
Paper Information
Category: Research Articles
Received: Aug. 4, 2020
Accepted: --
Published Online: Sep. 8, 2021
The Author Email: LI Wen-xin (3300144190@qq.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20