Online measurement of iron grade in iron concentrate slurry by LIBS based on SPA‐SVR model

ZHANG Qi; ZHANG Zhansheng; CHEN Tong; ZHANG Peng; QI Lifeng; SUN Lanxiang

doi:10.3969/j.issn.1007-5461.2024.03.015

Chinese Journal of Quantum Electronics, Volume. 41, Issue 3, 533(2024)

Online measurement of iron grade in iron concentrate slurry by LIBS based on SPA‐SVR model

ZHANG Qi^{1,2,3,4,5、*}, ZHANG Zhansheng¹, CHEN Tong^2,3,4,5,6, ZHANG Peng^2,3,4,5, QI Lifeng^2,3,4,5, and SUN Lanxiang^2,3,4,5,6

Author Affiliations

¹Shenyang University of Chemical Technology, Shenyang 110142, China

²State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China

³Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang 110016, China

⁴Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China

⁵Liaoning Liaohe Laboratory, Shenyang 110169, China

⁶University of Chinese Academy of Sciences, Beijing 100049, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. Schematic diagram of the SIA-LIBSlurry online slurry analysis system structure

Download full size

View in Article

Fig. 2. Flow chart of SPA algorithm

Download full size

View in Article

Fig. 3. Wavelength selected by CARS algorithm

Download full size

View in Article

Fig. 4. (a) Number of variables selected by SPA algorithm and their corresponding $E_{R M S_C V}$ ; (b) Wavelength variable selected by SPA algorithm

Download full size

View in Article

Fig. 5. Regression effect of (a) SVR model, (b) CARS-SVR model and (c) SPA-SVR model

Download full size

View in Article

Table 2. Selected 12 features of SPA
View table
View in Article
Table 2. Selected 12 features of SPA
Element Wavelength/nm
Fe 280.18, 302.03, 309.99, 317.89, 378.79, 440.47
Si 288.08
Ca 393.66
Na 589.59
N 746.83
其他元素 561.40, 615.81

Table 3. Prediction results of iron elements in iron ore slurry using SVR models established by various variable extraction methods
View table
View in Article
Table 3. Prediction results of iron elements in iron ore slurry using SVR models established by various variable extraction methods
Methods Number of variables Kernel C γ $E_{R M S_t r a i n}$ $E_{R M S_v a l}$ $E_{R M S_p r e d}$ ${R^{2}}_{p r e d}$
- 6116 RBF 10.0 0.003 1.42 1.39 1.52 0.23
CARS 231 RBF 10.0 0.082 1.02 1.08 1.11 0.59
SPA 12 RBF 10.0 1.733 0.80 0.86 0.97 0.69

Tools

Get Citation

Copy Citation Text

Qi ZHANG, Zhansheng ZHANG, Tong CHEN, Peng ZHANG, Lifeng QI, Lanxiang SUN. Online measurement of iron grade in iron concentrate slurry by LIBS based on SPA‐SVR model[J]. Chinese Journal of Quantum Electronics, 2024, 41(3): 533

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites