Study on Oil Identification Method Based on Three-Dimensional Fluorescence Spectrum Combined With Two-Dimensional Linear Discriminant Analysis

De-ming KONG; Rui DONG; Yao-yao CUI; Shu-tao WANG; Hui-chao SHI

doi:10.3964/j.issn.1000-0593(2021)08-2505-06

Spectroscopy and Spectral Analysis, Volume. 41, Issue 8, 2505(2021)

Study on Oil Identification Method Based on Three-Dimensional Fluorescence Spectrum Combined With Two-Dimensional Linear Discriminant Analysis

De-ming KONG^1、*, Rui DONG^1、1;, Yao-yao CUI^{2、2; *;}, Shu-tao WANG^1、1;, and Hui-chao SHI^3、3;

Author Affiliations

¹1. School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China

²2. School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China

³3. School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(6)

Fig. 1. Three-dimensional fluorescence spectrum of lubricating oil
(a): Before removing scattering; (b): After removing scattering

Download full size

View in Article

Fig. 2. Original emission and excitation spectrum of lubricating oil and characteristics of training sample obtained by projection vector
(a): Emission spectrum; (b): Excitation spectrum; (c): First emission characteristic; (d): Second emission characteristic; (e): First excitation characteristic; (f): Second excitation characteristic

Download full size

View in Article

Fig. 3. First three principal component score

Download full size

View in Article

Table 1. Contribution rate of principal component
View table
View in Article
Table 1. Contribution rate of principal component
Principal component Contribution rate/%
PC1 66.52
PC2 19.63
PC3 4.61
PC4 3.12
PC5 2.61
PC6 0.92
PC7 0.34
PC8 0.27
PC9 0.26
PC10 0.23

Table 2. Classification results after 2D-LDA characteristics extraction
View table
View in Article
Table 2. Classification results after 2D-LDA characteristics extraction
emission excitation
D J G L D J G L
D 4 0 0 0 3 0 0 1
J 0 3 0 0 0 3 0 0
G 0 1 4 0 0 0 5 0
L 0 0 0 8 0 0 0 8
SENS/% 100 100 80 100 75 100 100 100
SPEC/% 100 94 100 100 100 100 100 92
ACC/% 100 100 80 100 75 100 100 100

Table 3. Classification result after principal component characteristic extraction
View table
View in Article
Table 3. Classification result after principal component characteristic extraction
D J G L Acc/%
D 3 0 0 1 75
J 0 3 0 0 100
G 0 0 4 1 80
L 0 1 0 7 87.5
SENS/% 75 100 80 88
SPEC/% 100 94 100 83

Tools

Get Citation

Copy Citation Text

De-ming KONG, Rui DONG, Yao-yao CUI, Shu-tao WANG, Hui-chao SHI. Study on Oil Identification Method Based on Three-Dimensional Fluorescence Spectrum Combined With Two-Dimensional Linear Discriminant Analysis[J]. Spectroscopy and Spectral Analysis, 2021, 41(8): 2505

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites