三维荧光光谱结合稀疏主成分分析和支持向量机的油类识别方法研究

doi:10.3964/j.issn.1000-0593(2021)11-3474-06

Abstract
References
Related Citation (15)

Download: PDF (2274 KB)
Export: BibTeX | EndNote (RIS)

Abstract The emergence of oil pollution has destroyed the ecological environment. Therefore, the study of oil identification methods is of great significance to the protection of the environment. Petroleum spectrum data can be obtained by fluorescence spectroscopy. At the same time, the spectrum data is preprocessed, and feature information is extracted by dimensionality reduction. Then the pattern recognition algorithm is used for classification, it can realize the qualitative analysis of oil. However, it is vital to study a more efficient way of data dimensionality reduction and recognition algorithms. Based on the three-dimensional fluorescence spectroscopy technology, this paper uses sparse principal component analysis (SPCA) to extract the features of the fluorescence spectrum data measured by the FS920 spectrometer, and the support vector machine (SVM) algorithm applies for classification and recognition, thereby a more efficient oil identification method is obtained. First, seawater and sodium dodecyl sulfate (SDS) was prepared into a micelle solution with a concentration of 0.1 mol·L^-1. It was used as a solvent to prepare solutions of 20 different concentrations of 4 kinds of oil: Diesel oil, Jet fuel, Gasoline and Lubricating oil. Then, the three-dimensional fluorescence spectrum was measured by the FS920 spectrometer, and the data schould be preprocessed. Finally, the pre-processed data is extracted using SPCA, and principal component analysis (PCA), and the feature vectors are classified by SVM and K-nearest neighbor (KNN) two pattern recognition algorithms, the classification results of four models PCA-KNN, SPCA-KNN, PCA-SVM and SPCA-SVM are obtained. The research results show that the classification accuracy rates obtained by the four models are 85%, 90%, 90% and 95% respectively. In the same classification algorithm, the classification accuracy obtained by using SPCA is 5% higher than that of PCA. Therefore, SPCA can better highlight the main components in its sparsity, and the sparsity of the load matrix can remove redundant information between variables, achieve the optimization of dimensionality reduction, and provide a better classification for subsequent classification. Effective data feature information; Under the same feature extraction algorithm, the classification accuracy rate obtained by using the SVM algorithm for classification is 5% higher than the accuracy rate obtained by the KNN algorithm, it shows that the SVM algorithm has more advantages in classification. Therefore, this paper uses three-dimensional fluorescence spectroscopy technology combined with SPCA and SVM algorithms to accurately identify petroleum, which provides a new idea for the efficient detection of petroleum pollutants in the future.

Key words：Three-dimensional fluorescence spectrum; Feature extraction; Sparse principal component analysis; Support vector machine

Received: 2020-10-14 Accepted: 2021-02-15

ZTFLH:

O433.4

Corresponding Authors: CHEN Xiao-yu E-mail: chenxiaoyu@ysu.edu.cn

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2021)11-3474-06 OR https://www.gpxygpfx.com/EN/Y2021/V41/I11/3474

[1] Loh Andrew, Ha Sung Yong, An Joon Geon, et al. Marine Pollution Bulletin, 2019, 138(Jan. ): 328.
[2] LIU Hui, YUAN Xing-qi, WANG Juan, et al(刘慧, 袁兴启, 王娟, 等). Physical Testing and Chemical Analysis Part B(Chemical Analysis)(理化检验·化学分册), 2018, 54(2): 241.
[3] DU Yun, ZHENG Ya-nan, WANG Shu-tao(杜云, 郑亚南, 王书涛). Optics and Precision Engineering(光学精密工程), 2018, 26(9): 2213.
[4] XU Li, ZHANG Zhi-rong, DONG Feng-zhong, et al(许丽, 张志荣, 董凤忠, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2019, 56(19): 193003.
[5] CHEN Zhi-kun, GUO Rui, CHENG Peng-fei(陈至坤, 郭蕊, 程朋飞). Laser & Optoelectronics Progress(激光与光电子学进展), 2020, 57(13): 133002.
[6] Jana Sádecká, Michaela Jakubíková, Pavel Májek. Food Control, 2018, 88: 75.
[7] LI Jie, LI Xiao-long, TANG Qiu-hua, et al(李杰, 李晓龙, 唐秋华, 等). Optics and Precision Engineering(光学精密工程), 2017, 25(4): 352.
[8] WANG Lei, NIE Hui(王磊, 聂晖). Instrument Technique and Sensor(仪表技术与传感器), 2017，(9): 94.
[9] GUI Dong-dong, LU Qi, JIN Can-can, et al(桂冬冬, 鲁齐, 金灿灿, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(S1): 133.
[10] FU Jian-hua, ZHOU Xin-qi, LIU Hui-jun, et al(付建华, 周新奇, 刘辉军, 等). Physical Testing and Chemical Analysis Part B(Chemical Analysis)(理化检验·化学分册), 2017, 53(2): 146.
[11] Wu Xijun, Zhao Zhilei, Tian Ruiling, et al. Food Chemistry, 2020, 311: 125882.
[12] WANG Shu-tao, WU Xing, ZHU Wen-hao, et al(王书涛, 吴兴, 朱文浩, 等). Acta Optica Sinica(光学学报), 2019, 39(5): 0530002.
[13] CHEN Ying, ZHANG Can, XIAO Chun-yan, et al(陈颖, 张灿, 肖春艳, 等). Acta Optica Sinica(光学学报), 2020, 40(10): 1030002.
[14] Santos M C D, Azcarate S M, Lima K M G, et al. Microchemical Journal, 2020, 155: 104783.