Classification and Identification of Oil-in-Water Light Oil Emulsions Based on LIF
CHEN Xiao-yu1, NING Xiao-dong1, LI Xin-yi2, DU Ya-xin1, KONG De-ming2*
1. Department of Electronic and Communication Engineering, School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China
2. Department of Instrument Science and Engineering, School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China
Abstract：Oil spills at sea are one of the important forms of Marine pollution. In weathering and migration, oil spills will form emulsions such as oil-in-water, water-in-oil, water-in-oil-in-water, and other emulsions. Among them, water molecules greatly affect oil-in-water emulsions, and their fluorescence characteristics are not prominent, making it difficult to classify and identify light oil emulsions. It has important significance for pollution control in the future. Several common light oils were selected to mix with seawater and emulsifiers in different proportions to prepare the light oil emulsion of the oil-in-water type. A convenient laser-induced fluorescence (LIF) system built in the laboratory was used to detect the fluorescence spectra of light oil emulsions. In this paper, the classification model of the sparrow search algorithm (SSA) optimized support vector machine (SVM) (from now on referred to as SSA-SVM) is constructed to realize the classification and identification of oil spill in the emulsion stage. Firstly, principal component analysis (PCA) was used to reduce the dimension of the fluorescence spectrum, and the first three principal components with a cumulative contribution rate of 99% were selected as inputs, and the type of light oil was taken as the output; after that, SSA is used to obtain the optimal parameters of SVM iteratively. Then, the SSA-SVM classification model was constructed. Finally, samples from the test set are substituted into the model for the classification identification, and the identification accuracy is 100%. In this study, the particle swarm optimization (PSO) support vector machine model (from now on referred to as PSO-SVM) and genetic algorithm optimization support vector machine model (from now on referred to as GA-SVM) were constructed at the same time as a comparison. From the experimental results, compared with the PSO algorithm and GA algorithm, the SSA algorithm improved the classification and recognition accuracy of the test set's lightweight oil emulsions by 1.77% and 3.04% year-on-year. The fitness curve reached the highest in the 2nd generation, which is better than the 4th generation of PSO and the 36th generation of GA, and the convergence speed is faster. In this study, the laser-induced fluorescence technique is used to realize the classification and identification of light oil emulsions of oil-in-water type, which promotes the development of the classification and detection mechanism of oil spill area on the sea surface, and the proposed SSA-SVM model provides a new way of classification and identification of light oil emulsions.
Key words：Laser-induced fluorescence; Sparrow search algorithm; Light oil emulsion; Oil in water; Support vector machine
陈晓玉，宁晓东，李心怡，杜雅欣，孔德明. 基于LIF对水包油型轻质油乳化液的分类识别[J]. 光谱学与光谱分析, 2024, 44(11): 3064-3068.
CHEN Xiao-yu, NING Xiao-dong, LI Xin-yi, DU Ya-xin, KONG De-ming. Classification and Identification of Oil-in-Water Light Oil Emulsions Based on LIF. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3064-3068.
[1] Lv Y N, Sun C Y, Liu B, et al. AIChE Journal, 2017，63(3): 1010.
[2] Bukin O, Proschenko D, Alexey C, et al. Photonics, 2020, 7(36): 1.
[3] Ye X, Chen B, Lee K, et al. Environmental Pollution, 2020, 262: 114294.
[4] YUAN Li, WANG Li-bin, JIAO Hui-hui(袁 丽，王立彬，焦慧慧). Spectroscopy and Spectral Analysis(光谱学与光谱学分析), 2021, 41(6): 1852.
[5] YUAN Li, KONG De-ming, ZHANG Xiao-dan，et al(袁 丽，孔德明，张晓丹，等). Chines Journal of Lasers(中国激光), 2020, 47(10): 292.
[6] 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): 397.
[7] JIANG Fan, QIAO Xin, ZHENG Hua-Jun, et al（蒋 帆，乔 欣，郑华军，等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2011, 27(7): 343.
[8] XU Xiang-jun, WANG Xian-shuang, LI Ang-ze, et al（徐向君，王宪双，李昂泽，等）. Chines Journal of Lasers（中国激光）, 2019, 46(3): 285.
[9] WANG Shu-tao, ZHU Cai-yun, LIU Ming-xin, et al(王书涛，朱彩云，刘洺辛，等). Acta Metrologica Sinica（计量学报）, 2018, 39(5): 747.
[10] HU Hong-zhi, QIN Chang, GUAN Fang, et al(胡鸿志，覃 畅，管 芳，等). Science Technology and Engineering(科学技术与工程), 2021, 21(25): 10755.
[11] Xue J, Shen B. Systems ence & Control Engineering, 2020, 8(1): 22.
[12] Pecker. The International Journal of Advanced Manufacturing Technology, 2019, 105(1-4): 1497.
[13] JING Min, HUA Deng-xin, LE Jing, et al(景 敏，华灯鑫，乐 静，等). Acta Physica Sinica（物理学报），2016, 65(7): 88.
[14] HUANG Yao, ZHAO Nan-jing, MENG De-shuo, et al（黄 尧，赵南京，孟德硕，等）. Chinese Optics（中国光学）, 2020, 13(6): 1401.
[15] Chang C C, Lin C J. ACM Transactions Intelligent Systems Technology, 2011, 2(3): 1.
