Multi Spectral Detection of Ethanol Content in Gasoline Based on SiPLS Feature Extraction and Information Fusion
ZHOU Kun-peng1, 2, BI Wei-hong1*, XING Yun-hai1, CHEN Jun-gang1, ZHOU Tong1, FU Xing-hu1
1. School of Information Science and Engineering, The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Yanshan University, Qinhuangdao 066004, China 2. School of Physics and Electronic Information, Inner Mongolia University for Nationalities, Tongliao 028000, China
Abstract:The ethanol content in ethanol gasoline was detected with ultraviolet/visible(UV/vis) and near-infrared (NIR) spectroscopy while information fusion technology and synergy interval PLS(SiPLS) algorithm were used as the feature extraction method with the establishment of partial least squares(PLS) regression model. Using the information fusion theory, UV/vis and NIR spectra were used for data fusion, the data level fusion (Low level data fusion, LLDF) and feature level fusion(Mid-level data fusion, MLDF) model were established. The results were compared with the single source modelwith low level data fusion before vector normalization(LLDF-VN1) selected for the optimal model. Finally, the optimal model was tested using the spectral data collected from the samples of high ethanol content and commercial gasoline. The results showed that both UV/vis and NIR can be used to detect and provide good prediction results, whereas direct fusion of the UV/vis and NIR spectral data provided the best results in the regression model based on the calibration set, with the highest correlation coefficient rc, the smallest Biasc and RMSECV values, as 0.999 9, 0.125 8 and 0.000 6, respectively. And the prediction effect of the model of LLDF-VN1(low level data fusion before vector normalization) was the best, rp=0.999 1,Biasp=0.352 7,RMSEP=-0.073 8. In the verification of the optimal model (LLDF-VN1) by the self distribution solution, rp=0.999 7, Biasp=0.102 2, RMSEP=0.329 1; and that for gasoline sold on market, rp=0.990 1, RMSEP=0.675 1, Biasp=0.892 7, respectively. It showed that the data level fusion based on UV/vis and NIR spectral information could be used to detect the content of ethanol in ethanol-gasoline quickly and accurately, achieving a wide range of ethanol concentration detection, which laid a foundation for further realization of the rapid detection of substances in the blended fuel oil.
周昆鹏1, 2,毕卫红1*,邢云海1,陈俊刚1,周 彤1,付兴虎1 . 基于SiPLS特征提取和信息融合的汽油中乙醇含量的多光谱检测 [J]. 光谱学与光谱分析, 2017, 37(02): 429-434.
ZHOU Kun-peng1, 2, BI Wei-hong1*, XING Yun-hai1, CHEN Jun-gang1, ZHOU Tong1, FU Xing-hu1 . Multi Spectral Detection of Ethanol Content in Gasoline Based on SiPLS Feature Extraction and Information Fusion . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(02): 429-434.
[1] Rodrigo C Costa, José R Sodré. Fuel, 2010, 89: 287. [2] SU Hui-bo, LI Hai-long, LI Fan, et al(苏会波, 李海龙, 李 凡, 等). Chinese Journal of Environmental Engineering(环境工程学报), 2015, 9(2): 823. [3] WEI Yan-ju, CHEN Xiao, LI Dong-hua, et al(魏衍举, 陈 晓, 李东华, 等). Chinese Internal Combustion Engine Engineering(内燃机工程). 2016, 37(1): 78. [4] CHEN Li-dan, ZHAO Yan-ru(陈立旦, 赵艳茹). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(8): 168. [5] Haule K, Toczek H. Journal of KONES, 2014, 21(3): 127. [6] Wrona M, Pezo D, Nerin C. Food Chemistry, 2013, 141(4): 3993. [7] Ajayi, Ibironke Adetolu. Bioresource Technology, 2008, 99(11): 5125. [8] Stella Corsetti, David McGloin, Johannes Kiefer. Fuel, 2016, 166: 488. [9] YANG Li-li, WANG Yu-tian, LU Xin-qiong(杨丽丽, 王玉田, 鲁信琼). Chinese Journal of Lasers(中国激光), 2013, 40(6): 298. [10] Milanez K D T M, Silva A C, Paz J E M, et al. Microchemical Journal, 2016, 124: 121. [11] Stella Corsetti, Florian M Zehentbauer, David McGloin, et al. Fuel, 2015, 141: 136. [12] HOU Pei-guo, LI Ning, CHANG Jiang, et al(侯培国, 李 宁, 常 江,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(6): 1529. [13] BI Wei-hong, CHEN Lian-sheng, ZHANG Hao, et al(毕卫红, 陈连生, 张 浩,等). Journal of Optoelectronics·Laser(光电子·激光), 2014, 25(10): 1963. [14] De Graaf G, Lacerenza G, Wolffenbuttel R, et al. Instrumentation and Measurement Technology Conference. IEEE, 2015. [15] Marta Ferreiro-González, Jesús Ayuso, José A álvarez. Fuel, 2015, 153: 402. [16] Wang Xiaofei, Bao Yanfei, Liu Guili, et al. Procedia Engineering, 2012, 29: 2285. [17] Chen Baisheng, Wu Huanan, Sam Fong Yau Li. Talanta, 2014, 120: 325. [18] Qin Xusong, Gao Furong, Guohua. Water Research,2012, 46: 1133.