Abstract：To satisfy the requirement of the production control and quality inspection of petrochemical products, a novel fuzzy neural network control method is proposed for determining product composition by near infrared spectroscopy. For the data analysis three different diesel products were selected as samples and six analytical models, such as saturated hydrocarbons, polar compounds, monoaromatics, dicyclic aromatics, tricyclic aromatics and naphthenes, were developed with the proposed fuzzy neural network method. Based on dSPACE, the near infrared spectroscopy system real-time experimental platform has been established to testify and analyze different diesel samples. The experimental results show that the improved performance is superior because of its advantage of quick response and good robustness. The mean squared error (MSE) of calibration and prediction samples is of the order of 10-6 in the spectral range of 800-2 300 nm. The developed method can be used in the research on petrochemical products processing.
[1] Heinz W Siesler, Yukihiro Ozaki, Satoshi Kawata, et al. Near-Infrared Spectroscopy: Principles, Instruments, Applications. Weinheim: Wiley-VCH, 2002. [2] TANG Yan-feng, ZHANG Zhuo-yong, FAN Guo-qiang, et al(汤彦丰, 张卓勇, 范国强, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2005, 25(5): 715. [3] Bunce S C, Izzetoglu M, Izzetoglu K, et al. Engineering in Medicine and Biology Magazine, 2006, 25(4): 54. [4] LIU Yan-de, YING Yi-bin(刘燕德, 应义斌). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(8): 1454. [5] LI Yan-kun, SHAO Xue-guang, CAI Wen-sheng(李艳坤, 邵学广, 蔡文生). Chemical Journal of Chinese Universities(高等学校化学学报), 2007, 28(2): 246. [6] Pavlidis I, Morellas V, Papanikolopoulos N. IEEE Transactions on Intelligent Transportation Systems, 2000, 1(2): 72. [7] Van Vo T, Hammer P E, Hoimes M L, et al. IEEE Transactions on Biomedical Engineering, 2007, 54(4): 573. [8] YU Xiao-hui, ZHANG Zhuo-yong, MA Qun, et al(于晓辉, 张卓勇, 马 群, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(3): 481.
