光子学报, 2017, 46 (11): 1130002, 网络出版: 2017-12-08  

水质痕量石油类污染物分类识别方法

Classification of Trace Oil Pollutants in Water Quality
作者单位
燕山大学 电气工程学院, 河北 秦皇岛 066000
摘要
基于水质中石油类污染物的强荧光特性, 构建了荧光检测实验系统, 分别以50种不同浓度的汽油、柴油、煤油和机油的水溶液为测量样本, 分析了其荧光特性.由于四者荧光峰位置相似, 很难直接识别, 提出了一种运用神经网络进行模式识别的新方法, 将主成分分析法(PCA)和可拓神经网络(ENN)相结合对输入矢量进行降维并进行分类识别.结果表明, 该方法与ENN和PCA-BP算法相比, 迭代数由265降低到60;识别离差平方和由0.236 5降到0.014 5;识别效率由72.50%提升到96.25%;识别精度可达10-6级别.PCA-ENN算法具有较高的识别精度和识别效率, 同时也可用于水质中其它痕量有机物质的光谱识别.
Abstract
Based on strong fluorescence property of oil pollutant in water quality, a fluorescence detection system is constructed, gasoline, diesel, kerosene, engine oil with different concentrations in water quality are prepared to analyze their fluorescence characteristics. In order to identify the three oil with the similar fluorescence peaks, the Principal Component Analysis (PCA) combined with Extension Neural Network (ENN) is proposed, which can reduce input vector and identify similar substances. Compare with the ENN and PCA-BP, the results show that the proposed method can make the iteration number dropped from 265 to 60, make the sum of the squares of dispersion decrease from 0.236 5 to 0.014 5, make recognition efficiency increase from 72.50% to 96.25%, and reach the 10-6 level of recognition precision. The proposed method possesses high recognition accuracy and recognition efficiency, which can be used in spectral identification of other trace organic materials in water.
参考文献

[1] SPIER C, STRINGFELLOW W T, HAZEN T C, et al. Distribution of hydrocarbons released during the 2010 MC252 oil spill in deep offshore waters[J]. Environmental Pollution, 2013, 173(1): 224-230.

[2] COHEN M A. Water pollution from oil spills[J]. Encyclopedia of Energy Natural Resource & Environmental Economics, 2013, 3(3): 121-126.

[3] RUIZ M D, BUSTAMANTE I T, DAGO A, et al. A multivariate calibration approach for determination of petroleum hydrocarbons in water by means of IR spectroscopy[J]. Journal of Chemometrics, 2010, 24(7-8): 444-447.

[4] UOZUMI J, PEIPONEN K E, TURUNEN P, et al. Robust sensor for turbidity measurement from light scattering and absorbing liquids[J]. Optics Letters, 2009, 34(23): 3743-5.

[5] GAULIER F, GIBERT A, WALLS D, et al. Mercury speciation in liquid petroleum products: Comparison between on-site approach and lab measurement using size exclusion chromatography with high resolution inductively coupled plasma mass spectrometric detection (SEC-ICP-HR MS)[J]. Fuel Processing Technology, 2015, 131: 254-261.

[6] BERNABEU A M, FERNANDEZ-FERNANDEZ S, BOUCHETTE F, et al. Recurrent arrival of oil to Galician coast: the final step of the Prestige deep oil spill[J]. Journal of Hazardous Materials, 2013, 250-251(2): 82-90.

[7] MOONKOO K, UNHYUK Y, HONG S H, et al. Hebei spirit oil spill monitored on site by fluorometric detection of residual oil in coastal waters off Taean, Korea[J]. Marine Pollution Bulletin, 2010, 60(3): 383-9.

[8] WANG Chun-yan, LI Wen-dong, LUAN Xiao-ning. Species identification and concentration quantification of crude oil samples in petroleum exploration using the concentration-synchronous-matrix-fluorescence spectroscopy[J]. Talanta, 2010, 81(1-2): 684-691.

[9] JIANG F, LEE F S, WAN X, et al. The application of excitation/emission matrix spectroscopy combined with multivariate analysis for the characterization and source identification of dissolved organic matter in sea water of Bohai sea[J]. China Marine Chemistry, 2008, 110(1-2): 109-119.

[10] CALIMAG-WILLIAMS K, KNOBEL G, GOICOECHEA H C, et al. Achieving second order advantage with multi-way partial least squares and residual bi-linearization with total synchronous fluorescence data of monohydroxy-polycyclic aromatic hydrocarbons in urine samples[J]. Analytica Chimica Acta, 2014, 811: 60-69.

[11] 王玉田, 赵煦, 潘钊, 等. 基于荧光光谱的五维数据处理方法[J]. 发光学报, 2016, 37(11):1436-1443.

    WANG Yu-tian, ZHAO Xu, PAN Zhao, et al. Processing method of five-dimensional data based on fluorescence spectra[J]. Chinese Journal of Luminescence, 2016, 37(11): 1436-1443.

[12] 韩仲志, 万剑华, 刘杰, 等. 利用油品紫外荧光特性的多光谱成像检测[J]. 发光学报, 2015, 36(11):1335-1341.

    HAN Zhong-zhi, WAN Jian-hua, LIU Jie, et al. Multispectral imaging detection using the ultraviolet fluorescence characteristics of oil[J]. Chinese Journal of Luminescence, 2015, 36(11): 1335-1341.

[13] WANG Shu-tao, SHAO Xiao-qing, PAN Zhao, et al. Application of three-dimensional fluorescence spectrum method and PARAFAC in petroleum pollutant measurement and identification[J]. Advanced Materials Research, 2011, 311-313: 1213-1216.

[14] GOICOECHEA H C, CALIMAG-WILLIAMS K, CAMPIGLIA A D. Multi-way partial least-squares and residual bi-linearization for the direct determination of monohydroxy-polycyclic aromatic hydrocarbons on octadecyl membranes via room-temperature fluorescence excitation emission matrices[J]. Analytica Chimica Acta, 2012, 717(5): 100-109.

[15] 刘倩倩, 王春艳, 史晓凤, 等. 基于RBF神经网络的较低浓度下同步荧光光谱的溢油鉴别[J]. 光谱学与光谱分析, 2012, 32(4):1012-1015.

    LIU Qian-qian, WANG Chun-yan, SHI Xiao-feng, et al. Identification of spill oil species based on low concentration synchronous fluorescence spectra and rbf neural network[J]. Spectroscopy and Spectral Analysis, 2012, 32(4): 1012-1015.

[16] DJEMILI R, BOUROUBA H, KORBA M C A. Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals[J]. Biocybernetics & Biomedical Engineering, 2016, 36(1): 285-291.

[17] BIEROZA M, BAKER A, BRIDGEMAN J. Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment[J]. Environmetrics, 2011, 2(3): 256-270.

[18] WANG Shu-tao, CHEN Dong-ying, WANG Xing-long, et al. A New Method for the Determination of Potassium Sorbate Combining Fluorescence Spectra Method with PSO-BP Neural Network[J]. Spectroscopy and Spectral Analysis, 2015, 35(12): 3549-3554.

[19] CHEN Huang-cheng, GU Feng-chang, WANG Meng-hui. A novel extension neural network based partial discharge pattern recognition method for high-voltage power apparatus[J]. Expert Systems with Applications, 2012, 39(3): 3423-3431.

[20] SHATNAWI Y, Al-KHASSAWENEH M. Fault diagnosis in internal combustion engines using extension neural network[J]. IEEE Transactions on Industrial Electronics, 2013, 61(3): 1434-1443.

[21] WANG Zhen-mu, WU Ming-ju, CHEN Jian-hong, et al. Extension neural network approach to classification of brain MRI[C] Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IEEE Computer Society, 2009: 515-517.

[22] 常玉清, 王姝, 王福利, 等. 基于多PCA模型的过程监测方法[J]. 仪器仪表学报, 2014, 35(4):901-908.

    CHANG Yu-qing, WANG Shu, WANG Fu-li, et al. Process monitoring method based on multiple PCA models[J]. Chinese Journal of Scientific Instrument, 2014, 35(4): 901-908.

苑媛媛, 王书涛, 孔德明, 潘钊. 水质痕量石油类污染物分类识别方法[J]. 光子学报, 2017, 46(11): 1130002. YUAN Yuan-yuan, WANG Shu-tao, KONG De-ming, PAN Zhao. Classification of Trace Oil Pollutants in Water Quality[J]. ACTA PHOTONICA SINICA, 2017, 46(11): 1130002.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!