摘要： 为了实现钢结构防火涂料在流通使用领域中不同品牌的现场快速鉴别，提出了一种用近红外光谱技术快速鉴别钢结构防火涂料品牌的方法。运用光栅扫描型近红外光谱仪器，通过近红外漫反射光谱获取不同品牌钢结构防火涂料的光谱曲线，并对光谱数据进行标准正态变量变换(standard normal variate transformation, SNV)、Norris二阶求导等优化处理。利用主成分分析法(principal component analysis, PCA)对钢结构防火涂料品牌进行聚类分析，前五个主成分的累积方差贡献率已达到99.791%，以PC1，PC2和PC3×10的得分值对所有建模样品在三维空间作图，对不同品牌的钢结构防火涂料具有很好的聚类作用。利用5个品牌的各25个样品建立校正模型，用余下5个品牌的各5个样品，共计25个样品进行外部验证，通过未知样品光谱的主成分得分值计算其与校正模型中每个品牌的马氏距离值，实现未知样品的品牌鉴别。建立的定性分析模型对未知样品的外部验证正确率达到100%。说明该分析方法能够快速准确的鉴别钢结构防火涂料品牌，并为市场规范提供技术参考。
关键词：近红外光谱;钢结构防火涂料;主成分分析;马氏距离;涂料鉴别
Abstract：In order to achieve the rapid identification of fire resistive coating for steel structure of different brands in circulating, a new method for the fast discrimination of varieties of fire resistive coating for steel structure by means of near infrared spectroscopy was proposed. The raster scanning near infrared spectroscopy instrument and near infrared diffuse reflectance spectroscopy were applied to collect the spectral curve of different brands of fire resistive coating for steel structure and the spectral data were preprocessed with standard normal variate transformation(standard normal variate transformation, SNV)and Norris second derivative. The principal component analysis(principal component analysis, PCA)was used to near infrared spectra for cluster analysis. The analysis results showed that the cumulate reliabilities of PC1 to PC5 were 99.791%. The 3-dimentional plot was drawn with the scores of PC1, PC2 and PC3×10, which appeared to provide the best clustering of the varieties of fire resistive coating for steel structure. A total of 150 fire resistive coating samples were divided into calibration set and validation set randomly, the calibration set had 125 samples with 25 samples of each variety, and the validation set had 25 samples with 5 samples of each variety. According to the principal component scores of unknown samples, Mahalanobis distance values between each variety and unknown samples were calculated to realize the discrimination of different varieties. The qualitative analysis model for external verification of unknown samples is a 100% recognition ration. The results demonstrated that this identification method can be used as a rapid, accurate method to identify the classification of fire resistive coating for steel structure and provide technical reference for market regulation.
薛 岗，宋文琦*，李树超 . 基于近红外光谱技术的钢结构防火涂料品牌鉴别方法研究 [J]. 光谱学与光谱分析, 2015, 35(01): 104-107.
XUE Gang, SONG Wen-qi*, LI Shu-chao . Study on Discrimination of Varieties of Fire Resistive Coating for Steel Structure Based on Near-Infrared Spectroscopy . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(01): 104-107.
[1] Sichuan Fire Reseach Institute of Ministry of Public Security. GB 14907—2002，Fire Resistive Coating for Steel Structure(钢结构防火涂料)，2002. [2] Fire Department of Ministry of Public Security, Shenyang Fire Reseach Institute of Ministry of Public Security, Tianjin Fire Reseach Institute of Ministry of Public Security, et al. GA 588—2012, Rules for Field Inspection and Judgement of Fire Products(消防产品现场检查判定规则)，2012. [3] LU Wan-zhen, YUAN Hong-fu, XU Guang-tong(陆婉珍，袁洪福，徐广通). The ModernAnalysis Technique for Near Infrared Spectra(现代近红外光谱分析技术).Beijing: Chinese oil and Chemical Press(北京：中国石油化工出版社)，2007. 1. [4] HU Ai-qin，YUAN Hong-fu，XUE Gang，et al(胡爱琴，袁洪福，薛 岗，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2012, 32(8): 2135. [5] XUE Gang，SONG Wen-qi(薛 岗，宋文琦). Acta Photonica Sinica(光子学报)，2013, 42(8): 908. [6] XIA Li-ya，SHEN Shi-gang，LIU Zheng-hao，et al(夏立娅，申世刚，刘峥灏，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2013, 33(1): 102. [7] DENG Xiao-bo，YANG Sen，GAO Ping，et al(邓小波，杨 森，高 萍，等). New Chemical Material(化工新型材料)，2010, 38(9): 57. [8] CHU Xiao-li(褚小立). Molecular Spectroscopy Analytical Technology Combined with Chemometrics and Its Applications(化学计量学方法与分子光谱分析技术). Beijing：Chemical Industry Press(北京：化工出版社)，2011. 7. [9] Jerry Workman Jr，Lois Weyer. Practical Guide to Interpretive Near-Infrared Spectroscopy(近红外光谱解析实用指南). Translated by CHU Xiao-li, XU Yu-peng, TIAN Gao-you(褚小立，许育鹏，田高友，译). Beijing: Chemical Industry Press(北京：化学工业出版社)，2009. 19.
