基于近红外光谱技术的易燃液体快速鉴别

发布时间：2018-01-28 03:40

本文关键词： 近红外光谱易燃液体判别分析极限学习机　出处：《激光杂志》2017年11期 　论文类型：期刊论文

【摘要】：快速、便捷、准确、低成本的液体检测方法对公众的安全有着重大的意义。文章采用近红外光谱分析方法,研究了对易燃液体的快速鉴别方法。采集了典型易燃液体和非易燃液体样品的近红外吸收光谱图,在建立判别预测模型时,分别对两类液体样品的光谱数据进行主成分分析,选取了特征波长点,从而提取样本的特征值。利用判别分析法和极限学习机判别法分别建立了判别预测模型,两种方法的分类对训练集的准确率均能达到98%以上,对测试集能达到100%,并且耗时极短。结果表明近红外光谱可以快速鉴别易燃液体与非易燃液体。
[Abstract]:Rapid, convenient, accurate and low-cost liquid detection method is of great significance to public safety. Near infrared spectroscopy analysis method is used in this paper. The fast identification method of flammable liquid was studied. The near infrared absorption spectra of typical flammable liquid and non-flammable liquid were collected, and the discriminant prediction model was established. The spectral data of two kinds of liquid samples were analyzed by principal component analysis and the characteristic wavelength points were selected to extract the eigenvalues of the samples. The discriminant prediction models were established by discriminant analysis and extreme learning machine discriminant method. The classification accuracy of the two methods can reach more than 98% for the training set and 100 for the test set, and the time is very short. The results show that the near infrared spectrum can quickly distinguish flammable liquid from non-flammable liquid.
【作者单位】：南京信息工程大学信息与控制学院;江苏省大气环境与装备技术协同创新中心;
【基金】：国家自然科学基金青年基金项目(61302189)
【分类号】：D918.9;O657.33
【正文快照】： 2.江苏省大气环境与装备技术协同创新中心,南京210044()随着恐怖暴力事件数量的增长,对危险携带物的检查受到了国内外的高度重视。其中液态危险物由于方便购买已成为暴力恐怖分子的常用工具。2013年5月广州地铁一号线发生一起预谋纵火案,犯案者携带20升汽油及自制遥控点火装置

【相似文献】