摘要
基于近红外光谱技术,构建了石脑油关键物性参数(密度、馏程、PONA组成)的快速分析方法。采用矢量归一化结合一阶导数预处理光谱数据,通过偏最小二乘法(PLS)建立定量预测模型。实验结果表明,模型决定系数(R^(2))>0.95,预测均方根误差(RMSEP)<0.5%,检测时间缩短至30 s。工业验证显示,该法检测精度达到ASTM标准要求,分析效率提升20倍以上。
A rapid analysis method for the key physical property parameters(density,distillation range,PONA composition)of naphtha was developed based on near-infrared spectroscopy technology.Vector normalization combined with first derivative is used to preprocess the spectral data,and a quantitative prediction model is established through the partial least squares method(PLS).The experimental results showed that the determination coefficient(R^(2))of the model was greater than 0.95,the root mean square error of prediction(RMSEP)was less than 0.5%,and the detection time was shortened to 30 seconds.Industrial verification shows that the detection accuracy of this method meets the requirements of the American Society for Testing and Materials standards(ASTM standards),and the analysis efficiency is improved by more than 20 times.
作者
王季泉
Wang Jiquan(Laboratory and Measurement Center,SINOPEC INEOS(Tianjin)Petrochemical Co.,Ltd.,Tianjin 300271,China)
出处
《精细石油化工》
2025年第4期52-56,共5页
Speciality Petrochemicals
关键词
近红外光谱
石脑油
偏最小二乘法
快速分析
near-infrared spectroscopy
naphtha
partial least squares
rapid analysis
作者简介
王季泉(1970-),工程师,主要从事色谱、电化学、近红外等分析仪器运用及研究。E-mail:wangjiquan.tjsh@sinopec.com。
