摘要
汽油管道调合的在线优化过程中,调合优化与控制系统对近红外光谱模型的依赖很大。光谱模型的精度及适应性直接影响整个在线调合系统。本文就如何建立适用于在线汽油调合的汽油辛烷值近红外光谱模型展开研究,提出一种采用主元分析(PCA)结合人工神经网络(ANN)的方法建立汽油近红外光谱辛烷值模型的方法;并与多元线性回归及偏最小二乘法建立的线性模型做比较。结果表明主元分析结合人工神经网络所建立的模型适应性较高、抗干扰能力强,适合汽油在线调合的现场应用。
Abstracts： During the gasoline online blending process, blending optimization and control system is greatly dependent on the near-infrared spectral model. The spectral model＇s accuracy and adaptability directly affect the entire online blending system. This paper studies how to establish model for gasoline octane during the gasoline online blending with near infrared spectroscopy. It is proposed using principal component analysis （PCA） with Artificial Neural Network （ANN） method to establish gasoline near infrared spectroscopy-octane model. We also use multiple linear regressions and partial least squares method to establish gasoline octane model for comparison. The results show that the model established by PCA and ANN has strong anti-jamming capability and suitable for gasoline online blending field applications.
出处
《计算机与应用化学》
CAS
CSCD
北大核心
2014年第1期63-68,共6页
Computers and Applied Chemistry
关键词
汽油调合
近红外
主元分析
Keyword： gasoline blending
near infrared spectroscopy
principal component analysis
