作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (02): 200-202. doi: 10.3969/j.issn.1000-3428.2007.02.070

• 工程应用技术与实现 • 上一篇    下一篇

基于支持向量机的油品质量预测

李方方,赵英凯,姜志兵   

  1. (南京工业大学自动化学院,南京 210009)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-01-20 发布日期:2007-01-20

Prediction of Oil Quality Based on Support Vector Machines

LI Fangfang, ZHAO Yingkai, JIANG Zhibing   

  1. (School of Automation, Nanjing University of Technology, Nanjing 210009)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-01-20 Published:2007-01-20

摘要: 以某炼油厂加氢装置的现场数据为基础,利用支持向量机技术建立了轻柴油的凝点、闪点、95%馏出温度等3个关键指标的预测模型,并且分析了神经网络和支持向量机在预测上的差异,验证了用支持向量机建立的油品质量预测模型能快速得到有效信息,从而为实现质量指标的实时预估奠定了基础。

关键词: 支持向量机, 核函数, 轻柴油, 预测

Abstract: Based on the local data from hydrogenation equipment, a predictive model using support vector machines is established for three important quality targets of diesel oil in this paper, and compared with neural network on precision. It proves that the proposed predictive models based on support vector machines can predict the quality target efficiently and rapidly. It provides a method for online diagnosing fault of quality targets.

Key words: Support vector machines(SVM), Kernel function, Diesel oil, Prediction