期刊文献+

加氢裂化常压塔轻石脑油干点软测量 被引量:1

The Soft Sensoring for Dry Point of Light Naphtha on the Atmospheric Tower in the Hydrogenation and Cracking Process
在线阅读 下载PDF
导出
摘要 先进控制技术可以把若干个变量控制在期望的控制点上,从而达到装置效益的整体优化。近年来,各种先进控制软件在催化裂化装置、加氢裂化等装置上得到了广泛的应用。为了实施加氢裂化装置的先进控制,需要在线计算其产品质量指标。轻石脑油干点就是其中一个质量指标。为了避免单纯依靠过程数据进行软测量建模而导致的计算结果与工艺分析结果相矛盾的情况,结合过程数据和质量指标的关联公式,利用粒子群算法建立轻石脑油的软测量模型。该软测量模型已在现场实施,应用结果表明,该模型有较高精度。 The advanced control technology could control several variables at the expected control value, there fore the benefit of the unit can reach optimum. In recent years various advanced control softwares have been applied in CCU, HCU etc. units. It is required to calculate products quality on-line to execute the advanced process control. The dry point of light naphtha is one important product quality parameter. To avoid the contradiction between the calculation result based on the module built from the soft measurement of the process data and the calculation result based on process analysis, combining the related formula on process data and quality index, the soft measurement model of light naphtha has been built, used the particle swarm algorithm. The soft measurement model has been applied in site. The application result has shown that the model has high accuracy.
作者 薛秀莉 苗荣
出处 《石油化工自动化》 CAS 2009年第6期54-56,共3页 Automation in Petro-chemical Industry
关键词 轻石脑油干点 软测量 关联公式 粒子群 dry point of light naphtha soft sensor relevant formula particle swarm optimization
  • 相关文献

参考文献7

二级参考文献40

共引文献17

同被引文献20

  • 1胡志坤,桂卫华,彭小奇,姚俊峰,张卫华.铜转炉生产操作模式智能优化[J].控制理论与应用,2005,22(2):243-247. 被引量:16
  • 2严爱军,柴天佑,岳恒.竖炉焙烧过程的多变量智能优化控制[J].自动化学报,2006,32(4):636-640. 被引量:20
  • 3Hu Zhikun(胡志坤). Research on intelligent optimization methods of operational pattern in the complex process of nonferrous metallurgy smelting [D]. Changsha: Central South University,2005.
  • 4Dana Angluin,Philip Laird. Learning from noisy examples [J]. Machine Learning,1988,2 (4): 343-370.
  • 5Fabien Lauer,GrardBloch. Incorporating prior knowledge in support vector吨ression [J]. Machine Learning,2008,70 (1): 256-264.
  • 6Suykens 1 A K. Least squares support vector machine classifiers [J]. Neural Processing Letters. 1999. 9: 293 300.
  • 7Adams N M. Hand D J. Comparing classifiers when the misallocation costs are uncertain [J]. Pattern Recognition. 1999.32 (7): 1139-1147.
  • 8Y oav Freund. Boosting a weak learning algorithm by majority DJ. Information and Computation. 1995. 12 (2): 256-285.
  • 9Schapire R. Singer Y. BoosTexter: a boosting-based system for text categorization [J]. Machine Learning. 2000. 39 (2/3): 135-168.
  • 10Friedman H. Hastie T. TibshiraniR. Additive logisticregression: a statistical view of Boosting [J]. Annals of Statistics. 2000. 28 (2): 337-343.

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部