期刊文献+

DDAG双支持向量机在ERT系统流型识别中的应用研究 被引量:1

Research on the Application of DDAG Bi-support Vector Machine in Flow Regime Identification of Electrical Resistance Tomography System
下载PDF
导出
摘要 两相流体具有复杂的流动特性,流型的准确识别是两相流参数准确测量的基础。针对电阻层析成像(ERT)系统和油/水两相流的流型,先用小波包分析提取ERT系统测量的压差波动信号的特征,然后将特征数据输入构造好的DDAG双支持向量机多类分模型进行识别。仿真实验结果对比证明,DDAG双支持向量机是一种兼顾效率和准确性的流型识别方法。 Two-phase fluid has complex flow characteristics.The exact identification of flow regime is the foundation for measuring twophase flow's parameter accurately. According to electrical resistance tomography( ERT) system and flow regime of oil-water two-phase flow,wavelet packet analysis is adopted to extract the features of the differential pressure fluctuation signal measured by ERT system,then the extracted feature data is input to the prepared DDAG bi- support vector machine to carry out multi-class identification. Experimental results showed that the DDAG bi-support vector machine is an effective and accurate method of regime identification.
作者 张华
出处 《长春大学学报》 2016年第12期33-35,48,共4页 Journal of Changchun University
关键词 电阻层析成像 流型识别 小波包 DDAG双支持向量机 ERT flow regime identification wavelet packet DDAG bi-support vector machine
  • 相关文献

参考文献4

二级参考文献69

  • 1黄剑锋,刘付显,朱法顺.基于多类分类支持向量机的空袭目标识别[J].微计算机信息,2008,24(10):258-260. 被引量:4
  • 2朱远平,戴汝为.基于SVM决策树的文本分类器[J].模式识别与人工智能,2005,18(4):412-416. 被引量:24
  • 3孟媛媛,刘希玉.一种新的基于二叉树的SVM多类分类方法[J].计算机应用,2005,25(11):2653-2654. 被引量:42
  • 4Vapnik V. The nature of statistical learning theory. pringer-Verlag, NewYork. NY, 1995.
  • 5Weston J, Watkins C. Multi-class Support Vector Machines.Technical Report CSD TR 98 04,Royal Holloway, University of London, Department of Computer Science, 1998.
  • 6Crammer K, Singer Y. Ultraconservative Online Algorithms for Multi-class Problems. Proc of the 14th Annual Conf on Computational Learning Theory, 2001.
  • 7Hsu CW, Lin CJ. A Comparison of Methods for Multi-class Support Vector Machines. IEEE Transaction on Neural Networks, 2002,(13):415 - 425.
  • 8Platt J C, Cristianini N, Shawe-Taylor J. Large Margin DDAGs for Multi-class Classification. Advances in Neural Information Processing Systems, MIT Press, 2000;12:547 - 553.
  • 9张学工译.统计学习理论的本质.清华大学出版社,2000.
  • 10Vapnik V N. The nature of statistical learning theory. New York:Springer, 2000.

共引文献68

同被引文献20

引证文献1

二级引证文献4

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