基于SEV/SEC-iPLS 的近红外光谱波长优选方法
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:


Wavelength Optimization Method for Near Infrared Spectrum Based on SEV/SEC-iPLS
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为实现建模区间的波长优选,将iPLS 法与验证标准差/校正标准偏差(standard error of verification/standard error of calibration,SEV/SEC)相结合,以喷气燃料为研究对象,对其初馏点进行定量分析。结果表明:iPLS 法结合 SEV/SEC 的组合评价指标用所选光谱区间建立的校正模型性能得到较大改善,模型的决定系数R2、SEV 分别为 0.94 和1.05,较全谱区模型分别提升55.70%和36.23%,较传统iPLS 法分别提升44.44%和17.50%,并通过配对t 检验法 验证,证明了该波长优选方法的可行性与有效性。

    Abstract:

    In order to optimize the wavelength of modeling interval, iPLS method and SEV/SEC (standard error of verification/standard error of calibration) were combined to quantitatively analyze the initial boiling point of jet fuel. The results show that the performance of the correction model established by iPLS method combined with SEV/SEC combination evaluation index using the selected spectral interval is greatly improved, the coefficient of determination (R2) and standard error of verification (SEV) of the model are 0.94 and 1.05 respectively, which are 55.70% and 36.23% higher than the full spectral region model, and 44.44% and 17.50% higher than the traditional iPLS method, respectively. The feasibility and effectiveness of this method are verified by t test method.

    参考文献
    相似文献
    引证文献
引用本文

曾庆松.基于SEV/SEC-iPLS 的近红外光谱波长优选方法[J].,2021,40(12).

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-08-15
  • 最后修改日期:2021-09-20
  • 录用日期:
  • 在线发布日期: 2021-12-06
  • 出版日期:
文章二维码