一种预测烷烃气体含量的方法与装置

By using an update mechanism based on historical neighborhood mutual information entropy and an ensemble learner, the problems of decreased model accuracy and low update efficiency in infrared spectroscopy detection technology are solved. This enables high-precision prediction of alkane gas content and adaptive model updating, thereby improving the safety and efficiency of oil and gas exploration.

CN117076943BActive Publication Date: 2026-07-17CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
Filing Date
2023-08-11
Publication Date
2026-07-17

Smart Images

  • Figure CN117076943B_ABST
    Figure CN117076943B_ABST
Patent Text Reader

Abstract

本发明提供一种预测烷烃气体含量的方法与装置。该方法包括：采集样气烷烃红外光谱数据作为历史数据集，采集现场烷烃红外光谱数据作为当前待测数据；采用滑动窗口分别提取历史数据集和待测数据对应的特征，分别得到历史特征xq‑i、待测特征xq；计算待测特征xq和历史特征xq‑i的互信息熵，并根据互信息熵确定是否更新当前模型；历史特征xq‑i为第q‑i次测量得到的历史数据对应的特征；确定需要更新模型后，根据相似度度量准则确定待测数据与样本数据集中的相似样本；根据相似样本，更新当前模型，并以更新后的模型预测烷烃气体的含量。本发明提供的方法，能够提高监测烷烃气体含量的精度。
Need to check novelty before this filing date? Find Prior Art