Support vector regression-based study of interference in absorption spectral lines of mixed gases |
| |
| Authors: | YAN Xiangyu LI Honglian WANG Yitong FANG Lide and ZHANG Rongxiang |
| |
| Affiliation: | School of Quality and Technical Supervision, Hebei University, Baoding 071002, China;National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China;Hebei Key Laboratory of Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China,School of Quality and Technical Supervision, Hebei University, Baoding 071002, China;National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China;Hebei Key Laboratory of Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China,School of Quality and Technical Supervision, Hebei University, Baoding 071002, China;National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China;Hebei Key Laboratory of Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China,School of Quality and Technical Supervision, Hebei University, Baoding 071002, China;National & Local Joint Engineering Research Center of Metrology Instrument and System, Baoding 071002, China;Hebei Key Laboratory of Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China and College of Physics Science and Technology, Hebei University, Baoding 071002, China |
| |
| Abstract: | When measuring the concentration of multi-component gas mixtures based on supercontinuum laser absorption spectroscopy (SCLAS), there are interferences between the absorption spectral lines. For the spectral interference problem of CO2 and CH4 at 1 432 nm, a method based on support vector regression (SVR) is proposed in this paper. The SVR model, the k-nearest neighbor (KNN) model and the least squares (LS) model are used to analyze and predict the absorption spectral data, and the prediction accuracies were 96.29%, 88.89% and 85.19%, respectively, with the highest prediction accuracy of the SVR model. The results show that the method can accurately measure the concentration of gas mixtures, realize the detection of mixed gases using a single waveband, and provide a solution to the overlapping spectral line interference of multi-component gas mixtures. |
| |
| Keywords: | |
|
| 点击此处可从《光电子快报》浏览原始摘要信息 |
|
点击此处可从《光电子快报》下载全文 |
|
