Qualitative and quantitative studies of multicomponent gas by CNN-KPCA-RF model

IF 2.7 3区化学 Q2 CHEMISTRY, ANALYTICAL

Vibrational Spectroscopy Pub Date : 2024-01-01 DOI:10.1016/j.vibspec.2023.103647

Haibo Liang, Yu Long, Gang Liu

{"title":"Qualitative and quantitative studies of multicomponent gas by CNN-KPCA-RF model","authors":"Haibo Liang, Yu Long, Gang Liu","doi":"10.1016/j.vibspec.2023.103647","DOIUrl":null,"url":null,"abstract":"<div><p>To improve the accuracy of multi-component gas analysis in infrared spectroscopy and simplify the workflow, an infrared spectroscopy gas detection method based on an improved convolutional neural network is proposed. This method can not only identify a variety of gas categories but also finely identify the concentration of gas. To verify the model identification effect proposed in this paper, eight kinds of gases such as CH4 and C2H6 were used as the sample gases for gas identification and concentration classification, and the corresponding hardware was used to complete the development of the system. The experimental results show that the accuracy of the model method for gas species identification can reach 90%, and the accuracy for concentration identification is the same. In addition, compared with the traditional CNN method, the recognition effect is significantly improved. With the improvement of the data set, the number of gas categories detected by this method and the measurement accuracy will be improved.</p></div>","PeriodicalId":23656,"journal":{"name":"Vibrational Spectroscopy","volume":"130 ","pages":"Article 103647"},"PeriodicalIF":2.7000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0924203123001546/pdfft?md5=ca21f506a6e1480be5b3cb97a4570bc1&pid=1-s2.0-S0924203123001546-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Vibrational Spectroscopy","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0924203123001546","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}

引用次数: 0

Abstract

To improve the accuracy of multi-component gas analysis in infrared spectroscopy and simplify the workflow, an infrared spectroscopy gas detection method based on an improved convolutional neural network is proposed. This method can not only identify a variety of gas categories but also finely identify the concentration of gas. To verify the model identification effect proposed in this paper, eight kinds of gases such as CH4 and C2H6 were used as the sample gases for gas identification and concentration classification, and the corresponding hardware was used to complete the development of the system. The experimental results show that the accuracy of the model method for gas species identification can reach 90%, and the accuracy for concentration identification is the same. In addition, compared with the traditional CNN method, the recognition effect is significantly improved. With the improvement of the data set, the number of gas categories detected by this method and the measurement accuracy will be improved.

查看原文本刊更多论文

利用 CNN-KPCA-RF 模型对多组分气体进行定性和定量研究

为了提高红外光谱分析中多组分气体分析的准确性并简化工作流程，提出了一种基于改进的卷积神经网络的红外光谱气体检测方法。该方法不仅能识别多种气体类别，还能精细识别气体浓度。为了验证本文提出的模型识别效果，以 CH4、C2H6 等 8 种气体作为样本气体进行气体识别和浓度分类，并利用相应的硬件完成了系统的开发。实验结果表明，模型法的气体种类识别准确率可达 90%，浓度识别准确率也是如此。此外，与传统的 CNN 方法相比，识别效果显著提高。随着数据集的改进，该方法检测到的气体种类数量和测量精度都将得到提高。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Vibrational Spectroscopy 化学-分析化学

CiteScore

4.70

自引率

4.00%

发文量

103

审稿时长

52 days

期刊介绍： Vibrational Spectroscopy provides a vehicle for the publication of original research that focuses on vibrational spectroscopy. This covers infrared, near-infrared and Raman spectroscopies and publishes papers dealing with developments in applications, theory, techniques and instrumentation. The topics covered by the journal include: Sampling techniques, Vibrational spectroscopy coupled with separation techniques, Instrumentation (Fourier transform, conventional and laser based), Data manipulation, Spectra-structure correlation and group frequencies. The application areas covered include: Analytical chemistry, Bio-organic and bio-inorganic chemistry, Organic chemistry, Inorganic chemistry, Catalysis, Environmental science, Industrial chemistry, Materials science, Physical chemistry, Polymer science, Process control, Specialized problem solving.