A NDIR CO sensor enhanced by Machine learning algorithm applying in gas outburst Early warning

IF 3.1 3区物理与天体物理 Q2 INSTRUMENTS & INSTRUMENTATION

Infrared Physics & Technology Pub Date : 2025-02-25 DOI:10.1016/j.infrared.2025.105801

Ruixiang Sun , Guolin Li , Haoran Yuan , Guangzhao Cui , Longju Li , Yingjie Zhao

{"title":"A NDIR CO sensor enhanced by Machine learning algorithm applying in gas outburst Early warning","authors":"Ruixiang Sun , Guolin Li , Haoran Yuan , Guangzhao Cui , Longju Li , Yingjie Zhao","doi":"10.1016/j.infrared.2025.105801","DOIUrl":null,"url":null,"abstract":"<div><div>In underground mines, the abnormal variations of carbon monoxide (CO) gas concentration are significant warning signals for gas outbursts and gas explosions. A CO sensor is engineered utilizing the principle of non-dispersive infrared (NDIR). The sensor consists of a broadband infrared light source (HIS2000R-0WC), a 3-meter path multi pass gas chamber (MPCC), and a dual channel pyroelectric detector. The center wavelengths of the two filters in the detector are 4.66 μm and 3.95 μm, respectively. An enhanced wavelet threshold denoising algorithm based on adaptive noise complete ensemble empirical mode decomposition with adaptive noise (EWTD-CEEMDAN) has been developed to enhance the signal-to-noise ratio (SNR) of voltage differential ratio signal. The proposed method demonstrates an approximate increase of 9.57 dB in SNR. The Zebra Optimization Algorithm-Least Squares Support Vector Machine (ZOA-LSSVM) algorithm model is employed to invert the CO concentration with a determination coefficient (R<sup>2</sup>) of 0.99992. Temperature compensation is performed to enhance the precision of sensor detection. According to the Allan-Werle deviation, the theoretical limit of detection (LoD) for CO is 9.56 ppb when the sensor integration time is 201 s. The experimental findings indicate that the sensor exhibits commendable performance and provides a reliable method for preventing mine gas outburst.</div></div>","PeriodicalId":13549,"journal":{"name":"Infrared Physics & Technology","volume":"147 ","pages":"Article 105801"},"PeriodicalIF":3.1000,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infrared Physics & Technology","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1350449525000945","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}

引用次数: 0

Abstract

In underground mines, the abnormal variations of carbon monoxide (CO) gas concentration are significant warning signals for gas outbursts and gas explosions. A CO sensor is engineered utilizing the principle of non-dispersive infrared (NDIR). The sensor consists of a broadband infrared light source (HIS2000R-0WC), a 3-meter path multi pass gas chamber (MPCC), and a dual channel pyroelectric detector. The center wavelengths of the two filters in the detector are 4.66 μm and 3.95 μm, respectively. An enhanced wavelet threshold denoising algorithm based on adaptive noise complete ensemble empirical mode decomposition with adaptive noise (EWTD-CEEMDAN) has been developed to enhance the signal-to-noise ratio (SNR) of voltage differential ratio signal. The proposed method demonstrates an approximate increase of 9.57 dB in SNR. The Zebra Optimization Algorithm-Least Squares Support Vector Machine (ZOA-LSSVM) algorithm model is employed to invert the CO concentration with a determination coefficient (R²) of 0.99992. Temperature compensation is performed to enhance the precision of sensor detection. According to the Allan-Werle deviation, the theoretical limit of detection (LoD) for CO is 9.56 ppb when the sensor integration time is 201 s. The experimental findings indicate that the sensor exhibits commendable performance and provides a reliable method for preventing mine gas outburst.

查看原文本刊更多论文

在地下矿井中，一氧化碳（CO）气体浓度的异常变化是瓦斯爆发和瓦斯爆炸的重要预警信号。一氧化碳传感器是利用非色散红外线（NDIR）原理设计的。传感器由一个宽带红外光源（HIS2000R-0WC）、一个 3 米路径多通气室（MPCC）和一个双通道热释电探测器组成。探测器中两个滤光片的中心波长分别为 4.66 μm 和 3.95 μm。为了提高电压差比信号的信噪比（SNR），我们开发了一种基于自适应噪声完整集合经验模式分解（EWTD-CEEMDAN）的增强型小波阈值去噪算法。所提出的方法将信噪比提高了约 9.57 dB。采用斑马优化算法-最小二乘支持向量机（ZOA-LSSVM）算法模型反演一氧化碳浓度，确定系数（R2）为 0.99992。进行温度补偿以提高传感器的检测精度。根据 Allan-Werle 偏差，当传感器积分时间为 201 秒时，一氧化碳的理论检测限（LoD）为 9.56 ppb。

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

Infrared Physics & Technology 物理-光学

CiteScore

5.70

自引率

12.10%

发文量

400

审稿时长

67 days

期刊介绍： The Journal covers the entire field of infrared physics and technology: theory, experiment, application, devices and instrumentation. Infrared'' is defined as covering the near, mid and far infrared (terahertz) regions from 0.75um (750nm) to 1mm (300GHz.) Submissions in the 300GHz to 100GHz region may be accepted at the editors discretion if their content is relevant to shorter wavelengths. Submissions must be primarily concerned with and directly relevant to this spectral region. Its core topics can be summarized as the generation, propagation and detection, of infrared radiation; the associated optics, materials and devices; and its use in all fields of science, industry, engineering and medicine. Infrared techniques occur in many different fields, notably spectroscopy and interferometry; material characterization and processing; atmospheric physics, astronomy and space research. Scientific aspects include lasers, quantum optics, quantum electronics, image processing and semiconductor physics. Some important applications are medical diagnostics and treatment, industrial inspection and environmental monitoring.