期刊文献+

基于一维卷积神经网络的气体识别方法研究 被引量:6

Study on Gas Recognition Method Based on One-Dimensional Convolutional Neural Network
下载PDF
导出
摘要 混合气体定性识别是人工嗅觉进行气体检测与分析的关键问题。为提高人工嗅觉系统对混合气体检测识别的准确率,提出了一种基于一维卷积神经网络的气体识别方法。该方法利用卷积神经网络对原始数据进行自适应特征提取,如响应稳定值、响应建立时间以及人工难以描述的特征。使用通过混合气体数据采集系统所获取到甲烷、一氧化碳、乙烯及两种混合物的实验样本数据进行实验,结果表明所提方法的识别准确率可达99.98%。相比于传统算法,所提方法具有更高的准确率与模型泛化能力。 Qualitative identification of mixed gases is a key issue for gas detection and analysis of artificial olfaction.A gas recognition method based on one-dimensional convolutional neural network was proposed to improve the accuracy of mixed gas detection and recognition of artificial olfaction.Convolutional neural network is used to extract adaptive features from the original data adaptively,such as response stability value,response establishment time,and features that are difficult to describe.Corresponding experiments are performed by using the data of methane,carbon monoxide,ethylene and two kinds of mixtures,obtained through the designed mixed gas data acquisition system.The experimental results show that gas recognition accuracy of the proposed algorithm is 99.98%.Compared with the traditional algorithm,the proposed algorithm has higher accuracy and better model generalization ability.
作者 李鹏 徐永凯 杨佳康 陆一 LI Peng;XU Yongkai;YANG Jiakang;LU Yi(Jiangsu Key Laboratory of Meteorological Observation and Information Processing,Nanjing University of Information Science and Technology,Nanjing Jiangsu 210044,China;Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology,Nanjing University of Information Science and Technology,Nanjing Jiangsu 210044,China;Binjiang College of Nanjing University of Information Science and Technology,Wuxi Jiangsu 214105,China)
出处 《电子器件》 CAS 北大核心 2022年第3期645-650,共6页 Chinese Journal of Electron Devices
基金 国家自然科学基金项目(41075115) 江苏省重点研发计划社会发展项目(BE2015692) 无锡市社会发展科技示范工程项目(N20191008)。
关键词 人工嗅觉 传感器阵列 气体识别 一维卷积神经网络 artificial olfaction sensor array gas recognition one-dimensional convolutional neural network
  • 相关文献

参考文献9

二级参考文献49

共引文献86

同被引文献36

引证文献6

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部