基于改进OS-ELM的电子鼻在线气体浓度检测  

Online gas concentration detection of electronic nose based on improved OS-ELM

作　　者：朱梓涵 陶洋[1] 梁志芳 Zhu Zihan;Tao Yang;Liang Zhifang(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065

出　　处：《电子技术应用》2023年第10期71-75,共5页Application of Electronic Technique

基　　金：国家重点研发计划项目(2019YFB2102001)。

摘　　要：电子鼻是一种仿生传感系统,该设备能够同时对多种气体进行识别,因此应用在许多领域当中。气体浓度算法是电子鼻对气体定量分析时的核心部分,为了提高电子鼻浓度检测算法精度,提出一种基于在线序列极限学习机(Online Sequential-Extreme Learning Machine,OS-ELM)的预测模型。该模型通过一维卷积神经网络(One Dimen‐sional Convolutional Neural Network,1DCNN)提取特征,使用OS-ELM对气体浓度进行预测,并提出了一种改进的粒子群(Particle Swarm Optimization,PSO)算法以克服OS-ELM需人工调整模型参数的问题。由理论分析,改进的算法比传统PSO算法有更强的搜索能力。实验结果表明,所提模型对气体的预测精度上较传统的预测模型具有更高的预测精度和泛化能力。Electronic nose is a bionic sensing system,which can identify many gases at the same time,so it is used in many fields.The gas concentration detection algorithm is the core part of the gas quantitative analysis by electronic nose.In order to improve the accuracy of the electronic nose concentration detection algorithm,a prediction model based on online sequential-extreme learning machine(OS-ELM)is proposed.The model uses one-dimensional convolutional neural network(1DCNN)to extract features,uses OS-ELM to predict gas concentration,and proposes an improved Particle Swarm Optimization(PSO)algorithm to overcome the problem that OS-ELM needs to manually adjust model parameters.The theoretical analysis shows that the improved algorithm has stronger search ability than the traditional PSO algorithm.Finally,the experimental results show that the proposed model has higher prediction accuracy and generalization ability compared with the traditional prediction model.

关 键 词：电子鼻 浓度检测 一维卷积神经网络 在线序列极限学习机 粒子群算法 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]