阵列传感器气体浓度检测的改进型海鸥算法研究  

Research on Improved Seagull Algorithm for Gas Concentration Detection of Array Sensor

作　　者：李鹏 纵彪[2,3] 林事力 张立豪 刘轩宇 LI Peng;ZONG Biao;LIN Shili;ZHANG Lihao;LIU Xuanuyu(School of Automation,Wuxi University,Wuxi Jiangsu 214105,China;Jiangsu Key Laboratory of Meteorological Observation and Information Processing,Nanjing University of Information Science&Technology,Nanjing Jiangsu 210044,China;Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology,Nanjing University of Information Science&Technology,Nanjing Jiangsu 210044,China)

机构地区：[1]无锡学院自动化学院,江苏无锡214105 [2]南京信息工程大学,江苏省气象探测与信息处理重点实验室,江苏南京210044 [3]南京信息工程大学,江苏省大气环境与装备技术协同创新中心,江苏南京210044

出　　处：《电子器件》2025年第1期31-37,共7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(BE201569);无锡市社会发展科技示范工程项目(N20191008)。

摘　　要：针对阵列传感器对二元混合气体定量检测时由于交叉敏感特性导致检测精度低的问题,提出一种改进型的海鸥算法优化核极限学习机算法。该方法首先使用核主成分分析(KPCA)对数据进行降维处理以及特征提取,选择贡献率大的主成分作为输入向量,其次改进了海鸥算法(SOA)中的非线性收敛因子B和螺旋形状系数u、v,再使用改进型海鸥算法优化核极限学习机(KELM)的关键参数,即正则化系数C和核参数σ,组成SOA-KELM定量检测模型,最终计算分析后输出结果。实验结果表明改进型海鸥算法搜索能力更好,改进型海鸥算法优化核极限学习机(SOA-KELM)的回归能力更强,检测误差更小,相关系数检测在0.9916以上,为阵列传感器气体浓度检测提供了一种新方法。Targeting at the problem of low detection accuracy due to cross-sensitivity when the array sensors are used to detect binary mixed gas quantitatively,an improved seagull algorithm is proposed to optimize the kernel extreme learning machine algorithm.Firstly,the kernel principal component analysis(KPCA)is used to reduce the dimension of the data and extract the features.The principal com-ponent with large contribution rate is selected as the input vector.Secondly,the nonlinear convergence factor(B)and two spiral shape coefficients(u and v)in the seagull algorithm(SOA)are improved.Then,the improved seagull algorithm is used to optimize the key pa-rameters of the kernel extreme learning machine(KELM),namely the regularizition coefficient(C)and the kernel parameter(σ),to form the SOA-KELM quantitative detection model.Finally,the output results are calculated and analyzed.The experimental results show that the improved seagull algorithm has better search ability and higher accuracy.The improved seagull algorithm optimizes the kernel extreme learning machine(SOA-KELM)with stronger regression ability.The correlation coefficient detection is above 0.9916,which provides a new method for gas concentration detection by using array sensors.

关 键 词：浓度检测 核主成分分析 核极限学习机 改进型海鸥算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP212.9[自动化与计算机技术—控制科学与工程]