使用免疫聚类和疫苗提取实现“大数”干扰滤波  

Realization of"big data"interference filtering using immune clustering and vaccine extraction

作　　者：陈强 邓博仁 蓝希先 CHEN Qiang;DENG Boren;LAN Xixian(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学电气工程与自动化学院,江西赣州341000

出　　处：《传感器与微系统》2023年第6期146-149,共4页Transducer and Microsystem Technologies

基　　金：江西省自然科学基金资助项目(2016BAB2016140)。

摘　　要：针对瓦斯传感器因受到强电磁干扰而造成误报警动作的问题,提出了一种基于人工免疫算法的抗干扰模型。通过离线学习和训练,提取两种信号的特征值并进行免疫聚类学习,在干扰信号中得到免疫疫苗,在在线测试中识别干扰信号,并用疫苗对其进行滤波,从而达到抗干扰的目的,根据仿真实验结果可以看出:该模型效果良好,可有效降低因“大数”干扰信号而造成的误报警。Aiming at the problem of false alarm action of gas sensor caused by strong electromagnetic interference,an anti-jamming model based on artificial immune algorithm is proposed.Through offline learning and training,characteristic values of two kinds of signals are extracted and immune clustering learning is carried out to obtain the immune vaccine from the interference signal.The interference signal is identified in online test and the vaccine is used to filter it,so as to achieve the purpose of anti-interference.According to the simulation results,it can be seen that the model has good effect.It can effectively reduce the false alarm caused by"big data"interference signal.

关 键 词：免疫算法 智能抗干扰 信号识别 瓦斯传感器 

分 类 号：TN911.7[电子电信—通信与信息系统]