摘要
针对传统微弱信号检测方法在混沌背景下的检测能力较弱,提出了一种基于IA-SVM模型的混沌小信号检测方法。该方法经求嵌入窗构建混沌相空间后,利用免疫算法寻优能力对支持向量机中影响预测精度的三个参数进行优化,从而建立混沌时间序列的预测模型。实验验证结果表明,预测信号的均方根误差为0.0001463(信噪比为-104.2473 dB),较传统微弱信号检测方法有着显著优势。
Aiming at the poor detection ability of traditional weak signal detection method under chaotic background,a chaotic small signal detection method based on IA-SVM model was proposed.The method was constructed by embedding the window to construct the chaotic phase space,the immune algorithm optimization ability was used to optimize the three parameters in the support vector machine that affect the prediction accuracy,so as to establish the prediction model of the chaotic time series.Experimental verification results showed that the root mean square error of the predicted signal was 0.0001463(signal-to-noise ratio is-104.2473dB),which had significant advantages over the traditional weak signal detection method.
作者
孙江
行鸿彦
吴佳佳
SUN Jiang;XING Hongyan;WU Jiajia(Collaborative Innovation Center for Meteorological Disaster Prediction and Evaluation, Nanjing University of Information Science and Technology, Nanjing 210044, China;Jiangsu Key Laboratory of Meteorological Detection and Information Processing, Nanjing University of Information Science and Technology , Nanjing 210044, China)
出处
《探测与控制学报》
CSCD
北大核心
2020年第3期119-125,共7页
Journal of Detection & Control
基金
国家自然科学基金项目资助(61671248,41605121)
江苏省重点研发计划项目资助(BE2018719)。
关键词
微弱信号检测
免疫算法
支持向量机
混沌特性
weak signal detection
immune algorithm
support vector machine
chaotic characteristics
作者简介
孙江(1996—),男,江苏南京人,硕士研究生,研究方向微弱信号检测、仪器仪表,E-mail:1643719315@qq.com。
