Abstract:

To solve the problem of low recognition accuracy of radar new active jamming in strong noise environment， a KPCA-SAE-BP network algorithm is proposed. The features of jamming signal in time domain， frequency domain， waveform domain， wavelet domain and bispectral domain are extracted to construct 67-dimensional input space， and the high-dimensional data is nonlinear dimensionality reduction and reconstruction through kernel principal component analysis （KPCA）. A SAE-BP neural network is then used for classification and recognition. Simulation experiments show that in strong noise environment where JNR is greater than -1dB， the recognition accuracy of the KRPA-SAE-BP network algorithm for six new active Jamming is more than 90%， and the training and recognition time is less than 0.7 seconds. Compared with classical BP neural network， SAE-BP network， PCA-BP network and GA-BP network， it has better detection and recognition performance.

Key words: active jamming recognition, kernel principal components analysis（KPCA）, stacked auto encoder（SAE）, backpro pagation（BP） neural network, feature extraction, feature dimension reduction

摘要：

针对强噪声环境下雷达新型有源干扰识别准确率不高的问题，提出了一种KPCA-SAE-BP网络算法。提取干扰信号时域、频域、波形域、小波域、双谱域等特征构建67维输入空间，经过核主成分分析(kernel principal component analysis，KPCA)将高维数据进行非线性降维与重构，利用SAE-BP神经网络完成分类识别。仿真结果表明，在干噪比(JNR)大于-1 dB的强噪声环境中，KPCA-SAE-BP网络算法对6种新型有源干扰的识别准确率达到90%以上，训练与识别时间少于0.7 s。相同参数条件下，与经典BP神经网络、SAE-BP网络、KPCA-BP网络、GA-BP网络相比，具有更好的检测识别性能。

关键词: 有源干扰识别, 核主成分分析, 堆叠自编码器, 反向传播神经网络, 特征提取, 特征降维