摘要
电磁炮测试中,炮口产生强烈的火光信号以及振动等噪声,会严重干扰电枢特征信号的识别处理;为了提升对电枢信号的自动识别率,提出了一种基于小波变换和卷积神经网络(CNN)相结合的电枢信号识别方法;利用小波变换对过靶信号进行小波阈值去噪,进而重构信号,然后利用CNN提取信号的深层次特征,通过CNN的全连接层输出信号的分类结果;当输入信号为电枢信号时,对其作最大值检测获取电枢信号的特征点;实验结果表明,所提方法对比传统小波阈值滤波法在特征点自动拾取准确率上提升了5.88%;该算法对电磁炮电枢过靶信号的滤波、识别具有一定的参考意义。
In the test of an electromagnetic gun,a muzzle generates the strong fire-light signal and noise such as vibration,which can seriously interfere with the recognition processing of armature feature signals.In order to improve the automatic recognition rate of armature signals,an armature signal recognition method based on the combination of wavelet transform and convolutional neural network(CNN)is proposed.The wavelet transform is used to denoise the over-target signal with the wavelet threshold,and then the signal is reconstructed,and then the CNN is used to extract the deep-level features of the signal,and the classification result of the signal is output through the fully connected layer of the CNN.When the input signal is an armature signal,the maximum detection is performed to obtain the feature points of the armature signal.The experimental results show that compared with the traditional wavelet threshold filtering methods,the automatic picking accuracy of the proposed method improves 5.88%in feature point.The algorithm has a certain reference significance for the filtering and identification of electromagnetic gun armature over-target signals.
作者
田霖浩
杨俊
郭昊琰
TIAN Linhao;YANG Jun;GUO Haoyan(School of Information and Communication Engineering,North University of China,Taiyuan 030051,China)
出处
《计算机测量与控制》
2023年第4期161-166,共6页
Computer Measurement &Control
关键词
小波变换
小波阈值
卷积神经网络
电磁炮
光幕靶
wavelet transform
wavelet threshold
convolutional neural network
electromagnetic gun
light curtain target
