小波神经网络在微弱信号检测中的应用

Application of Wavelet Neural Network to Weak Signal Detection

因为噪声总是会影响检测的结果,所以低信噪比下的信号检测是目前检测领域的热点,而强噪声背景下微弱信号的提取又是信号检测的难点。小波神经网络比数字滤波器更加适合检测微弱信号。小波神经网络是一种时频分析的自适应系统,它能检测信号中的微小变化。该文提出了一种新的检测白噪声中微弱信号的方法。仿真结果表明,小波神经网络在检测微弱信号的特征和改善信噪比方面是一种十分有效的方法。

The demand for detection of objects with low probability of observation is increasingly needed.The reason is that noises always badly affect measured results.The method of signal detection in low signal to noise ratio （SNR） is widely concerned.To detect the weak signals buried in noises is a fundamental and important problem.h has been found that digital filters are not suitable for processing weak signals in noise,while wavelet neural network （WNN） is used to analyze weak digital signal and extract small-features.WNN is a time-frequency analysis adaptive system,which detects the subtle small changes in the signal spectrum.In this paper,we propose a new method which is investigated by detecting the simulating weak signal in white noise.The results show that the WNN is a quite effective method for the extraction features of weak signal and improving the ratio of signal to noise.