论文部分内容阅读
根据人工神经网络理论,初步研究了人工神经网络对地震信号及震相进行识别的能力.为了进行识别,将三分向地震资料的矢量模作为神经网络的输入.结果表明:用此方法确定地震震相和到时是十分有效的,特别是对于信噪比较高的地震记录,效果更好.
According to artificial neural network theory, the ability of artificial neural network to recognize seismic signals and seismic facies is studied preliminarily.In order to identify, the vector mode of tridimensional seismic data is used as the input of neural network.The results show that using this method to determine the seismic Seismic phase and arrival time is very effective, especially for the high signal-to-noise ratio of seismic records, the better.