摘要
研究了地震信号在小波包变换下的特性,依据地震事件识别中"历史事例对比法"的思想,根据不同震源地震信号频率时变特性的不同,提出了基于"能量分布特征"的特征值,同时采用该特征值用神经网络方法对地震事件进行识别分类。该方法不依赖于系统的数学模型,而是直接利用各频率成分能量的变化提取特征值作为神经网络的输入特征向量来进行事件的识别,避免了对地震信号、传播途径准确建模的困难,简便、直观地完成了事件的识别。实验证明,该方法的事件识别率可达到99%以上,是一种有效的地震事件识别方法。
It is studied in this paper about the feature of seismic signal by wavelet packet. According to the difference of the time-frequency about seismic signals, a energy-distributing feature is proposed to i-dentify seismic events by neural network. This method directly extracts the feature of seismic signal by energy varying of every frequency component, which forms the input vectors of neural network to conveniently identify the seismic events. It doesn't depend on the mathematic model, and avoids the difficulty of exactly designing model about the spreading route of seismic signal. The ratio of discrimination to seismic signals is more than 99% by our experiment. It is proved to be the effective method.
出处
《核电子学与探测技术》
CAS
CSCD
北大核心
2004年第6期698-701,共4页
Nuclear Electronics & Detection Technology
