用自组织神经网络实现地震同相轴自动追踪

Seismic event automatic tracking using self-organizing neural network

1. 清华大学自动化系, 北京 100084;2. 石油大学, 北京 100083

Department of Automation, Tsinghua University, Beijing 100084

本文提出了一种用自组织神经网络自动追踪地震同相轴的方法。文中简单地介绍了自组织神经网络,并针对地震同相轴追踪这一具体问题,设计了相应的学习方法。自组织神经网络可以进行无监督学习,且可以边学习边工作,因此本文提出的方法追踪迅速,自动化程度高。实际资料处理结果表明,本方法具有较好的应用前景。

A seismic event automatic tracking method by means of self-organizing neural network is presented in this paper. The self-organizing neural network is introduced simply here. In connection with the concrete problem of seismic event tracking, we design a corresponding learning method. The method is rapid in tracking and high in automation degree because the self-organizing neural network can learn without supervision and can learn and work at the same time. The real data processing result indicates that the method has good prospect.