论文部分内容阅读
针对地震勘探数据采集工作中存在大量废道的问题,提出了一种基于BP神经网络的废道自动切除方法。通过对废道的产生机理和干扰特性的深入分析,提取能够反映废道本质特征的参数,结合BP神经网络强大的模式识别和自主适应能力,设计了一个三层的BP神经网络结构;最后,采用实际地震资料对处理算法进行验证。结果表明,该方法废道处理的准确率高、处理速度快,并且具有良好的适应性,能够满足地震勘探工作对废道处理的要求。
Aiming at the problem of a large number of waste tracks in the seismic data acquisition, an automatic waste strip removal method based on BP neural network is proposed. Through in-depth analysis of the generation mechanism and interference characteristics of the waste passage, the parameters which can reflect the nature of the waste passage are extracted and combined with the powerful pattern recognition and autonomous adaptability of BP neural network to design a three-layer BP neural network structure. Finally, The actual seismic data is used to verify the processing algorithm. The results show that this method has the advantages of high accuracy, fast processing speed and good adaptability, which can meet the requirements of the seismic exploration work on the waste disposal.