罗银河, 董桥梁, 俞国柱. 优化人工神经网络在折射波静校正中的应用[J]. 煤田地质与勘探, 2005, 33(1): 69-72.
引用本文: 罗银河, 董桥梁, 俞国柱. 优化人工神经网络在折射波静校正中的应用[J]. 煤田地质与勘探, 2005, 33(1): 69-72.
LUO Yin-he, DONG Qiao-liang, YU Guo-zhu. The application of optimized artificial neural network to refraction static correction[J]. COAL GEOLOGY & EXPLORATION, 2005, 33(1): 69-72.
Citation: LUO Yin-he, DONG Qiao-liang, YU Guo-zhu. The application of optimized artificial neural network to refraction static correction[J]. COAL GEOLOGY & EXPLORATION, 2005, 33(1): 69-72.

优化人工神经网络在折射波静校正中的应用

The application of optimized artificial neural network to refraction static correction

  • 摘要: 应用优化人工神经网络进行折射波初至拾取, 结合微测井和小折射资料反演风化层以及折射层速度, 并利用Taner全三维静校正原理进行折射波静校正。实际资料计算结果表明: 该方法有效提高了折射波初至拾取的效率, 很好地实现了CMP的“同相叠加”, 较好地改善了叠加剖面的信噪比和剖面的横向分辨率。

     

    Abstract: Optimized artificial neural network is used to pick refraction first arrival times, log and field refraction data are combined to inverse weathering layer velocity and refraction layer velocity, and Taner’s 3-D refraction static correction is applied in this paper. The result of real data shows that the work efficiency is enhanced by using Optimized artificial neural network to pick refraction first arrival times, the CMP gathers are stacked in phase and the ratio of S/N and transversal resolution of the stacked profile are improved.

     

/

返回文章
返回