利用BP神经网络进行测井资料外推

Logging data extrapolation using BP neural network

针对在地震资料约束下测井资料外推的具体问题，修改了BP网络的能量函数，增加一项反演目标函数，使之作为一项新的能量约束，从而实现用BP网络自适应地外推测井资料，有机地将BP网络与地震反演结合起来。本文论述了其理论与算法，并给出了资料处理应用实例。对实际资料的测井速度外推结果表明，此方法处理速度快、稳定性好、可信度高，具有较好的应用前景。

In order to cope with the problem of logging data extrapolation that is restrained by seismic data, we revise the energy function of BP neural network andadd an inversion objective--function as a new energy restraint,so that people can doadaptive extrapolation of logging data and then combine BP network with seismicdata inversion. We expound the theory and algorithm of the technique,and offer application example in the article. The extrapolation result of real logging velocityshows that this technique will find good application because it brings fast operation, good stability and high reliability.