论文部分内容阅读
通过对理论信号和实测信号的分析，研究了人工神经网络对层状介质结构识别的鲁棒性，分析了层状介质物理参数的变化对神经网络识别效果的影响．实验结果表明，各介质参数在一定范围内变化时，所得神经网络具有较强的鲁棒性．该研究结果反映出利用神经网络进行层状介质结构识别具有较强的实用价值．
By analyzing the theoretical signal and the measured signal, the robustness of artificial neural network to the identification of layered media is studied, and the influence of the change of physical parameters of layered media on the recognition effect of neural network is analyzed. The experimental results show that the neural network has strong robustness when the parameters of each medium change within a certain range. The results of this study show that using neural networks to identify layered media structures has strong practical value.