论文部分内容阅读
This paper studies lithologic identification from log information based on PNN(Probability Neural Network).The models lithologic identification of log interpretation has been built and is applied to predict the testing samples.The prediction result has higher consistency with the practical cases.The prediction and convergence rate have been greatly improved compared to the tradi-tional BP Neural Networks,and the computational complexity has also been greatly reduced.The results show that the PNN is very promising for the application of lithologic identification.
This paper studies lithologic identification from log information based on PNN (Probability Neural Network). The models lithologic identification of log interpretation has been built and is applied to predict the testing samples. The prediction result has higher consistency with the practical cases. Prediction and convergence rate have been greatly improved compared to the tradi- tional BP Neural Networks, and the computational complexity has also been greatly reduced. The results show that the PNN is very promising for the application of lithologic identification.