录井油气水层判别的神经网络模型研究

Study on netural network model of distinguishing to logging oil and gas water layer

基于BP神经网络的算法原理,本文通过对渤海油田某工区录井、测井、测试数据等解释结论的学习和训练,构建了录井油气水层神经网络解释模型,运用该模型可进行储层流体性质的识别和划分,解释符合率达到了80%以上。

Based on the principle of BP neural network algorithm, interpretation results of mud logging, well logging and testing in Bohai oilfield are analyzed with the method of learning and training in this paper. In the study, the author built the model of BP neural network for the interpretation of oil, gas and water layers with mud logging data. By using this model, properties of reservoir fluids can be identified and divided. Finally, the interpretation coincidence rate of this model is proved to reach above 80%.