Study on Formation Pore Pressure Prediction for Wildcat Well
Formation pore pressure prediction before drilling is very important for safe drilling. Because of the poor pore pressure prediction, many accidents such.as blowout, lost circulation, sticking, and so on were occurred frequently. Nowadays at home and abroad, there are few reports about how to predict formation pore pressure for wildcat well. Based on the selection of similar structure, a method for predicting formation pore pressure of wildcat well is proposed in this paper. GA-BP (Genetic Neural Network) model is established by use of seismic data, logging data and formation test data of the well who has the similar structure to the wildcat well. On the basis of neural network theory, genetic algorithm is used to optimize neural network. According to seismic data, formation pore pressure of wildcat well will be predicted before drilling by use of this GA-BP model. Formation pore pressure for Xinjiang well DXi was predicted before drilling. Compared with evaluation results of logging data, average relative error of the prediction results is 9.6％. The field application results indicate that this method is feasible and has high accuracy.
formation pore pressure wildcat well interval velocity neta-al network genetic algorithm petroleum industry
ZHANG Hui GAO Deli
Department of Petroleum Engineering,China University of Petroleum,Beijing 102249,China
国际会议
The 2008 International Symposium on Safety Science and Technology(2008年安全科学技术国际会议)
北京
英文
2437-2440
2008-09-24（万方平台首次上网日期，不代表论文的发表时间）