基于BP神经网络的深部地层压力预测技术

地层压力的准确预测是优质高效安全钻井、减少井下复杂情况、合理开发油气层的基础.由于地层压力的实测方法费用较高、周期长,且影响钻井安全,因此提出一种基于神经网络技术的地层孔隙压力预测新方法,并详细论述了神经网络预测模型的建立过程.该方法以声波时差、自然电位、自然伽马数等测井数据及钻杆压力测试数据为学习样本,具有十分高的准确度.对大庆油田萨尔图和杏树岗两个区块的地层压力进行实例预测,预测结果表明,其预测结果与实测结果的相对误差<±8.9%.

Pressure Prediction Technology of the Deep Strata, Based On the BP Neural Network

The accurate prediction of strata pressure is the base for safely, qualitily, and efficiently drilling, decreasing hole problems and reasonable development of the reservoir. Because of the high cost, long cycle of the formation pressure measured method, which may influences the safety of drilling operation, thus a new method for predicting strata pressure, based on the BP neural network, is presented in this paper, and establishing process of the neural network forecast model are discussed in detail. This method takes the acoustic time, natural potential, natural gamma ray log data and pipe pressure test data as study sample, which has a very high accuracy. The paper predicts strata pressure of the Saertu oil field and Xingshugang oil field in Daqing, and the results show that relative error between the predicted data and experimental data is less than ?.9%.