利用BP网络技术进行油井流入动态分析方法研究

论述了应用人工神经网络技术进行油井流入动态分析的方法 :将油井视为一个黑箱非线性动态系统 ,不需要建立描述油井动态的复杂数学模型 ,只要对其动态系统的输入 /输出进行网络训练 ,即可建立相应的人工神经网络预测模型 ,并用此进行油井流入动态预测及分析 ,绘制出精确的 IPR曲线 .依据 BP网络和实际应用的特点 ,提出了滚动预测技术 ,并对该技术进行了实例分析 ,取得了较好的效果 .

Study on Analyzing the Inflow Performance of Oil Wells by BP Network Technique

The method is discussed of analyzing the inflow performance of oil wells by artificial neural network technique. In this method, an oil well is considered as a black box-like nonlinear dynamic system, so there is no need to build up a complicated mathematical model describing the dynamic of the oil well. The corresponding neural network prediction model can be built up by means of network learning of input/output of the dynamic system. The dynamic prediction and analyses for oil wells can be done and accurate IPR curve is drawn according to the model. Based on the various improved methods of BP networks, the structure and algorithm of networks are improved and optimized. At the same time, according to the characteristic and practical application of BP networks, a technique of rolling predicting is put forward. Finally good effects are gained by applying this technique to producing wells.