常规声波时差曲线高分辨率处理方法

Method for high resolution processing of conventional acoustic slowness log

分析了常规声波测井的纵向响应特征,研究了低分辨率声波时差曲线和高分辨率声波时差曲线间非线性映射关系.在此基础上,将关键井的高、低分辨率声波时差曲线作为学习样本,构建学习样本集;以人工神经网络技术为手段,建立反演预测模型,进而生成其它井的高分辨率声波时差曲线.选择了大庆油田某区块8口井作为建模和预测对象,实际应用表明:预测的高分辨率时差曲线的平均相对误差为6.80%,最大相对误差在1.631 km处,为24.80%,最小相对误差在1.629 km处,为0.06%.

Based on analyzing the vertical response characteristic of conventional acoustic logging, researching thoroughly the very complex nonlinear relationship between conventional acoustic slowness log with low resolution and slowness log with high resolution, forecasting model is established using training samples consisting of key wells' slowness curves with high, low vertical resolution to create the other well's slowness curve with higher vertical resolution by means of Artificial Neural Networks(ANN) technique. Some 8 wells in Daqing Oilfield are selected as object of establishing model and forecasting. As shown in the practical applications, the average relative error of high resolution acoustic slowness log predicted is 6.80%, the maximum average relative error is 24.8% at 1.631 km while the minimum average relative error is 0.06% at 1.629 km. Therefore,it has wide application perspective.