首先利用自回归线性预测技术消除地层厚度对测井曲线值的影响 ,然后从多条测井曲线中提取有效特征 ,再利用取心井训练神经网络来预测未知井 ,进而达到恢复薄、差地层真电阻率的目的。实际资料处理结果表明 ,此方法具有较好的应用前景。 Firstly, the effect of formation thickness on logging curve values ​​is eliminated by using the autoregressive linear prediction technique. Then, effective features are extracted from multiple logging curves, and then cored wells are used to train the neural network to predict unknown wells, so as to recover the thin and poor strata The purpose of true resistivity. The actual data processing results show that this method has a good application prospects.