神经模糊混合系统在测井储层识别中的应用

Application on Neuron-fuzzy Hybrid System for Log Reservoir Identification

储层识别是石油勘探中十分重要的基础工作,它可以为油田勘探和开发提供可靠的依据。神经模糊混合方法是通过对测井数据的学习,运用模糊逻辑与神经网络相结合的混合系统对测井数据进行提取和优化。根据来自不同油井的观测数据,采用一个二阶段的策略来决定该预测模型的结构和参数,从而对测井储层进行识别。给出了该混合方法预测的初步结果,为油井的开发提供了重要的参考。

Reservoir identification is a very important basis task in petroleum exploration and it may supply a decision criterion for oil exploration and exploitation. This paper proposes a neuron- fuzzy hybrid system approach to solve the problem of reservoir identification from log data. The new approach uses a hybrid system of fuzzy logic and neural network for extraction and optimization to log data via learning from it. A two-phase learning strategy is adopted to determine the structure and parameters of the predictive model on the basis of experimental data derived from different log; hence a log reservoir is identified. Preliminary results on the identification of the hybrid approach are reported, the important reference is provided for exploration of a new well.