基于径向基神经网络的油藏反演方法

文章提出一种基于径向基(radial basis function, RBF)神经网络的油藏反演方法。该方法利用抽样生成的井底压力数据构造RBF神经网络模型，由RBF神经网络预测值与实际观测值的偏差定义目标函数，再利用粒子群算法(particle swarm optimization, PSO)对其进行优化，最终得到不确定参数的最优解和反演参数。与多项式拟合方法相比，RBF神经网络方法具有更好的拟合结果和更高的精度，甚至在多项式拟合方法失效时，该方法也能得到很好的模拟结果。油田实际算例表明，该方法具有良好的拟合效果，能大幅提高反演效率，具有很好的应用前景。

This paper proposes a reservoir inversion method based on radial basis function(RBF) neural network. In this method, the RBF neural network model is constructed by using the bottom hole pressure(BHP) data generated by sampling, and the objective function is defined by the deviation between the predicted value of the RBF neural network and the actual observed value, and then the particle swarm optimization(PSO) algorithm is used to optimize the objective function. Finally, the optimal solution of the uncertain parameters and the inversion parameters are obtained. Compared with the polynomial fitting method, the RBF neural network method has better fitting results and higher precision. Even when the polynomial fitting method fails, the RBF neural network method still works well. A practical example in oilfield shows that this method has good fitting effect, can greatly improve the inversion efficiency, and has a good application prospect.