基于量子差分进化算法的油田水淹层识别方法

Oilfield Water Flooded layer Identification Method Based on Quantum Differential Evolutionary Algorithm

为提高水淹层识别精度及识别效率,本文提出一种基于量子差分进化算法的识别方法。首先根据样本数据建立非线性回归模型,然后采用差分进化算法优化模型参数。方法简单直观,物理概念清楚。以大庆油田实际水淹层数据进行仿真,结果表明该方法的正确识别率比BP神经网络有15%的提高。

To enhance the efficiency and accuracy of water flooded layer recognition, a differential evolutionary-based identifica- tion method is proposed in this paper. First, the nonlinear regression model is derived from the sample data, and then, the parameters of model are optimized by quantum differential evolutionary algorithm. The proposed method is simple, intuitive, and with clear physical concept. Taking actual water flooded layer data of Daqing oil field as example, the simulation results show that the correct recognition rate of this method is 15 percent higher than BP neural network.