基于量子蚁群优化的油田水淹层识别方法

摘要

To enhance the efficiency and accuracy of water flooded layer recognition ,a quantum ant colony optimization‐based identification method is proposed in this paper .First ,a Bloch sphere‐based quantum ant colony optimization algorithm is proposed ,and then ,the nonlinear regression model is derived from the sample data .Finally ,the parameters of model are optimized by quantum ant colony algorithm .The proposed method is simple ,intuitive ,and with clear physical concept .Tak‐ing actual water flooded layer data of Daqing oil field as example ,the simulation results show that the correct recognition rate of this method is 25 percent higher than BP neural network .%为提高油田水淹层识别精度及识别效率，论文提出一种基于量子蚁群优化算法的识别方法。首先提出一种基于 Bloch 球面搜索的量子蚁群算法，然后根据样本数据建立非线性回归模型，最后采用量子蚁群算法优化模型参数。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25％的提高。