论文部分内容阅读
针对油田水淹层识别存在的模糊性和多解性，提出了一种基于模糊神经网络的水淹层自动识别方法。该方法将神经网络技术所具有的高度自适应性、容错性及固有的并行处理能力与模糊逻辑所具有的模拟人类思维中的模糊综合判别特点有机地结合，实现了多因素模糊综合判断推理来完成水淹层自动识别。采用该方法，对大庆油田135个地层样本进行处理，符合率达87．6％。结果表明该方法对解决水淹层自动识别问题具有良好的适应性，可提高水淹层自动识别的精度。
Aiming at the fuzzy and multi-solution of waterflooded zone identification in oilfields, an automatic waterflooded zone identification method based on fuzzy neural network is proposed. This method combines the high degree of adaptability, fault tolerance and inherent parallel processing ability of neural network technology with the fuzzy comprehensive discrimination characteristic of the simulated human thinking possessed by fuzzy logic to realize the multi-factor fuzzy comprehensive judgment reasoning Complete water flooded layer automatic identification. Using this method, 135 stratigraphic samples from Daqing Oilfield were treated with a coincidence rate of 87.6%. The results show that this method has good adaptability to solve the problem of automatic recognition of water flooded layer and can improve the accuracy of automatic recognition of water flooded layer.