基于模糊超球神经网络的沉积微相识别  

Automatic sedimentary facies identifying method based on fuzzy neural networks and image process technology

作　　者：唐世伟[1] 李子芳[1] 许少华[1] 

机构地区：[1]大庆石油学院计算机科学与工程学院,黑龙江安达151400

出　　处：《大庆石油学院学报》2002年第2期48-51,共4页Journal of Daqing Petroleum Institute

基　　金：黑龙江省自然科学基金资助项目 (F9917)

摘　　要：提出了一种基于模糊超球神经网络聚类与图像处理技术相结合的沉积微相识别方法 .首先将测井曲线和地层参数转化为二值点阵图像模式 ,经过数据编码压缩 ,提取和记忆地层模式特征 ,然后利用模糊超球神经网络聚类和BP算法相结合的方法训练多层前馈神经网络 .应用该方法识别了大庆油田的 186个小层的沉积微相 ,其网络自动识别准确率可达 86 .0 % .结果表明 ,该神经网络稳定 ,且具有良好的适应性 .In this paper we propose an automatic sedimentary facies identifying method based on combing fuzzy ellipsoidal neural networks and image process technology. First, we translate digital well measure curves and stratum parameters into binary image modes. Second, through contracting binary data codes, we distill and store stratum mode characters token from well measure curves. Last, we combine fuzzy ellipsoidal neural networks clustering and BP algorithm to train a multi-layers forward neural network. The neural network keeps properties of being stable, fast learning, awfully memorable and generalized ability. This model is suitable to solve issues of sedimentary facies identify. The test result shows this special method can identify sedimentary facies very well.

关 键 词：模糊超球神经网络 沉积微相 识别 模糊神经网络 图像处理 BP算法 测井曲线 大庆油田 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TE151[自动化与计算机技术—控制科学与工程]