基于模糊C均值聚类算法的岩屑识别方法研究  

Cutting recognition based on Fuzzy C-means clustering algorithm

作　　者：万红吉[1] 杨晓敏[1] 陈默[1] 吴炜[1] 白茹[1] 滕奇志[1] 吴凤翼[1] 

机构地区：[1]四川大学电子信息学院,成都610064

出　　处：《四川大学学报（自然科学版）》2010年第3期537-542,共6页Journal of Sichuan University(Natural Science Edition)

摘　　要：采用代数平均的办法对不同岩性的岩屑图像进行颜色RGB分量提取和分析,提取了反映不同岩屑岩性的特征参数,最后将模糊C均值聚类算法应用到岩屑的识别过程中,取得了较好的识别效果.通过对四川大邑3口天然气井的现场随钻采样实验,结果证明算法识别正确率达到90%以上,为快速分析录井现场岩屑的岩性提供了一条有效的途径.During PDC bit drilling, how to recognize the rock fragments automatically and objectively is very important. In this paper, a research is proposed for color and gray of rock fragments. First, the color and gray of rock fragments are detected by using algebraic average. Then the features are used to train the support fuzzy C-means clustering algorithm classifier. Finally, the rock fragments are classified by using the trained support fuzzy C-means clustering algorithm. Using the algorithm, after logged 3 wells of Dayi of Sichuan gas reservoir, a high recognition rate can be reached. The experimental results demonstrate the algorithm is feasible, robust and applicable.

关 键 词：PDC钻头 岩屑识别 模糊C均值 颜色RGB分量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]