改进的K近邻方法在岩性识别中的应用

The advanced k-nearest neighborhood method used in the recognition of lithology

岩性识别是石油勘探中的一项重要内容,数据信息的精度往往会严重的影响到识别的准确率.本文根据数据的特点,改进了传统的K近邻方法,提出了加权K近邻的方法,进一步增强了利用测井数据识别岩性的能力,并在实际应用中证明了本方法的正确性和实用性.

Distinguishing of lithology is an import task in petroleum exploration. Sometimes the data accuracy will affect the percent accuracy of recognition. In this paper, based on the characteristics of data set, we put forward weighted knearest neighborhood method. It can strengthen the ability of recognition of lithology. We applied this method to practice and testified its correctness and practicability. 