Research on TV imaging casing damage detection and classification method based on C4.5 decision tree

摘要

The casing damage is one of the important problems in oilfield development. The television imaging technology can get enough images of the inner wall of casing to detect the casing, but the efficiency of manually identifying the images is very low. Through the mapping relationship between image and casing damage type, the image features can be obtained. Then, the continuous data threshold selection of C4.5 decision tree algorithm is improved. Finally, the improved C4.5 decision tree algorithm is used to classify casing damage types. Experimental results show that the detection and classification method proposed in this paper can be well implemented.