首页|Image processing and machine learning based cavings characterization and classification
Image processing and machine learning based cavings characterization and classification
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Wellbore failure is the most headache and common problem in drilling engineering.Wireline loggings like caliper log and image log are usually used to identify wellbore failure.However,it is impossible to discern the failure types and take steps in real-time using the post-drilling methods.During the drilling process,various cavings will circulate to the ground with drilling fluid when wellbore instability occurs.These cavings are the foremost indicator of wellbore deterioration and have a potential link to the mechanism of borehole failure.Unfortunately,the use of cavings to understand borehole instability and its mechanism requires correct descriptions of caving which are inclined to be qualitative and fragmentary in previous studies,as well as proper interpretation which entails a wealth of field experience and comprehensive understanding of drilling,geo-mechanics and geology.This paper proposes a new method for caving characterization and a caving interpretation workflow based on image processing and machine learning.Firstly,we thoroughly analyze all modes of borehole failures and the corresponding cavings they generate,and make clear the significant characteristics to distinguish different types of cavings.Then the morphologies of caving contour and surface are quantitatively characterized using Speeded-Up Robust Features(SURF)algorithm and 2D-Discrete Wavelet Transform(DWT),respectively.These two categories of characteristics are used as the input of Light Gradient Boosting Machine(LightGBM)-based classification model,and the mode of borehole failure that generates the caving can be inferred from the classification results.We demonstrate the application of this interpretation workflow utilizing the cavings from the T oilfield,Xinjiang,China.The result shows that the average accuracy of classification is 90.9 %,which reflects that the workflow has a satisfactory performance in caving interpretation as well as that the features have high representativeness and robustness for caving characterization.This method opens up a new path to the early warning of borehole instability and real-time diagnosis of instability mechanism,thus corresponding remedies can be taken in time to avoid serious downhole accidents.
NSTL
