Session: 11-03-02 Data Science Applications in Drilling

Paper Number: 127683

127683 - Intelligent Identification Workflow of Drilling Conditions Combining Deep Learning and Drilling Knowledge 

Oil and gas drilling is a complex construction process, drilling conditions as the key parameters of the construction process, efficient and accurate identification of drilling conditions is the basis for statistical drilling efficiency and analysis of drilling status. With the continuous development of integrated logging technology and sensor technology, field operators and researchers have access to large amounts of real-time data. The existing methods mainly include logical judgment and manual judgment, which have the problems of insufficient accuracy and low efficiency, respectively. In recent years, more and more scholars have adopted data-driven methods such as machine learning to identify drilling conditions, but pure data-driven models have the problem of high false positive rate. In this paper, an intelligent drilling condition identification method based on deep learning combined with drilling experience knowledge is proposed, which first removes the abnormal fluctuation of logging data through an efficient real-time data cleaning process, and then selects the most critical parameters to characterize the drilling state during the drilling process and extracts their change characteristics, and constructs an intelligent drilling condition recognition model based on deep learning algorithm. Then, according to the expert knowledge of working condition judgment, the logical constraint is formed, and it is added to the identification process. The final workflow can effectively realize the real-time intelligent identification of 10 drilling conditions, with an identification accuracy rate of more than 95%, and provide a basis for drilling efficiency analysis and risk prevention

Presenting Author: Zihao Liu China University of Petroleum (Beijing)

Presenting Author Biography: Liu Zihao, currently studying at China University of Petroleum (Beijing) with a doctoral degree, current research direction is oil and gas intelligent drilling and drilling risk intelligent analysis, has published multiple articles related to intelligent selection of drilling tools and drilling risk prediction.

Authors:

Zihao Liu China University of Petroleum (Beijing)
Xianzhi Song China University of Petroleum (Beijing)
Shanlin Ye China University of Petroleum (Beijing)
Baodong Ma China University of Petroleum (Beijing)
Chengkai Zhang China University of Petroleum (Beijing)
Zheng Wang China University of Petroleum (Beijing)
Xuezhe Yao China University of Petroleum (Beijing)
Zhaopeng Zhu China University of Petroleum (Beijing)
Yifan Wang China University of Petroleum (Beijing)