Improving drilling efficiency and reducing well construction period using machine learning and big data

Improving drilling efficiency and reducing well construction period using machine learning and big data

Machine learning

Efficiency

Big data

Offshore oil well production

Offshore technology

Infill drilling

Decision trees

Offshore oil wells

Data Analytics

Classification (of information)

Informatization

In the informatization and intellectualization era of oil and gas, automation is essential to measure and track detailed performance for routine drilling operations by automatically measuring these individual operations consistently. Presently, the analysis of drilling effectiveness usually relies on manual post analysis, which is subjective and arbitrary, and cannot reflect the real field situation in time, resulting in great deviation. Therefore, this paper proposes a new method combining big data and machine learning, which can learn experience from drilled wells and apply learned experience in new well to be drilled. To develop the methodology, firstly, 8 comprehensive logging parameters for 5 drilled wells in same block are collected. Data analysis through decision tree is carried out to develop an intelligent rig state classification system considering the different drilling process. secondly, the continuous improvement system based on the intelligent rig state classification system is established to analyze invisible nonproductive time during drilling and learn experience from 5 wells in the database. Thirdly, the learned experience from continuous system, which are some approaches to eliminate the nonvisible productive time, will be applied to the new wells to be drilled. Consequently, a new method combining logging big data and machine learning, is proposed for drilling efficiency improvement. The results show that the average accuracy of the rig state classification by the proposed method is 92%, and the proposed continuous improvement method has successfully eliminate non invisible production time and the well construction time has been shorten by 34.6% comparing with the wells drilled before, which yields time and cost savings for tomorrows market. This is one of the first attempts for improving drilling efficiency considering comprehensive data using machine learning and big data. This methodology is successfully applied to drilling performance improvement, which reducing well construction period and save the cost. Copyright 2020, Offshore Technology Conference

Xu, Jie

Yang, Jin

Zhang, Wandong

Hou, Xinxin

Zhao, Xin

Yin, Qishuai

Zhao, Shaowei

Xie, Tao

Zhang, Lei

Lin, Hai

Hao, Mingxuan

Offshore Technology Conference Asia 2020, OTCA 2020, November 2, 2020 - November 6, 2020

2020

conferencePaper