Drilling automation
This comprehensive review of stuck pipe prediction methods focuses on data frequency, approach to variable selection, types of predictive models, interpretability, and performance assessment with the aim of providing improved guidelines for prediction that can be extended to other drilling abnormalities, such as lost circulation and drilling dysfunctions.
New case studies highlight how artificial intelligence, advanced hardware, and innovative business models are enabling success in drilling automation.
This paper tests several commercial large language models for information-retrieval tasks for drilling data using zero-shot, in-context learning.
-
This paper describes the application of learnings from an offshore project in the Caspian to an underground gas storage project to enhance drilling performance. -
The winners of this year’s Drillbotics competition are teams from the University of Stavanger and Clausthal University of Technology. Thirteen teams registered last fall, coming from seven countries spanning four continents.
-
CNPC’s record-breaking 11,100-m exploration borehole in the Taklamakan Desert promises to unlock the science of producing oil and gas trapped in the world’s deepest reservoirs.
-
The duo’s new services will be initially deployed in Iraq.
-
Nabors is connecting Corva’s platform to its universal rig controls and automation platform, allowing apps built and developed in Corva to monitor and control any rig equipped with the platform.
-
The authors of this paper present an autonomous directional-drilling framework built on intelligent planning and execution capabilities and supported by surface and downhole automation technologies.
-
The authors of this paper discuss a global rate-of-penetration machine-learning model with the potential to eliminate learning curves and reduce time and costs associated with developing a new model for every field.
-
The authors of this paper describe a project that demonstrated the feasibility of using deep-learning and machine-learning approaches to introduce camera-based solids monitoring to the drilling industry.
-
A joint webinar conducted by the Human Factors and Ergonomics Society and the Society of Petroleum Engineers addressed the role of human factors in automation in the oil and gas industry.
-
This paper highlights the potential of machine learning to be used as a tool in assisting the drilling engineer in bit selection through data insights previously overlooked.
