Digital transformation of oil and gas companies requires consistent improvement of work performance management. Oil and gas companies strive to improve work efficiency and consistently develop and implement digital products. The realization of such complicated solutions requires deep diving into current business processes and transformation of them. This paper deals with implementation of digital management system for exploration and production wells. Digital management system for exploration and production wells is based on ideology of digital twin and act as a single window and single source of data for all exploration and production wells. Digital management system covers whole construction process started from planning stage to execution and results assessment and orchestrates the exchange of data between process phases and people involved in it. Transparency provided by the digital twin improves efficiency and accelerates well construction process. Cognitive assistants based on AI and ML techniques are implemented at every stage: while planning, the assistants search analogue wells, analyze its design and complications while drilling and provide recommendations for the most optimal well design, offers the optimum drilling mud density and recommends the most suitable set of logs to cover geological section uncertainty. At the execution stage, a number of ML assistants are used to increase efficiency and reduce risks while drilling: automatic method for anomaly detection while drilling to prevent complications while drilling, machine learning based model for automatic torque and drag control to control borehole condition to predict any signs of differential stuck, key sitting and pack-off, data-driven model for drilling bit position and direction determination to predict BHA position while drilling including a blind zone, data-driven model for the identification of the rock type at a drilling bit for correct geosteering application.

As part of the digital transformation, the oil and gas sector should move beyond the traditional way of drilling, towards utilizing new and more efficient technologies. The objective of this paper is to show how a digital twin based on the virtual model of a drilling well can be used to optimize the operation and improve operational performance. Utilizing digital twins in drilling is a more advanced and cost-effective method to plan, monitor and operate well construction than the traditional method. A Digital twin in drilling is to use advanced down hole data and advanced modeling of the physical drilling system based on thermo-hydraulic and mechanical models during the lifecycle of well construction. It provides several benefits to the operation and improves drilling performance. Various drilling models interact during the whole drilling life cycle. During operations, real-time data from wells are used in combination with modeled data from a digital twin. This can realize early detection of anomalies and offer early diagnostic messages to avoid problems before they fully develop. It helps to reduce non-productive time and increase safety. The Digital Twin technology can be used during the whole drilling operation. Several drilling case studies will be presented using the digital twin to provide real-time ECD control during tripping in and out of the well, as well as back-reaming procedure on some oil fields. Automatic pickup hook load roadmap plotting including; lift, slack and rotation off bottom (ROB), for some oilfields are discussed. The results of the simulation are presented in both 2D and 3D visualization format. By using the digital twin, challenges and risks during the operation have been identified. Automated diagnostic alarms have detected and prevented hazardous incidents ahead of the time. Digital Twin technology will play an important role in the automation process of drilling. The technology will provide automatic quality control and calibration of drilling data, automated forward looking, automated diagnostics and decision support and eventually automatic optimization of the drilling process in real-time. This will be achieved by linking the Digital Twin to the rig control system.

Summary In this paper we present a new data-driven methodology for a drilling bit position and direction determination. The model is based on machine learning approach and trained on a data collected in a real-time or near real-time: mechanical parameters of drilling, tool-face data, MWD/LWD data, etc. The proposed methodology might be an interest for directional drilling service companies, operator companies that develop low-thickness productive strata. One of the main advantages of the proposed approach is economic efficiency which it provides due to absence of additional costs associated with payments for additional man hours for precise trajectory and direction monitoring. Methodology allows to predict trajectory at any time of drilling. The methodology is illustrated on the historical data of drilling of one oilfield. At the current stage, the results of the testing show good quality. Blind test on 154 independent sliding episodes shows that median absolute error (MedAE) of depth, inclination and azimuth are 0.26 m, 0.25° and 0.42°. These errors will decrease after adding more wells and steps, which are described in future plans.

No abstract