Intelligent Drilling Surveillance Through Real Time Diagnosis

Rey-Fabret, I.; Nauroy, J.F.; Vincké, O.; Peysson, Yannick; King, Isabelle; Chauvin, H.; Cagnard, F.

doi:10.2516/ogst:2004026

Cited by 3 publications

(1 citation statement)

References 11 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The real-time information is combined with a predefined knowledge to identify and predict unexpected events or abnormal modes. The drilling industry has developed multiple applications for process control, automation and simulation, which include a diagnosis approach [1], [2], [3]. Rig-site diagnosis systems include alarm systems to warn the driller when an abnormal situation is rising.…”

Section: Overviewmentioning

confidence: 99%

Geosteering Diagnosis: A New Approach to Monitor the Well Position Within a 3D Geological Model

Thevoux-Chabuel¹,

Fejerskov

2006

Proceedings of SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

TX 75083-3836, U.S.A., fax 01-972-952-9435. AbstractWith the increasing demand for more efficient drilling operations, the oil industry is searching for new ways of utilizing all data available while drilling. The integration of the realtime drilling information with data from offset wells and the reservoir model is considered of high value for accurate wellbore placement and geosteering. This paper introduces an original methodology to better understand and analyze the well position within the subsurface and to warn the end user when predefined geological and drilling events are appearing or prognosed ahead of the drill bit. The concept is called Geosteering Diagnosis. We identify a monitored trajectory as composed of a real-time and a project-ahead section. The bit and the MWD/LWD sensors are monitored objects attached to the trajectory. A number of targeted objects (i.e. horizons, contacts, faults, targets, planned and previous drilled wells trajectories, well and grid properties) are accessible from the 3D geological model. Rules can be defined based on the relationship between the monitored objects and any targeted objects. Various thresholds are used to identify events at the time of the drilling and alarms can be triggered on specific cases. The Geosteering Diagnosis is applied to a production well in the North Sea. The rules are used to monitor drilling against the predefined geological model. They provide quantitative information, which can be used to either update the geological model, or take actions regarding the course of the well.

show abstract

Section: Overviewmentioning

confidence: 99%

Geosteering Diagnosis: A New Approach to Monitor the Well Position Within a 3D Geological Model

Thevoux-Chabuel¹,

Fejerskov

2006

Proceedings of SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

show abstract

Geosteering Diagnosis: A New Approach to Monitor the Well Position within a 3D Geological Model

Thevoux-Chabuel

Fejerskov

2006

All Days

View full text Add to dashboard Cite

With the increasing demand for more efficient drilling operations, the oil industry is searching for new ways of utilizing all data available while drilling. The integration of the realtime drilling information with data from offset wells and the reservoir model is considered of high value for accurate wellbore placement and geosteering. This paper introduces an original methodology to better understand and analyze the well position within the subsurface and to warn the end user when predefined geological and drilling events are appearing or prognosed ahead of the drill bit. The concept is called Geosteering Diagnosis. We identify a monitored trajectory as composed of a real-time and a project-ahead section. The bit and the MWD/LWD sensors are monitored objects attached to the trajectory. A number of targeted objects (i.e. horizons, contacts, faults, targets, planned and previous drilled wells trajectories, well and grid properties) are accessible from the 3D geological model. Rules can be defined based on the relationship between the monitored objects and any targeted objects. Various thresholds are used to identify events at the time of the drilling and alarms can be triggered on specific cases. The Geosteering Diagnosis is applied to a production well in the North Sea. The rules are used to monitor drilling against the predefined geological model. They provide quantitative information, which can be used to either update the geological model, or take actions regarding the course of the well. Introduction 3D visualization tools are today part of the drilling operation process, allowing a better communication and understanding between the experts of the asset team. Real-time data are integrated within the earth model and can be visualized in real-time operation centers. Measurement While Drilling data (MWD) and the Logging While Drilling data (LWD) are used to evaluate the position of the well, assess the physical properties of the rocks and fluids drilled, and analyze the behaviour of the drillstring in real-time. Positioning horizontal wells within few centimetres height of targeted areas is only possible because of the evolution of the combined drilling and logging technologies. From the kick-off point, through the landing area and within the reservoir it is critical to have the best possible understanding of the formations crossed by the drill bit. The LWD data provides that knowledge in real-time at a high resolution scale. An optimal decision making process will not only rely on a constant monitoring of the drilling data within the 3D geological environment, but also on an accurate understanding of where these measurements are performed along the drillstring. Some logging data can effectively be measured tens of meters behind the bit. Each of the physical property measured by the MWD/LWD tools can be defined onto the Bottom Hole Assembly by its distance from the bit. The experience shows that it is often difficult to measure the distances between a measurement point along the BHA and a particular object in the 3D geological model. But this knowledge is important for the asset team for taking actions regarding the update of the 3D earth model at the time of the drilling. A diagnosis approach was then proposed to constantly monitor and analyse the MWD/LWD information against the geological model and predict future trends of the data based on the project-ahead trajectory. The methodology relies on the definition of rules based on measured distances and property differences between tools on the BHA and objects of the geological model. By applying multiple thresholds on the rules it is possible to define different levels of warnings, which will help to identify and predict coming events. At the same time the project-ahead approach is used to predict when possible events will appear. The Geosteering Diagnosis can be an excellent tool to help validating the geological model update at the time of the drilling. A final objective, but somewhat far away at this preliminary stage, would be automated well follow-up and steering reducing on-site personal.

show abstract

Deep Learning Approach of Drilling Decision for Subhorizontal Drain Geosteering Based on APC-LSTM Model

Zhu

Dai

Liu

et al. 2022

SPE Drilling &Amp; Completion

View full text Add to dashboard Cite

Summary Steering drilling is used for exploring oil, natural gas, and other liquid and gaseous minerals. Steering drilling consists of high-efficiency drill bits, steering power drilling tools, and logging while drilling (LWD) and is used in petroleum drilling engineering. This paper mainly discusses subhorizontal drain geosteering, one of the methods of guided subhorizontal drilling. We use the currently popular deep learning method to conduct intelligent guided drilling. Geosteering is a sequential drilling decision process under uncertain stratum environment. However, the current geosteering drilling process relies heavily on manual work and has no use of temporal context. This paper aims to solve decision-making of geosteering in deep well (between 4500 and 6000 km) or ultradeep well (between 6000 and 9000 km). To this end, we make three contributions: (1) a wide-angle eye mechanism to obtain more geological information; (2) an asymmetric peephole convolutional long short-term memory (APC-LSTM) approach for geosteering drilling decision, whose input data were assembled with the wide-angle eye mechanism; and (3) use of the deep convolution generative adversarial networks (DCGAN) model to generate simulated logging data and conduct experiments in the simulation environment to verify our proposed method. APC-LSTM can capture the spatial-temporal correlation better between different strata for decision-making. Meanwhile, the APC-LSTM drilling decision model achieved better performance than other advanced methods in two drilling data sets. Tested in a simulative drilling environment, our proposed model achieves excellent application effect. Moreover, our method has been applied to the wells of oil field in practice.

show abstract

Intelligent Drilling Surveillance Through Real Time Diagnosis

Cited by 3 publications

References 11 publications

Geosteering Diagnosis: A New Approach to Monitor the Well Position Within a 3D Geological Model

Geosteering Diagnosis: A New Approach to Monitor the Well Position Within a 3D Geological Model

Geosteering Diagnosis: A New Approach to Monitor the Well Position within a 3D Geological Model

Deep Learning Approach of Drilling Decision for Subhorizontal Drain Geosteering Based on APC-LSTM Model

Contact Info

Product

Resources

About