Design of an Automated Drilling Prediction System - Strengthening While-Drilling Decision Making
- Armando Almeida Leon (Petrolink) | Edwin Hernandez (Petrolink) | Samuel Renee Perez Bardasz (Petrolink)
- Document ID
- Society of Petroleum Engineers
- SPE Digital Energy Conference, 5-7 March, The Woodlands, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2013. Society of Petroleum Engineers
- 1.4.1 BHA Design, 1.11 Drilling Fluids and Materials, 1.6.2 Technical Limit Drilling, 1.11.2 Drilling Fluid Selection and Formulation (Chemistry, Properties), 1.6.1 Drilling Operation Management, 1.6 Drilling Operations, 1.5 Drill Bits, 1.10.1 Drill string components and drilling tools (tubulars, jars, subs, stabilisers, reamers, etc), 1.2.2 Drilling Optimisation, 1.12.6 Drilling Data Management and Standards, 7.6.4 Data Mining, 1.13 Drilling Automation, 1.6.3 Drilling Optimisation, 1.12.2 Logging While Drilling
- system, automated, real-time, prediction, while-drilling
- 0 in the last 30 days
- 413 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Real-Time systems and monitoring centers continue gaining interest as decision-makers face tight time constraints to discover and develop hydrocarbon fields, while the increased complexity of wells being drilled is coupled with reduced engineering workforce capacity.
The promise of remote data visualization and analysis, problem mitigation and optimal utilization of highly-skilled team members is being realized. The predictive side, however, is still a challenge for the industry. Anticipating unplanned drilling events such as stuck pipe, lost circulation and kicks, represents a tremendous opportunity to return value from data, in the form of unplanned downtime reduction, cost saving and even a safer operating environment.
Data mining processes are fundamental to obtain the predictive benefits of real-time systems, and have been progressing from descriptive to predictive optimization methods. In design of these systems, descriptive and predictive methods are enhanced by real-time and historic data corresponding to six drilling operations aspects: bottom hole assembly design, mud properties, equivalent circulation density, lithology column description, rock conductivity and well-correlation events. Algorithms and human participation are taken into account to generate "accurate alerts?? rather than simple out-of-range alarms. Specific examples are provided in order to show how available technology, data mining and model development can increase drilling efficiency by enabling better while-drilling decision-making.
Advanced sensor technologies, improved data quality control, Wellsite Information Transfer Standard Markup Language (WITSML) data advantages, and virtual real-time drilling optimization concepts have been assimilated in the design and implementation of the prediction system. This paper aims to be useful as a reference to expand and improve decisions while drilling the well, by anticipating and identifying trouble zones using real-time predictive analyses.
|File Size||479 KB||Number of Pages||6|