Geosteering Agent for Wellbore Localization Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current geosteering processes lack the necessary accuracy for autonomous wellbore construction, particularly in determining the optimal trajectory within permeable rock layers and fluid boundaries during the drilling of horizontal wells.
Innovation Solution
A method utilizing a trained stochastic clustering and pattern matching agent to compare real-time sensor measurements with a dynamic earth model, allowing for precise estimation and adjustment of the well path to achieve geological objectives, such as maximizing contact with more permeable formations and economic fluid targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional geosteering methods are used, then the process is simpler, but the accuracy of wellbore localization and trajectory control is insufficient for autonomous drilling
Solution Approach 1:
The geosteering system is segmented into multiple independent modules: stochastic clustering module, pattern matching module, earth model generation module, and trajectory optimization module. Each module handles a specific aspect of the localization and control process, improving measurement precision while managing system complexity through functional decomposition
Solution Approach 2:
A trained stochastic clustering and pattern matching agent serves as an intermediary between raw sensor measurements and wellbore localization results. This agent processes and interprets sensor data, bridging the gap between measurement acquisition and accurate geological positioning, thereby enhancing localization accuracy without requiring direct complex interactions between all system components
2Manufacturing precision
If real-time sensor measurements are continuously processed, then the well path accuracy is improved, but the computational time and processing load increase
Solution Approach 1:
The earth model is generated and the stochastic clustering agent is trained beforehand using historical well data and geological information. This preliminary preparation allows the system to quickly process real-time sensor measurements during drilling without performing full model training or complex computations from scratch, thus maintaining high trajectory precision while reducing real-time processing time
Solution Approach 2:
The system implements continuous feedback loops where real-time sensor measurements are compared against the pre-generated earth model and previous trajectory estimates. The stochastic clustering agent rapidly processes this feedback information to adjust the well path trajectory, achieving high precision through iterative refinement without requiring excessive computational time at each step
Data Source
AI summary
A method of geosteering in a wellbore construction process uses an earth model that defines boundaries between formation layers and petrophysical properties of the formation layers in a subterranean formation. Sensor measurements related to the wellbore construction process are inputted to the earth model. An estimate is obtained for a relative geometrical and geological placement of the well path with respect to a geological objective using a trained stochastic clustering and pattern matching agent. An output action based on the sensor measurement for influencing a future profile of the well path with respect to the estimate.