Drilling Mode Pattern Recognition for Well Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for improving drilling speed and efficiency in new wells rely on limited drilling indicators and fail to account for non-linear relationships between these indicators across different formations and depths, lacking a systematic approach to utilize historic drilling data effectively.
Innovation Solution
A method using a pattern recognition model to extract drilling modes from historic data, selecting optimal drilling parameter settings based on efficient drilling variables like MSE and ROP, and applying these settings to create a drilling plan for new wells, which includes cleaning, formatting, and applying the data using a computer-readable medium to execute the program code.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional drilling methods relying on limited indicators (MSE and ROP only) are used, then the drilling process is simple to operate, but drilling efficiency cannot be sufficiently improved and the method fails to account for non-linear relationships across different formations and depths
Solution Approach 1:
The patent segments the continuous drilling data into discrete drilling modes using cluster analysis. Multiple drilling indicators (MSE, ROP, WOB, RPM, torque, etc.) are divided into distinct operational modes that represent different drilling conditions and formation types, allowing for more precise analysis while maintaining manageable complexity
Solution Approach 2:
The patent transitions from analyzing individual drilling indicators in isolation to a multi-dimensional analysis framework. By incorporating numerous drilling indicators simultaneously and using cluster analysis to create drilling modes, the system captures non-linear relationships across multiple dimensions of drilling parameters, enabling better efficiency improvement
2Speed
If drilling parameter settings are optimized based on comprehensive historic data analysis, then drilling speed and efficiency improve significantly, but the complexity of data processing and pattern recognition increases
Solution Approach 1:
The patent performs preliminary clustering analysis on historic drilling data to identify drilling modes before actual drilling operations. By pre-processing the data and establishing reference drilling modes in advance, the system reduces real-time complexity while maintaining the ability to optimize drilling parameters based on comprehensive patterns learned from historical data
Solution Approach 2:
The patent creates reference drilling modes that serve as templates or copies of optimal drilling patterns from historic data. These reference modes can be applied to new drilling scenarios without requiring complex real-time analysis, enabling speed improvement while managing computational complexity through pattern replication
3Productivity
If multiple drilling indicators are analyzed simultaneously to capture non-linear relationships, then drilling efficiency improves, but the difficulty of detecting and measuring relationships between indicators increases
Solution Approach 1:
The patent introduces cluster analysis as an intermediary method that processes multiple drilling indicators simultaneously. This intermediary technique transforms complex multi-indicator relationships into discrete drilling modes, making it easier to detect and measure relationships between indicators while still capturing non-linear patterns across multiple parameters
Data Source
AI summary
A method for drilling a new oil or gas well in a selected geographical location includes extracting drilling modes from historic drilling data obtained from a group of drilled wells in the selected geographical location using a pattern recognition model. Each drilling mode represents a distinct pattern that quantifies at least two drilling variables at a specified drilling depth. The method also includes selecting a sequence of drilling modes at positions along a reference well as reference drilling modes that represent more efficient values for a selection of one or more of the at least two drilling variables compared to other extracted drilling modes; associating drilling parameter settings with the reference drilling modes; and drilling the new oil or gas well applying at least some of the drilling parameter settings.