Real-time Wellbore Drilling Data Quality Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for improving wellbore data accuracy for drilling tool control are inefficient, relying heavily on manual review to eliminate statistical outliers and missing values, which slows down the drilling process and requires extensive expertise.
Innovation Solution
A system utilizing machine learning models, specifically feature-extraction models and autoencoders, to dynamically identify and correct outliers and missing values in real-time, integrated with a message queuing telemetry transport (MQTT) protocol for immediate data processing and parameter control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual review methods are used to eliminate statistical outliers and missing values, then data accuracy can be improved, but the drilling process slows down and requires extensive expertise
Solution Approach 1:
The patent replaces manual review processes with automated machine learning models. Specifically, autoencoders and neural networks are trained to automatically identify and correct statistical outliers and missing values in wellbore data, eliminating the need for manual expert review while maintaining or improving data accuracy and significantly reducing processing time
Solution Approach 2:
The system implements self-service through self-supervised learning where the machine learning models automatically learn from the data itself without requiring external expert intervention. The autoencoders are trained to reconstruct clean data patterns, enabling the system to autonomously identify and correct anomalies in real-time drilling operations
2Measurement precision
If manual review methods are used to eliminate statistical outliers and missing values, then data accuracy can be improved, but extensive expertise is required
Solution Approach 1:
The patent substitutes manual expert analysis with automated machine learning systems. The complex pattern recognition tasks previously requiring expert knowledge are transferred to neural networks and autoencoders that automatically learn data patterns and anomalies, eliminating the need for extensive human expertise while maintaining high data accuracy
Solution Approach 2:
The system changes the operational parameters from manual expert judgment to automated algorithmic processing. By transforming the data processing approach from human-centric to machine-centric, the system eliminates expertise requirements while maintaining or improving measurement precision through consistent automated application of learning models
3Loss of time
If traditional data processing methods are used, then system simplicity is maintained, but response time increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models offline before real-time operations. The autoencoders and neural networks are trained in advance on historical wellbore data, enabling them to rapidly process and correct data in real-time during drilling operations without adding computational complexity to the time-critical processing path
Solution Approach 2:
The system replaces traditional sequential data processing methods with parallel machine learning inference. The automated models process multiple data streams simultaneously and correct anomalies in real-time, dramatically reducing response time despite the increased sophistication of the processing system
Data Source
AI summary
Aspects and features of a system for real-time drilling using automated data quality control can include a computing device, a drilling tool, sensors, and a message bus. The message bus can receive current data from a wellbore. The computing device can generate and use a feature-extraction model to provide revised data values that include those for missing data, statistical outliers, or both. The model can be used to produce controllable drilling parameters using highly accurate data to provide optimal control of the drilling tool. The real-time message bus can be used to apply the controllable drilling parameters to the drilling tool.