AI-Enabled Real-Time UCS Prediction for Drilling Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drilling technologies lack the ability to predict unconfined compressive strength (UCS) of subsurface rocks in real-time during drilling operations, leading to suboptimal drilling parameters and inefficient bit performance.
Innovation Solution
A method and system utilizing artificial intelligence (AI) to compute real-time UCS from logging-while-drilling data, adjusting drilling parameters to optimize drilling performance by integrating AI models with physical models to determine optimal drilling parameters based on real-time UCS data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If well logs are used to obtain unconfined compressive strength profile, then UCS data is available, but the data is only available after drilling is completed
Solution Approach 1:
The system performs preliminary actions by collecting and processing drilling data in real-time during the drilling operation, enabling UCS prediction before drilling is completed. The AI model is trained beforehand using historical well log data, and then applied during drilling to predict UCS values as drilling progresses, eliminating the waiting period for post-drilling well log analysis.
Solution Approach 2:
The patent replaces the traditional mechanical/well-log-based UCS measurement system with an AI-based computational system. Instead of relying on physical well log measurements taken after drilling, the system uses machine learning models that process drilling parameters (weight on bit, rotational speed, rate of penetration) to predict UCS values in real-time, substituting computational intelligence for physical measurement delays.
2Productivity
If drilling parameters are adjusted based on post-drilling well logs, then UCS information is obtained, but drilling performance cannot be optimized in real-time
Solution Approach 1:
The system implements a feedback mechanism where real-time UCS predictions are continuously fed back to the drilling control system. The AI model processes current drilling parameters and UCS predictions, and this information feeds back to adjust drilling parameters dynamically during the drilling operation, enabling continuous optimization rather than post-drilling analysis.
Solution Approach 2:
The drilling system becomes self-service by automatically adjusting its own parameters based on real-time UCS predictions from the AI model. The system monitors drilling performance, predicts UCS values, and autonomously optimizes drilling parameters without requiring external intervention or waiting for post-drilling well log analysis, enabling real-time self-optimization.
3Extent of automation
If AI models are trained using existing wells, then real-time UCS prediction capability is developed, but the system complexity increases
Solution Approach 1:
The complex task of AI model training is performed as a preliminary action before the actual drilling operation. Historical well log data and UCS values from existing wells are used to train the AI model in advance. Once trained, the model is deployed for real-time predictions during drilling, separating the complex training phase from the operational phase and reducing real-time complexity.
Solution Approach 2:
The AI model serves multiple functions: it predicts UCS values, identifies rock type transitions, and provides inputs for drilling parameter optimization. By creating a universal model that handles multiple drilling-related predictions simultaneously, the system reduces overall complexity compared to having separate specialized models for each function.
Data Source
AI summary
A method for optimizing a drilling performance of a drilling operation, based process data. The method includes obtaining process data while conducting a drilling operation through a subsurface, where the drilling operation is controlled by a set of drilling parameters, and determining, with a computational model that receives the process data as input, a real-time unconfined compressive strength (UCS) of the subsurface. The method further includes determining, based on the real-time UCS of the subsurface, a drilling performance of the drilling operation, and, upon determining that the drilling performance is not optimum, adjusting one or more drilling parameters, within the set of drilling parameters, to optimize the drilling performance.