Offset Well Risk Modeling for Well-Specific Drilling Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current offset well analysis in the oil and gas industry relies heavily on manual, qualitative risk assessment by human engineers, leading to inaccuracies due to human subjectivity and variability, and fails to account for differences between offset and new wells, resulting in high uncertainty.
Innovation Solution
A computer-implemented method using automated inference systems and machine learning models to analyze offset well data, predict drilling risks, and adjust drilling parameters in real-time, incorporating a Bayesian Belief Network for probabilistic risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual qualitative risk assessment by human engineers is used, then the process is simple and easy to operate, but the accuracy and reliability of risk prediction deteriorates due to human subjectivity and variability
Solution Approach 1:
The patent replaces the manual mechanical process of human engineers qualitatively assessing risk with an automated computer-implemented system that performs quantitative analysis. The system uses algorithms to process offset well data, drilling parameters, and geological information to generate objective risk predictions, eliminating human subjectivity while maintaining operational simplicity through automated workflows.
Solution Approach 2:
The system enables self-service by automatically gathering offset well information, processing drilling parameters, and generating risk assessments without requiring human engineers to manually collect and analyze data. The automated inference system performs the entire risk assessment process independently, improving both accuracy and efficiency.
2Use of energy by moving object
If manual qualitative forecasting based on human intuition is used, then the process requires minimal computational resources, but the reliability of risk prediction deteriorates due to human subjectivity and lack of calibration for well-specific conditions
Solution Approach 1:
The patent transforms the risk assessment approach by changing from qualitative parameters (human intuition) to quantitative parameters (measurable data). The system processes specific drilling parameters, geological properties, and operational data to generate calibrated risk predictions that are objectively tailored to each well's specific conditions, significantly improving reliability.
Solution Approach 2:
The system performs preliminary analysis by pre-processing offset well data and establishing baseline risk models before actual drilling operations. This preliminary action allows the system to quickly assess new wells by comparing them against pre-analyzed historical data, maintaining low computational overhead while improving prediction reliability through pre-calibrated models.
3Device complexity
If experienced risks are not calibrated for differences between offset well and new well, then the analysis process remains simple, but the accuracy of risk prediction deteriorates because risk events occur at different depth and severity
Solution Approach 1:
The patent applies local quality by tailoring the risk assessment to specific local conditions of each well. The system analyzes offset well data in the context of the new well's specific geological formation, drilling parameters, and operational characteristics. This localized analysis ensures that risk predictions are accurately calibrated for each well's unique conditions rather than applying generic assessments.
Solution Approach 2:
The system dynamically adjusts risk assessment parameters based on the specific characteristics of each well being analyzed. By changing parameters such as drilling depth, formation properties, and operational conditions to match the new well's profile, the system maintains simple analytical processes while achieving high prediction accuracy through parameter customization.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, computing system, and non-transitory computer-readable medium, of which the method includes receiving offset well data collected while drilling one or more offset wells, generating a machine learning model configured to predict drilling risks from drilling measurements or inferences, based on the offset well data, receiving drilling parameters for a new well, determining that the drilling parameters are within an engineering design window, generating a drilling risk profile for the new well using the machine learning model, and adjusting one or more of the drilling parameters for the new well, after determining the drilling parameters are within the engineering design window, and after determining the drilling risk profile, based on the drilling risk profile.