Proxy Model for Fast Oil and Gas Production Model Updating
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Oil and gas field production management is hindered by the time-consuming process of physically evaluating and managing wells, leading to outdated data for real-time decision-making, and the complexity of physics-based models requires cumbersome history matching processes, making it impractical to account for multiple parameters effectively.
Innovation Solution
Implementing a method that uses physical and proxy simulators to establish a base model, define uncertain parameters, and automatically execute simulators to generate outputs, fitting these outputs with a proxy model to determine sensitivities and optimize parameter ranges for real-time production decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If physics-based simulators are used to model oil and gas field production, then the accuracy and reliability of production predictions are improved, but the time required to execute the models and make decisions increases significantly
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing the relationships between input parameters and output predictions in a proxy model before actual production decisions are needed. This pre-computed knowledge base allows rapid querying during decision-making without re-running complex physics-based simulators, thus resolving the contradiction between accuracy and speed.
Solution Approach 2:
The patent creates a simplified copy (proxy model) of the complex physics-based simulator that replicates its predictive capabilities but executes much faster. This copy captures the essential input-output relationships without the computational burden of the full physics model, enabling rapid decision-making while maintaining prediction accuracy.
2Reliability
If multiple parameters are accounted for in physics-based models to improve comprehensiveness, then the quality of production optimization is improved, but the complexity of the history matching process increases making it impractical
Solution Approach 1:
The system extracts only the critical input parameters and their relationships from the complex physics-based model, separating the essential predictive relationships from the unnecessary computational complexity. This extraction creates a streamlined proxy model that maintains optimization quality while dramatically reducing process complexity.
Solution Approach 2:
The patent transforms the complex multi-parameter physics-based model into a simplified parameter relationship model that focuses on the most influential parameters. By changing the representation from detailed physics equations to parameter-correlation relationships, the system maintains comprehensiveness while reducing complexity to practical levels.
3Ease of operation
If periodic measurements are used to manage production in large oil fields, then the operational complexity is reduced, but the data becomes outdated and useless for real-time management decisions
Solution Approach 1:
The system replaces the mechanical periodic measurement approach with an automated computational system that continuously processes available data through the proxy model. This substitution eliminates the need for frequent physical measurements while providing continuous real-time predictions, thus maintaining operational simplicity while eliminating data timeliness issues.
Data Source
AI summary
Methods, systems, and computer readable media are provided for fast updating of oil and gas field production optimization using physical and proxy simulators. A base model of a reservoir, well, or a pipeline network is established in one or more physical simulators. A decision management system is used to define uncertain parameters for matching with observed data. A proxy model is used to fit the uncertain parameters to outputs of the physical simulators, determine sensitivities of the uncertain parameters, and compute correlations between the uncertain parameters and output data from the physical simulators. Parameters for which the sensitivities are below a threshold are eliminated. The decision management system validates parameters which are output from the proxy model in the simulators. The validated parameters are used to make production decisions.