Interwell Connectivity Model for EOR Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enhanced oil recovery (EOR) techniques in unconventional hydrocarbon reservoirs face challenges due to complex geomechanical processes and pressure-dependent reservoir properties, making it difficult to predict fluid migration and optimize hydrocarbon extraction.
Innovation Solution
An interwell connectivity model is developed to correlate gas injection inputs with hydrocarbon production outputs, allowing for controlled gas injection to optimize reservoir pressure and production rates by determining fluid connectivity between wells and using this data to control injection strategies such as huff and puff cycles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional reservoir simulation methods are used to predict fluid migration and optimize hydrocarbon extraction, then measurement precision and reliability may be maintained, but computational time and complexity increase significantly
Solution Approach 1:
The patent segments the reservoir into discrete grid cells and divides the simulation into sequential time steps, allowing parallel computation of individual cells while maintaining overall prediction accuracy. This segmentation enables the complex reservoir simulation to be broken into manageable computational units that can be processed more efficiently.
Solution Approach 2:
The patent replaces traditional mechanical reservoir simulation methods with a machine learning-based predictive model. The system trains neural networks on historical reservoir data to predict fluid migration patterns, pressure changes, and hydrocarbon extraction rates, substituting computationally intensive numerical simulations with faster AI-based predictions that maintain acceptable accuracy.
2Measurement precision
If complex geomechanical processes and pressure-dependent reservoir properties are fully modeled, then measurement precision improves, but device complexity and computational requirements increase
Solution Approach 1:
The patent transforms complex geomechanical parameters and pressure-dependent properties into simplified input features for machine learning models. By changing the representation of these parameters into standardized numerical inputs that capture essential relationships, the system maintains prediction accuracy while reducing model complexity and computational burden.
Solution Approach 2:
The patent creates simplified surrogate models that copy the essential behavior of complex reservoir systems. These surrogate models are trained to replicate the output of detailed geomechanical simulations but require far fewer computational resources, allowing accurate predictions without fully implementing the complete complex physics models.
3Productivity
If gas injection rates are increased to improve hydrocarbon recovery, then productivity increases, but energy consumption and operational costs increase
Solution Approach 1:
The patent implements a feedback control system that continuously monitors reservoir pressure, fluid saturation, and production rates, then adjusts gas injection rates accordingly. The machine learning model predicts optimal injection rates based on current reservoir state and desired production targets, reducing energy consumption by avoiding excessive injection while maintaining high productivity through precise control.
Solution Approach 2:
The patent transitions from static gas injection rates to dynamic, time-varying injection schedules. The system continuously adapts injection rates based on changing reservoir conditions, pressure buildup, and interwell connectivity changes, allowing optimal productivity at each stage while minimizing total energy consumption throughout the EOR process.
Data Source
AI summary
A methodology using an interwell connectivity model for hydrocarbon management is disclosed. The interwell connectivity model may include interwell connectivity metrics indicative of fluid interconnectivity amongst pairs of wells and may be used as predictive or prescriptive for enhanced oil recovery (EOR). As predictive, the interwell connectivity model may be used to determine an effect of gas injection into the reservoir on one or more aspects of EOR, such as reservoir pressure or production rates. As prescriptive, the interwell connectivity model may be used to improve or optimize various stages of EOR, such as during drilling or construction of the extraction site, during primary depletion, or during one or more huff-and-puff cycles.