Well Production Control Using Data-Driven Multiphase Flow Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The uncontrolled operation of hydrocarbon wells leads to inefficiencies and potential safety hazards, necessitating an intelligent production control system for optimized hydrocarbon fluid production.
Innovation Solution
A data-driven model using a dynamic mode decomposition (DMD) algorithm and data assimilation techniques to predict and control hydrocarbon production by analyzing wellhead pressure, temperature, and multiphase flow rates, generating optimal control settings for choke valves.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional CPU intensive simulations based on finite difference models are used for reservoir modeling and production forecasting, then model accuracy is improved, but computation time and processing speed deteriorate
Solution Approach 1:
The patent creates a simplified copy or surrogate model that replicates the behavior of the complex finite difference reservoir model. This surrogate model uses reduced-order modeling techniques to capture essential production dynamics without requiring full computational simulation, thereby providing fast predictions that are sufficiently accurate for real-time control applications.
Solution Approach 2:
The patent replaces the traditional mechanical/computational finite difference simulation system with a data-driven or reduced-order modeling approach. This substitution uses statistical or machine learning models trained on simulation data to predict production behavior, eliminating the need for repeated CPU-intensive numerical simulations while maintaining acceptable accuracy for control purposes.
2Ease of operation
If uncontrolled operation of wells is performed, then operational simplicity is improved, but production efficiency and safety deteriorate
Solution Approach 1:
The control system enables the well production process to self-regulate by automatically adjusting control parameters based on real-time sensor data and predictions from the surrogate model. The system monitors production conditions, predicts future behavior, and autonomously modifies operational parameters to maintain optimal production levels without requiring continuous manual intervention.
Solution Approach 2:
The patent implements a closed-loop control system where sensor measurements of actual production parameters are continuously fed back to the surrogate model and controller. This feedback mechanism allows the system to compare predicted versus actual production behavior and adjust control settings dynamically to optimize hydrocarbon recovery while ensuring safe operation.
3Productivity
If complex control systems are implemented for well production optimization, then production efficiency is improved, but system complexity and implementation difficulty worsen
Solution Approach 1:
The patent extracts only the essential dynamics and control relationships from the full reservoir simulation model to create a simplified surrogate model. By taking out and retaining only the critical production behavior characteristics, the system achieves adequate predictive capability with much reduced computational and implementation complexity compared to using complete reservoir models for real-time control.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system (134) for controlling and optimizing hydrocarbon production may include sensors (136, 138, 216) that capture sensor data pertaining to wellhead pressure values in a well. The system may also include a multiphase flow meter that captures production data pertaining to multiphase production flow rates of the well (120). The system may include an access module (220) to access an estimated parameter value associated with a second time and a parameter that pertains to production. The estimated parameter value is predicted by a data-driven model (208) for describing production fluid dynamics of the well (120), based on the sensor data (204) and the production data (206) obtained at a first time. The system includes a processor (222) to update the data-driven model (208) using a data assimilation algorithm and the production data (206) received at the second time. The processor (222) generates, using the updated data-driven model, an optimal control setting of a control tool (212) for causing an adjustment to a production system.