Annulus Pressure Prediction for Hydrocarbon Wells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Thermal expansion in hydrocarbon wells leads to excessive tubing casing annulus pressure, posing a key well integrity challenge during drilling and extraction, as existing monitoring systems fail to predict and manage annuli pressure anomalies effectively.
Innovation Solution
A data processing system that analyzes historical annuli survey data to predict pressure decline or build-up rates using machine learning models, combining effects of thermal and volumetric changes, and calculates failure factors to anticipate and mitigate potential well integrity issues through remedial actions like TCA refills or pressure bleed-offs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If thermal expansion of TCA fluids is allowed to occur naturally, then the wellbore can maintain its structural integrity during temperature changes, but excessive TCA pressure builds up which compromises well integrity
Solution Approach 1:
The system performs preliminary actions by continuously monitoring TCA pressure and predicting future pressure trends using machine learning models. It proactively identifies when pressure build-up is likely to occur and schedules remedial actions (such as pressure bleed-down or TCA replacement) before the pressure reaches critical levels that would compromise well integrity, thus preventing the harmful effect while maintaining the beneficial thermal expansion process.
Solution Approach 2:
The system implements feedback mechanisms by continuously measuring actual TCA pressure, comparing it against predicted values from machine learning models, and adjusting operational parameters accordingly. When pressure deviations from predicted trends are detected, the system triggers alerts and automated responses to control pressure levels, creating a closed-loop control system that maintains well integrity while allowing natural thermal expansion.
2Loss of information
If existing monitoring systems are used to track annuli pressure, then basic pressure data can be collected, but the systems fail to predict and manage annuli pressure anomalies effectively
Solution Approach 1:
The system replaces basic mechanical pressure monitoring with an advanced integrated system that combines machine learning prediction models, real-time data analytics, and automated control mechanisms. The machine learning models process historical and real-time data to predict pressure anomalies before they occur, providing proactive warning and control capabilities that go far beyond traditional reactive monitoring systems.
Solution Approach 2:
The system changes the parameter of monitoring from simple pressure measurement to multi-parameter analysis including temperature, pressure, time, and historical trends. By transforming raw pressure data into predicted pressure trends using machine learning, the system enables proactive identification of anomaly cycles and facilitates timely remedial actions, significantly improving well integrity management reliability.
3Reliability
If remedial actions are taken frequently to manage TCA pressure, then well integrity can be maintained, but operational complexity and maintenance costs increase
Solution Approach 1:
The system performs preliminary analysis by continuously predicting future TCA pressure trends using machine learning models trained on historical data. By identifying pressure anomaly cycles before they reach critical levels, the system enables proactive scheduling of remedial actions (such as pressure bleed-down or TCA replacement) at optimal times, preventing well integrity issues while avoiding unnecessary frequent interventions and reducing operational complexity.
Solution Approach 2:
The system implements self-service capabilities through automated monitoring, prediction, and control. The machine learning models automatically analyze pressure trends and trigger remedial actions without requiring constant human intervention. This automation reduces operational complexity by handling routine monitoring and control tasks autonomously, while still maintaining high well integrity through consistent, data-driven management.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables early detection and prevention of well integrity issues, reducing maintenance costs by predicting anomalies and allowing for timely remedial actions, thereby improving well control and maintenance efficiency across multiple wells.
Implementation Method 1
Thermal expansion of TCA (tubing casing annulus) fluids caused by the radial heat transfer from the upward flow of wellbore fluids to the TCA can result in excessive TCA pressure
Implementation Method 2
The data processing system is configured to combine effects of thermal and volumetric changes of the annular fluid and casing for making this quantification
Implementation Method 3
The data processing system assumes a linear fluid heat-up behavior and elastic plasticity of the tubing without thermal transfer to the adjacent annulus
Data Source
AI summary
A method and system for predicting a well pressure for a hydrocarbon well are configured to perform actions including receiving well attributes data describing a physical configuration of a well; generating, based on values of the well attributes data, a relationship for predicting an annulus pressure by equating a change in volume of fluid in the well to a change in volume of a tubing casing annulus; updating the relationship based on fluid properties of the fluid; and predicting a TCA pressure for the well based on the updated relationship.