Well Plug Leak Prediction Using Pressure Pulse Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hydraulic fracturing plugs in wells often experience integrity issues due to pressure fluctuations and mechanical stress, leading to leaks that can cause damage to well components and reduce productivity, with conventional monitoring methods being costly and unavailable during operations.
Innovation Solution
A learning machine utilizing DAS/DTS data and water hammer pressure pulse analysis is trained to predict plug integrity, allowing for early detection and mitigation of leaks without relying on conventional methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional monitoring methods (logging and testing, tracers, DAS/DTS systems) are used to determine plug integrity, then measurement precision is improved, but device complexity and cost increase, and availability during fracking operations is reduced
Solution Approach 1:
The patent replaces complex mechanical and optical monitoring systems (DAS/DTS, tracers) with a purely computational approach using machine learning algorithms that process existing pressure pulse data. This substitution eliminates the need for additional physical monitoring equipment while maintaining detection accuracy.
Solution Approach 2:
The patent creates a virtual copy of the physical monitoring function through machine learning models trained on historical data. Instead of installing physical sensors throughout the wellbore, the system uses computational models that replicate monitoring capabilities using existing pressure data, thereby reducing device complexity.
2Measurement precision
If conventional monitoring methods are used to determine plug integrity, then measurement precision is improved, but availability during fracking operations deteriorates
Solution Approach 1:
The system uses the fracking operation's own pressure pulse data to monitor plug integrity, eliminating the need for separate monitoring systems. The machine learning model processes existing pressure measurements to detect plug failures, making the monitoring function self-contained and available throughout the entire fracking process without interrupting operations.
Solution Approach 2:
The patent enables continuous monitoring of plug integrity throughout the entire fracking operation by processing pressure pulse data in real-time. The machine learning model continuously analyzes pressure variations to detect plug failures, ensuring uninterrupted monitoring availability unlike conventional methods that require separate logging and testing operations.
3Device complexity
If plug integrity is not monitored, then device complexity is reduced, but reliability deteriorates due to leaks and breaks
Solution Approach 1:
The patent implements a feedback mechanism where the machine learning model continuously analyzes pressure pulse data and provides real-time insights into plug integrity. The system detects anomalies in pressure patterns that indicate plug failures, providing feedback that enables timely intervention to maintain reliability without requiring complex physical monitoring systems.
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
Prevents lost hydraulic treatment stages, avoids casing damage, and maintains production by enabling early detection and adaptive operational adjustments in response to plug failures.
Implementation Method 1
pressure pulse water hammer analysis data
Implementation Method 2
Distributed Acoustic Sensing (DAS)/Distributed Temperature Sensing (DTS) data
Data Source
AI summary
Some implementations include a method for predicting a plug leak in a wellbore during hydraulic fracturing operations. The method may include: generating a training data set including feature samples and prediction samples, wherein the feature samples include values derived from past pressure pulses in the well with or without other fracturing treatment data and the prediction samples include values derived from digital acoustic sensing (DAS) sensors located in the wellbore; training, with the training data set, a learning machine to predict the plug leak during the hydraulic fracturing operations based on pressure with or without other treatment data indicating one or more current pressure pulses.