Electric Submersible Pump Fault Detection via Manifold Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for monitoring electric submersible pumps (ESPs) rely on two-dimensional performance curves, which fail to detect subtle performance deviations, leading to unnoticed errors and delayed corrective actions, resulting in increased operational costs due to premature failures.
Innovation Solution
A method and system that utilize sensors to generate a reduced set of components from observable parameters, applying principal component analysis to define a manifold of normal operation in a reduced component space, enabling early detection of deviations from normal operation and predicting ESP performance more accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional two-dimensional performance curves are used to monitor ESP performance, then the monitoring method is simple and easy to understand, but subtle performance deviations cannot be detected and measurement precision is insufficient
Solution Approach 1:
The patent transforms the conventional two-dimensional performance curves into a multi-dimensional monitoring framework by incorporating multiple observable parameters (vibration, temperature, pressure, flow rate, power consumption) simultaneously. This dimensional expansion enables detection of subtle performance deviations that cannot be captured by traditional single-parameter or two-dimensional curves, directly resolving the contradiction between measurement precision and system complexity.
Solution Approach 2:
The patent segments the complex monitoring task into distinct components: data acquisition from multiple sensors, dimensionality reduction processing, manifold construction for normal operation patterns, and deviation detection. This segmentation allows the system to handle complexity in a structured manner while achieving high measurement precision through coordinated processing of multiple parameters.
2Reliability
If multiple observable parameters are monitored simultaneously, then performance prediction accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent extracts the essential variability patterns from multiple observable parameters by constructing a manifold representation of normal operation. This extraction process identifies the core dimensions of normal ESP behavior, separating signal from noise and enabling accurate prediction without processing all raw parameter data in full complexity, thus resolving the contradiction between reliability and computational complexity.
Solution Approach 2:
The patent transforms multiple observable parameters into a reduced set of principal components that capture the essential variation in ESP performance. This parameter transformation maintains the predictive power of multiple parameters while reducing computational complexity by working with a smaller set of derived variables that encapsulate the essential performance characteristics.
3Device complexity
If dimensionality reduction is applied to observable parameters, then computational complexity is reduced, but information loss may occur
Solution Approach 1:
The patent incorporates a feedback mechanism where the manifold of normal operation is continuously constructed from historical data and used to evaluate new observations. This feedback loop ensures that the dimensionality reduction process preserves information critical for detecting deviations, as the manifold is adapted to capture the essential patterns in the data, preventing information loss while reducing computational complexity.
Solution Approach 2:
The patent performs preliminary dimensionality reduction by constructing the manifold of normal operation from training data before actual performance monitoring begins. This preliminary action establishes a reference framework that captures the essential variability of normal ESP operation, allowing subsequent monitoring to focus on detecting deviations from this pre-established pattern without losing critical information during the reduction process.
Data Source
AI summary
A method for monitoring performance of an electric submersible pump. The method includes receiving data indicating a plurality of observable parameters from one or more sensors, generating a reduced set of components representative of at least some of the observable parameters and the reduced set having a dimensionality less than the plurality of observable parameters, identifying one or more components of the reduced set that captures a total variance of the plurality of observable parameters above a predetermined threshold, constructing at least one manifold of normal operation of the electric submersible pump in a reduced component space, receiving additional data from the sensors, transforming the additional data into the identified components establishing an electric submersible pump performance, and detecting whether a deviation of the electric submersible pump performance from a normal mode of operation of the electric submersible pump exceeds a predetermined threshold.