Machine Learning Model for Pump-Lifted Well Surveillance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for managing pump-lifted wells in hydrocarbon fields are limited by their reliance on physics-based models that do not incorporate comprehensive data beyond pump card information, leading to inadequate surveillance and optimization capabilities.
Innovation Solution
A computer-implemented method using machine learning to generate a machine-learned model that predicts aspects of well and rod pump performance by integrating pump card data with well, reservoir, flowline, and user input data, enabling real-time status monitoring and recommended actions for hydrocarbon management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If physics-based models are used for managing pump-lifted wells, then the system is simpler and easier to implement, but the surveillance and optimization capabilities are inadequate
Solution Approach 1:
The patent combines multiple data sources (pump card data, well data, reservoir data, flowline data) with machine learning algorithms to create a hybrid system that integrates the simplicity of physics-based models with the predictive power of data-driven approaches, thereby enhancing surveillance and optimization capabilities while managing complexity
Solution Approach 2:
The patent introduces machine learning models as intermediaries between raw well data and management decisions, enabling the system to process and interpret complex multi-source data without requiring complete redesign of the underlying physics-based management framework
2Measurement precision
If only pump card data is used for well management, then the data collection system is simpler, but the prediction accuracy and actionable insights are limited
Solution Approach 1:
The patent creates a multi-functional data integration platform that processes diverse data types (pump card, well, reservoir, flowline data) through a unified machine learning framework, enabling the system to derive multiple insights from a single integrated model and avoid the need for separate analysis systems for each data type
Data Source
AI summary
A methodology for integrated pump and well data for managing pump-lifted wells in hydrocarbon fields is provided. Rod pumps are widely applied to various types of wells to provide uplift and may play a dominant role in the flow of hydrocarbon from reservoir to surface. Assess the state of each well and its components (including the associated rod pump) is important for optimal well and reservoir management for fields with artificially lifted wells. As such, a methodology is disclosed that performs machine learning in order to generate a machine-learned model using pump card data and at least one of well data, reservoir data, flowline data, user input data, or data generated from analysis of one or more of the well data, the reservoir data, the flowline data, or the user input data.