Physics-Guided Virtual Flowmeters for Connected Well Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring and optimizing the operation of connected oil and gas wells are inaccurate due to the high cost of multiphase mass flowmeters and the unsuitability of virtual flowmeters for connected configurations, leading to unknown flow rates and potential revenue losses, especially in mature fields.
Innovation Solution
A system comprising hardware processors and memory that receives data from multiple sources, preprocesses it, and uses physics-based soft sensors and models to forecast flow rates, pressure, and temperature distributions in real-time, while computing asset health and optimizing production settings through physics-guided well surveillance models and simulators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiphase mass flowmeters are installed at each wellhead to measure flow rates accurately, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates virtual copies of physical flowmeters by developing data-driven virtual flowmeters that replicate the measurement function using machine learning models. These virtual models process readily available well data (pressure, temperature, production rates) to estimate flow rates without requiring expensive physical multiphase flowmeters at each wellhead, thus achieving measurement capability while avoiding the complexity and cost of extensive physical instrumentation
Solution Approach 2:
The patent introduces an intermediary computational layer that mediates between available well data and flow rate estimation. Instead of directly measuring flow rates with complex physical instruments, the system uses machine learning models as intermediaries to infer flow rates from simpler, more readily available measurements, bridging the gap between available data and desired information
2Device complexity
If virtual flowmeters are used for single wells, then device complexity is reduced, but they are not suitable for connected well configurations leading to measurement inaccuracies
Solution Approach 1:
The patent merges multiple virtual flowmeter models into a unified system that handles connected well configurations. By combining data from multiple wells and using ensemble learning approaches, the system achieves accurate flow rate estimation for connected wells where individual virtual flowmeters would fail, maintaining low device complexity while improving measurement precision for the specific application
3Device complexity
If flow rates from individual wells are not monitored accurately, then device complexity is reduced, but production assessment accuracy and profitability decrease
Solution Approach 1:
The patent enables the monitoring system to serve itself by automatically collecting data from existing well infrastructure, processing it through virtual flowmeters, and generating flow rate estimates without requiring additional complex monitoring hardware. The system uses readily available operational data to self-generate the information needed for production assessment, eliminating the need for extensive additional instrumentation while preventing information loss
Data Source
AI summary
It is important to know the flow rates of oil and gas from individual wells in connected oil and gas wells. The existing methods for multiphase flow measurement are prohibitively expensive and used infrequently. The system is configured to ingest real-time and non-real-time data from a plurality of well data sources. Utilizing this data, a plurality of physics-guided data-driven well surveillance models run in real-time for forecasting a plurality of parameters including the flow rates of oil, gas and brine from individual wells, computing the health of well assets and performing fault detection and localization in well assets. The system is also configured to automatically compose a well performance optimization problem based on the current performance of the wells and health of well assets and solve the problem to identify optimal process settings for improving the operation of connected oil and gas wells.