SAGD Control via Causal Emulsion Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Steam-assisted gravity drainage (SAGD) oil well systems face challenges in optimizing emulsion production due to uncertainties in physics-based predictive models and limitations of statistical approaches, which lead to inefficient steam distribution and increased costs.
Innovation Solution
A causal model is developed using nonlinear autoregressive exogenous neural networks to forecast emulsion production and adjust controls based on historical time series data from sensors, incorporating physics-inspired inputs to optimize control parameters and account for individual well pair characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physics-based predictive models are used to forecast emulsion production, then prediction capability is improved, but model uncertainty increases leading to inefficient steam distribution
Solution Approach 1:
The patent combines physics-based predictive models with statistical approaches and real-time sensor data to create a hybrid forecasting system. This integration merges the theoretical strengths of physics models with the empirical accuracy of statistical methods, reducing overall model uncertainty while improving prediction reliability for emulsion production and steam distribution optimization
Solution Approach 2:
The patent introduces an intermediary data fusion layer that processes outputs from multiple modeling approaches (physics-based models, statistical models, and sensor data) before generating final forecasts. This intermediary layer reconciles uncertainties from different sources and produces more reliable predictions for control optimization
2Productivity
If steam injection rate is increased to improve bitumen recovery, then emulsion production increases, but energy consumption and costs increase
Solution Approach 1:
The patent implements a feedback control system that continuously monitors emulsion production rates, steam injection rates, and well performance metrics. The system uses this real-time feedback to dynamically adjust steam injection rates, increasing steam when production responds positively and reducing steam when marginal returns are achieved, thereby optimizing the balance between productivity and energy consumption
Solution Approach 2:
The patent employs dynamic control strategies that adapt steam injection rates based on real-time well response and changing reservoir conditions. Rather than using fixed injection rates, the system continuously adjusts operational parameters to maintain optimal productivity-to-energy-ratio throughout the production lifecycle
3Ease of operation
If statistical approaches are used for control optimization, then implementation simplicity is improved, but prediction accuracy deteriorates
Solution Approach 1:
The patent merges statistical approaches with physics-based models and machine learning algorithms to create a hybrid control optimization system. This combination maintains the implementation simplicity of statistical methods while incorporating the predictive accuracy of physics-based models, achieving both ease of operation and high prediction accuracy
Data Source
AI summary
A method for increasing efficiency in emulsion production for a steam-assisted gravity drainage (SAGD) oil well system includes generating a causal model of the SAGD oil well system and training the causal model of the SAGD oil well system utilizing historical time series data relating to one or more SAGD oil wells at one or more SAGD production sites of the SAGD oil well system. The historical time series data is obtained from a plurality of sensors in the SAGD oil well system. The method also includes utilizing the causal model to determine a forecast emulsion production and a forecast set of control parameters associated with one or more of the SAGD production sites of the SAGD oil well system. The method further includes adjusting a set of controls of the SAGD oil well system based on the forecast emulsion production and the forecast set of control parameters and subject to one or more constraints associated with the SAGD oil well system.