Unified Well Parameter Optimization via Predictive Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current well planning processes often result in well plans that do not adequately meet specified goals due to the decoupling of geologic, engineering, and economic factors, leading to suboptimal selection of well parameters and disregarding useful correlations between them.
Innovation Solution
A method and system for determining well parameters that utilize a computing system to train a well performance predictor based on field data, generate candidate well parameter combinations, predict their performance, and optimize for maximum return on investment (ROI) by considering correlations between parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a divide-and-conquer approach is used to optimize specific geologic, engineering, and economic factors separately, then specialized teams can make decisions regarding specific subsets of well parameters, but the approach does not account for subsurface and engineering interactions and leads to well plans that do not adequately meet overall corporate goals
Solution Approach 1:
The patent merges previously separate geologic, engineering, and economic optimization processes into a single integrated system. The unified optimizer simultaneously considers all factors and their interactions, eliminating the need for separate divide-and-conquer approaches while maintaining comprehensive decision-making capability.
Solution Approach 2:
The patent creates a universal optimization framework that handles multiple objectives (geologic factors, engineering factors, economic factors) simultaneously. This multi-functional system can optimize various well parameters across different domains in a single process, rather than requiring separate specialized processes.
2Adaptability or versatility
If field development teams rely on information relating to field analogs, production data from older wells, and past engineering studies, then decisions can be made based on existing knowledge, but the information is subject to uncertainties and may not capture complex interactions between parameters
Solution Approach 1:
The patent implements feedback mechanisms where the unified optimizer uses actual well performance data to continuously refine and update the optimization model. This feedback loop improves prediction accuracy over time by incorporating real-world outcomes, reducing uncertainties associated with relying solely on historical analogs and studies.
Solution Approach 2:
The system performs preliminary comprehensive analysis by integrating all available information (field analogs, production data, engineering studies) into the unified optimization framework before making decisions. This preliminary integration allows the system to account for complex interactions that would be missed in traditional sequential approaches.
3Adaptability or versatility
If geologists, completions engineers, and operations engineers have different goals (largest in-place reserves, maximize hydrocarbon production, minimize costs), then each team can optimize their specific objectives, but the resulting well plan does not adequately meet the corporation's desired overall goals
Solution Approach 1:
The patent merges the separate optimization objectives of geologists, completions engineers, and operations engineers into a single unified optimization process. The system simultaneously considers reservoir characterization, hydrocarbon production maximization, and cost minimization, ensuring alignment with overall corporate goals rather than conflicting departmental objectives.
Solution Approach 2:
The unified optimization framework dynamically adjusts well parameters (location, depth, orientation, completion design, stimulation parameters) to find the optimal balance between competing objectives. By changing parameters systematically across all domains simultaneously, the system achieves corporate-level optimization rather than isolated departmental optimization.
Data Source
AI summary
The systems and methods described herein include training a well performance predictor based on field data corresponding to a hydrocarbon field in which a well is to be drilled; generating a number of candidate well parameter combinations for the well and predicting a performance of the well for each candidate well parameter combination using the trained well performance predictor; and determining an optimized well parameter combination for the well such that the predicted performance of the well is maximized.