Well Placement Optimization via Inexpensive Constraint Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Well placement planning in the oil and gas industry is a time-consuming and inefficient process due to its manual nature and the difficulty in objectively exploring the complete solution space, leading to high computational costs and inefficiencies.
Innovation Solution
A constrained optimization framework is employed to generate well placement plans based on a reservoir model, where inexpensive constraints are evaluated first to filter out infeasible plans, followed by an objective function calculation using a reservoir simulator for feasible plans, thereby reducing unnecessary computational expenses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual well placement planning is performed with repeated simulations, then well placement plans can be generated, but the process becomes very time-consuming and computationally expensive
Solution Approach 1:
The patent applies preliminary action by performing feasibility evaluations using inexpensive constraints before executing computationally expensive reservoir simulations. The optimization engine pre-assesses candidate well placement plans against geometric, operational, and geological constraints to filter out infeasible options before they undergo full simulation, thereby reducing overall computational time and improving productivity
Solution Approach 2:
The patent segments the evaluation process into distinct stages: first evaluating inexpensive constraints (geometric, operational, geological), then proceeding to expensive reservoir simulations only for feasible candidates. This segmentation allows the system to handle the optimization problem in manageable parts, reducing the total computational burden and time required
2Measurement precision
If complete solution space is explored manually, then optimal well placement can be found, but the process becomes inefficient and difficult to manage
Solution Approach 1:
The patent implements feedback through its optimization engine that uses results from feasibility evaluations and reservoir simulations to guide subsequent search directions. The engine learns from previous evaluations, adjusting its exploration strategy to focus on promising regions of the solution space while avoiding previously identified infeasible areas, thereby maintaining optimization accuracy while improving efficiency
Solution Approach 2:
The optimization engine acts as an intermediary between the solution space and the evaluation processes. It systematically manages the exploration of candidate well placement plans, coordinating between inexpensive constraint evaluations and expensive simulations, and intelligently navigating the solution space to find optimal solutions without requiring exhaustive manual exploration
3Reliability
If reservoir simulator is accessed for every candidate plan, then accurate evaluation is achieved, but computational costs increase significantly
Solution Approach 1:
The patent applies preliminary action by performing feasibility evaluations using inexpensive constraints before executing computationally expensive reservoir simulations. The optimization engine pre-assesses candidate well placement plans against geometric, operational, and geological constraints to filter out infeasible options before they undergo full simulation, thereby reducing overall computational time and improving productivity
Solution Approach 2:
The patent applies local quality by applying different evaluation rigor to different candidate plans based on their feasibility characteristics. Feasible candidates receive full rigorous evaluation with reservoir simulations, while infeasible candidates are quickly rejected using simpler constraint checks, optimizing the allocation of computational resources according to local candidate quality
Data Source
Figure 1
Figure 2A~2D
Figure 3
AI summary
A method, apparatus, and program product utilize a constrained optimization framework to generate a well placement plan based on a reservoir model. Candidate well placement plans are generated from control vectors proposed by an optimization engine to optimize based upon an objective function that generally involves an access to a reservoir simulator. Inexpensive constraints that are not based on computation of the objective function are evaluated prior to accessing the reservoir simulator to avoid unnecessary accesses to the reservoir simulator for candidate well placement plans determined to be infeasible in view of the inexpensive constraints. For candidate well placement plans that are determined to be feasible based upon the inexpensive constraints, the objective function may be calculated and additional expensive constraints may thereafter be evaluated to further determine the feasibility of candidate well placement plans.