Surrogate Model for Optimizing Hydraulic Fracturing Schedules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current hydraulic fracturing methods for extracting hydrocarbons from subterranean reservoirs often result in poor resource production due to inadequate well design, fracture design, and production schedules, leading to reduced net worth and present value of well pad leases, and increased well density can cause suboptimal resource output.
Innovation Solution
A system and method that utilize a schedule generator to iteratively select and refine trial schedules for drilling, fracturing, and production parameters using a surrogate model, optimizing resource extraction by generating a customized work schedule that improves metrics such as cumulative resource output and net present value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to develop development design and production schedules for hydraulic fracturing, then comprehensive resource extraction planning can be achieved, but the process requires a significant amount of time
Solution Approach 1:
The patent creates a surrogate model that copies the essential characteristics and behavior of the complex reservoir model. This surrogate model can be evaluated much faster than the full reservoir model, allowing multiple schedule evaluations and optimizations to be performed in a fraction of the time while maintaining sufficient accuracy for decision-making purposes
Solution Approach 2:
The patent performs preliminary evaluations using the surrogate model to identify promising schedule options before committing computational resources to full reservoir model simulations. This preliminary filtering action reduces the overall time required by avoiding unnecessary detailed simulations of suboptimal schedules
2Productivity
If well density is increased to improve productivity of the asset, then more wells can be drilled in an area, but the wells may interact in the subsurface resulting in less than optimal resource output
Solution Approach 1:
The patent incorporates feedback mechanisms where the surrogate model evaluates the performance of different well spacing configurations and provides information about well interactions. This feedback allows the optimization process to adjust well spacing to maintain productivity while avoiding harmful subsurface interactions between adjacent wells
Solution Approach 2:
The patent uses dynamic optimization to adjust well spacing and drilling schedules based on predicted subsurface conditions and well interactions. Rather than using fixed well spacing, the system dynamically determines optimal configurations that maximize productivity while preventing interference between wells
3Productivity
If extraction schedules are not updated over time, then operational simplicity is maintained, but the schedules become stale and less relevant and accurate resulting in reduced resource extraction
Solution Approach 1:
The patent implements periodic updates of the extraction schedule using the surrogate model. At predetermined intervals or when triggered by specific conditions, the system re-evaluates the schedule using updated reservoir data and surrogate model predictions, ensuring the schedule remains current and optimized without requiring continuous complex management
Solution Approach 2:
The surrogate model is designed to be self-updating and self-evaluating, automatically incorporating new data and adjusting schedule recommendations without requiring extensive manual intervention. This self-service capability maintains schedule accuracy while minimizing the operational complexity of schedule management
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Significantly reduces the number of evaluations required, allowing for optimized resource extraction schedules to be generated in a fraction of the time of traditional methods, leading to increased resource production and improved economic optimization of well pad operations.
Implementation Method 1
The hydraulic fracturing process involves injecting a fracturing fluid including water, proppant particles (e.g., sand), and chemicals into wellbores under high pressure. The fracturing fluid penetrates small cracks and natural fractures in the reservoir and causes larger fractures emanating from the wellbores.
Data Source
AI summary
A system includes a schedule generator having one or more processors configured to obtain resource extraction parameters for extracting a resource from a reservoir. The resource extraction parameters include well creation parameters associated with drilling wellbores, well stimulation parameters associated with introducing fracturing fluid into the wellbores, and production parameters associated with extracting the resource through the wellbores. The schedule generator selects initial trial schedules having different values of the resource extraction parameters and receives initial resource output data generated by execution of the initial trial schedules with a designated reservoir model. The schedule generator generates a surrogate model based on the initial resource output data and the initial trial schedules and uses the surrogate model to perform iterations of selecting modified trial schedules until a predetermined condition is satisfied.