Drilling Control Optimization Using Event Stream Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Drilling operations across various industries face complexity, expense, and risk due to inefficiencies in controlling drilling parameters, particularly in optimizing rate of penetration and minimizing mechanical specific energy and wellbore stability.
Innovation Solution
An event stream processing engine (ESPE) is instantiated to execute an objective function model determined using historical drilling data, which processes current drilling data to determine optimal control values, potentially using neural network or decision tree models to maximize rate of penetration and optimize wellbore stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional drilling control methods are used, then drilling operations can be performed with simple control systems, but the rate of penetration is suboptimal and mechanical specific energy cannot be minimized
Solution Approach 1:
The system performs preliminary actions by training neural network models offline using historical drilling data before actual drilling operations. The models are trained to predict optimal control variables based on formation properties and drilling parameters, enabling real-time optimization without requiring complex real-time computation during drilling operations.
Solution Approach 2:
The patent replaces traditional mechanical trial-and-error control methods with a neural network-based computational system. The neural network models substitute for complex mechanical control mechanisms by using learned patterns from historical data to automatically determine optimal control variables, thereby increasing productivity while managing system complexity through software-based intelligence.
2Productivity
If drilling parameters are optimized to maximize rate of penetration, then drilling efficiency improves, but wellbore stability may be compromised
Solution Approach 1:
The system dynamically changes drilling parameters by inputting multiple control variables (bit type, drill stem rotation speed, pump rate, mud weight, etc.) into the neural network model. The model processes these parameter changes and outputs optimized control variable values that balance rate of penetration with wellbore stability, allowing simultaneous optimization of both objectives through multi-parameter coordination.
Solution Approach 2:
The patent implements feedback mechanisms where actual drilling results are fed back into the system to retrain and refine the neural network models. This continuous feedback loop enables the system to learn from actual performance and improve its predictions, ensuring that optimized parameters consistently achieve both high productivity and reliable wellbore stability across different drilling conditions.
3Ease of operation
If historical drilling data is processed to create objective function models, then optimal control values can be determined, but computational resources and time are required
Solution Approach 1:
The system performs preliminary model training using historical drilling data before actual operations begin. By pre-training the neural network models offline, the system eliminates the need for time-consuming real-time training during drilling operations, making optimal control determination accessible and efficient while investing computational resources in advance.
Solution Approach 2:
The patent creates copies of historical drilling data and models the optimal control relationships through neural network architectures. These digital copies and learned patterns allow the system to quickly determine optimal control values for new drilling scenarios without reprocessing entire historical datasets, thereby reducing computational time while maintaining ease of operation.
Data Source
AI summary
A computing device configured to determine an optimal value for a control of a drilling operation is provided. An event stream processing engine (ESPE) instantiated. The ESPE is instantiated to execute an objective function model determined using historical drilling data. The objective function model maximizes a rate of penetration for a previous drilling operation. The historical drilling data includes a plurality of values measured for each of a plurality of drilling control variables during the previous drilling operation. Measured drilling data that includes current drilling data values for a current drilling operation is received by the ESPE. The received, measured drilling data is processed through the ESPE instantiated to execute the objective function model to determine an optimal value for a control of the current drilling operation. The determined optimal value is output by the ESPE for the control of the current drilling operation.