Drillstring Condition Evaluation Using Virtual Sensor Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately evaluating the condition of drillstring components in boreholes is challenging due to material fatigue from downhole conditions, with existing methods being costly, prone to error, and inefficient in tracking environmental history, especially since sensors are costly and take up valuable space, increasing complexity and power demands.
Innovation Solution
A method and system using a trained artificial neural network to estimate tool parameters like vibration and temperature at various positions along the drillstring, allowing for condition evaluation and life management decisions, even with sensors positioned offset from the measurement points, creating a tool parameter history for component life management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors are deployed along the drillstring to accurately measure tool parameters at various positions, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual model (copy) of the drillstring system that replicates the physical behavior of the component. Instead of deploying multiple physical sensors, the system uses a single sensor's measurements as input to a trained neural network model that generates estimated values for multiple positions along the drillstring. This virtual copying approach achieves comprehensive monitoring without the complexity of multiple physical sensors.
Solution Approach 2:
The neural network model acts as an intermediary between the single physical sensor and the multiple measurement positions. The model receives limited sensor data and transforms it into comprehensive tool parameter estimates for various positions along the drillstring, effectively mediating the information gap without requiring direct physical measurement at each position.
2Reliability
If multiple sensors are installed along the drillstring to monitor tool parameters, then condition evaluation accuracy is improved, but the cost and space requirements increase
Solution Approach 1:
The system creates virtual replicas of sensor measurements at multiple positions through the neural network model. Instead of installing multiple physical sensors that would consume space and resources, the model generates copied measurement data for various positions along the drillstring based on input from a single sensor, thereby maintaining reliability without increasing sensor quantity.
Solution Approach 2:
A single physical sensor serves multiple functions by providing input data that the neural network model processes to generate tool parameter estimates for multiple positions along the drillstring. This multi-functionality approach allows one sensor to effectively perform the role of multiple sensors, reducing both quantity and space requirements.
3Measurement precision
If sensors are positioned exactly at the measurement points of interest, then measurement precision is improved, but device complexity and installation difficulty increase
Solution Approach 1:
Instead of positioning sensors exactly at measurement points (traditional approach), the patent inverts the approach by positioning a single sensor at a convenient location and using the neural network model to calculate tool parameters at distant positions. The system works backwards from the sensor location to estimate conditions throughout the entire drillstring, simplifying installation while maintaining accuracy.
Solution Approach 2:
The neural network model serves as an intermediary that bridges the gap between the sensor's physical location and the distant measurement points of interest. It transforms the single location's sensor data into accurate estimates for multiple positions, eliminating the need for precise sensor positioning at each measurement point.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Systems, methods and devices for evaluating a condition of a downhole component of a drillstring. Methods include estimating a value of a tool parameter of the component at at least one selected position on the drillstring; and using the estimated value to evaluate the condition of the downhole component. The estimating is done using a trained artificial neural network that receives information from at least one sensor that is positionally offset from the selected position. The method may further include creating a record representing information from estimated values of the tool parameter at the at least one selected position over time. The at least one selected position may include a plurality of positions, such as positions at intervals along the component, including substantially continuously along the component.