Adaptive Machine Learning for Well Tool Passage Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inexact nature of wellbore formation and completion can block or hinder the passage of tools, making it challenging to predict the interaction between well tools and well geometries, which affects tool string component selection, well design, and operational feasibility in drilling and production operations.
Innovation Solution
A distributed computing system with a modeling system that models interactions between the well tool string and the well, using a combination of mathematical, 3D geometric, and adaptive machine learning models to predict the passage of the tool string through the well, accounting for geometrical, material, and operational characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If wellbore formation and completion are performed with standard tolerances, then manufacturing cost and time are reduced, but tool passage becomes blocked or hindered due to geometric irregularities
Solution Approach 1:
The system performs preliminary modeling and prediction of tool string passage through the wellbore before actual drilling and completion operations. By simulating the interaction between tool geometries and wellbore characteristics in advance, operators can identify potential blockages and adjust either the well design or tool configuration proactively, preventing passage issues before they occur in the field.
Solution Approach 2:
The system creates virtual copies or digital models of both the wellbore geometry and tool string components. These digital twins allow for repeated simulation and analysis of tool passage scenarios without physical risk, enabling operators to test multiple configurations and predict interactions accurately before deploying actual equipment.
2Measurement precision
If detailed geometric modeling of tool string and wellbore is performed, then prediction accuracy of tool passage is improved, but computational complexity and time increase
Solution Approach 1:
The modeling system divides the tool string into discrete components (tubing, cables, tools, connectors) and the wellbore into sequential zones or intervals. This segmentation allows for modular analysis where each component's geometry and interaction characteristics can be modeled independently and then combined, reducing overall computational complexity while maintaining prediction accuracy.
Solution Approach 2:
The system employs dynamic modeling that adapts the level of geometric detail and computational effort based on the specific scenario being analyzed. For routine passages, simplified models are used; for complex or high-risk scenarios, more detailed geometric modeling is automatically applied, optimizing the balance between accuracy and computational resources.
Data Source
AI summary
In modeling passage of an elongate well tool through an interval of a well an adaptive machine learning model executed on a computing system receives a first set of inputs representing a plurality of characteristics of the well tool and a second set of inputs representing a plurality of characteristics of the well. The adaptive machine learning model also receives historical data representing a plurality of other well tools passed through a plurality of other wells and a plurality of characteristics of the other well tools and the other wells. The adaptive machine learning model matches the historical data with at least a portion of the first and second sets of inputs, and determines, based on the matching whether the well tool can pass through the interval of the well.