EM Collar Location via Interactive Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing collar locator algorithms in oil and gas wellbore inspection face challenges in accurately identifying and locating collars on multiple pipe strings due to varying joint lengths and overlapping collar signatures, leading to ambiguous situations and potential errors in pipe assignment.
Innovation Solution
An interactive workflow combining an automatic algorithm with user-assisted methodology for resolving ambiguities, utilizing electromagnetic (EM) measurements to predictively locate collars, and employing machine learning models to enhance collar identification and joint length estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If existing collar locator algorithms use periodicity or pattern recognition techniques, then collar location can be automated, but accuracy deteriorates in ambiguous situations with overlapping collar signatures
Solution Approach 1:
The system incorporates user feedback by allowing operators to review and correct algorithm-generated collar locations. Users can mark ambiguous situations and provide ground truth data, which then feeds back into the system to refine future automated detections. This feedback loop resolves the contradiction by maintaining automation while improving precision through continuous learning from user corrections.
Solution Approach 2:
The system introduces an intermediary layer between automated detection and final collar identification. This intermediary consists of user review and validation steps that mediate between the algorithm's automated picks and the final accepted collar locations. The intermediary resolves ambiguities through human expertise while maintaining the benefits of automation.
2Loss of time
If fully automated collar locator algorithms are used, then time consumption is reduced, but human error increases in ambiguous situations
Solution Approach 1:
The system uses user feedback to continuously improve algorithm reliability. Operators review automated results and correct errors, providing feedback that trains the system to recognize ambiguous situations better. This feedback mechanism maintains high reliability while preserving time efficiency through automation.
Solution Approach 2:
The system performs preliminary automated detection to handle the majority of straightforward collar locations, saving time. Only ambiguous cases requiring human intervention are identified through preliminary analysis, allowing the system to maintain both speed and reliability by preparing automated results in advance and reserving human expertise for edge cases.
3Measurement precision
If manual inspection and correction of algorithm picks is performed, then accuracy is improved, but productivity decreases due to tedious manual work
Solution Approach 1:
The system uses feedback from manual corrections to automatically improve future detections. By learning from operator corrections, the algorithm becomes more accurate over time, reducing the need for manual inspection. This feedback loop resolves the contradiction by maintaining high productivity through automation while improving precision through continuous learning.
Solution Approach 2:
The system performs self-service by automatically correcting its own errors through machine learning from user feedback. Rather than requiring continuous manual correction, the system learns from initial user inputs and autonomously improves its detection accuracy, maintaining high productivity while achieving high precision through self-improvement.
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
This approach significantly reduces human error and time consumption in collar location, providing accurate and efficient identification of collars and pipe joint lengths, even in complex multi-string configurations.
Implementation Method 1
In EC, when the transmitter coil emits the primary transient EM fields, eddy currents are induced in the casing. These eddy currents then produce secondary fields which are received along with the primary fields by the receiver coil.
Implementation Method 2
In EC, when the transmitter coil emits the primary transient EM fields, eddy currents are induced in the casing. These eddy currents then produce secondary fields
Data Source
AI summary
A method and system may include disposing an electromagnetic (EM) logging tool in a wellbore. The EM logging tool may include a transmitter disposed on the EM logging tool and a receiver disposed on the EM logging tool. The method may further include transmitting an electromagnetic field from the transmitter into one or more, measuring the eddy current in the one or more tubulars with the receiver, and forming an EM log from the plurality of measurements. Additionally, the method may include identifying a representative signature of a collar from the EM log, locating a plurality of signatures that are similar to the representative signature, iteratively locating a collar signature based at least in part on the representative signature, the plurality of signatures that are similar to the representative signature, and a joint length; and displaying a depth for each of the one or more collars.