Machine Learning Well Priority Ranking for Corrosion Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Corrosion of wells due to internal and external factors such as chemical reactions with pipe components, cement channeling, and cement bonding issues, makes it difficult to accurately assess well integrity and adjust production parameters effectively.
Innovation Solution
A method using machine learning models to determine a corrosion severity rank based on well corrosion values and barrier parameters, which are then used to calculate a well priority rank. This rank is used to generate a wellbore drilling plan.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional methods are used to assess well integrity, then the assessment process is simple, but the accuracy and reliability of corrosion detection is insufficient
Solution Approach 1:
The patent replaces traditional mechanical/physical inspection methods with a machine learning-based predictive system. The ML model processes multiple input features (corrosion values, barrier parameters, well criticality features) to predict corrosion severity ranks, substituting complex physical inspection processes with an automated computational approach that achieves higher accuracy.
Solution Approach 2:
The patent transforms the assessment approach by changing from direct physical measurement to predictive parameter calculation. The system uses input parameters (corrosion values, cement and casing barrier properties) as inputs to the ML model, which outputs predicted corrosion severity ranks. This parameter transformation enables more accurate and comprehensive well integrity assessment.
2Measurement precision
If comprehensive corrosion assessment is performed, then the accuracy of well condition knowledge is improved, but the time required for assessment increases
Solution Approach 1:
The patent applies preliminary action by pre-processing and organizing corrosion data, barrier parameters, and well criticality features before they are input to the machine learning model. The system prepares and structures the data in advance, allowing for rapid prediction without time-consuming analysis during the actual assessment process.
Solution Approach 2:
The patent substitutes time-consuming manual analysis with automated machine learning prediction. The ML model processes comprehensive corrosion assessment data automatically and quickly, providing accurate predictions of casing conditions at various depth intervals without requiring extensive manual measurement and analysis time.
3Productivity
If detailed wellbore drilling plans are generated, then the productivity of well maintenance operations is improved, but the complexity of planning increases
Solution Approach 1:
The patent incorporates feedback mechanisms where the machine learning model continuously refines its predictions based on actual well conditions and maintenance outcomes. The system uses feedback from well criticality features and corrosion severity ranks to generate optimized drilling plans, improving maintenance productivity while managing complexity through iterative refinement.
Solution Approach 2:
The patent transforms complex planning requirements into structured output parameters from the ML model. The model processes input parameters (corrosion values, barrier parameters) and outputs structured predictions (corrosion severity ranks, well priority ranks) that directly inform drilling plan parameters, simplifying the planning process while maintaining high productivity.
Data Source
AI summary
A method and a system for determining a well priority rank. The method includes obtaining well corrosion values and well barrier parameters, the well barrier parameters including properties of cement and casing and determining a corrosion severity rank using a machine learning model and based on the obtained well corrosion values and the obtained well barrier parameters. Further, the method includes determining the well priority rank based on the determined corrosion severity rank and well criticality features, the well criticality features indicating an amount of damage caused by a deterioration of a well. The determined well priority rank is used to generate a wellbore drilling plan.