Thermal Scanning and Machine Learning for Refractory Degradation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring refractory material degradation in manufacturing vessels, such as furnaces and ladles, are inadequate for detecting cracks and molten material penetration, leading to increased risk of leakage and unnecessary shutdowns, as they rely on visual inspections and laser scanning which lack accuracy and reliability, especially when slag buildup occurs.
Innovation Solution
A system integrating thermal scanning and machine learning-based mathematical models to correlate external surface temperature data with operational parameters, allowing for real-time estimation of refractory material degradation and molten material penetration, providing early warnings and improving maintenance planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If visual inspections and laser scanning are used to monitor refractory material degradation, then the monitoring process is simple and cost-effective, but the detection accuracy for cracks and molten material penetration is insufficient
Solution Approach 1:
The patent combines multiple monitoring methods (visual inspection, laser scanning, thermal imaging, and machine learning analysis) into an integrated system. This merging allows the system to leverage the simplicity of visual inspection while incorporating the enhanced detection capabilities of thermal imaging and AI analysis to achieve high accuracy in detecting cracks and molten material penetration without requiring overly complex individual components
Solution Approach 2:
The patent introduces thermal imaging technology as an intermediary between simple visual inspection and complex direct measurement methods. Thermal imaging serves as a mediator that provides enhanced detection capability for subsurface defects and molten material penetration while maintaining a non-contact, relatively simple implementation approach. The machine learning model acts as another intermediary that processes thermal data to extract meaningful degradation information
2Reliability
If conservative shutdowns are implemented to reduce leakage risk, then operational safety is improved, but productivity and vessel utilization decrease
Solution Approach 1:
The patent implements continuous monitoring with machine learning-based analysis that provides real-time feedback on refractory material degradation status. This feedback mechanism allows operators to make informed decisions about vessel operation based on actual degradation levels rather than following conservative fixed schedules. The system updates degradation assessments continuously and provides early warnings when degradation reaches critical thresholds, enabling optimized maintenance timing that balances safety with productivity
Solution Approach 2:
The patent performs preliminary assessment of refractory material condition through continuous monitoring and machine learning analysis before degradation reaches critical levels. By detecting early signs of deterioration such as thermal anomalies indicating cracks or molten material penetration, the system enables proactive maintenance planning that prevents catastrophic failures while avoiding premature shutdowns, thus optimizing both safety and vessel utilization
3Measurement precision
If multiple sensors are deployed to collect comprehensive data on refractory material condition, then measurement accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The patent makes the thermal imaging sensor multi-functional by designing it to perform multiple assessment tasks: detecting surface temperature anomalies, identifying potential crack locations, assessing molten material penetration, and monitoring overall refractory material condition. The machine learning model is trained to extract multiple types of degradation information from the same thermal data set. This universality allows comprehensive condition assessment using a single integrated sensor system rather than requiring multiple specialized sensors, thereby reducing system complexity while maintaining high measurement precision
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 enables more accurate assessment of refractory material condition, reducing the risk of operational failures, extending vessel life, and optimizing maintenance schedules by providing real-time risk calculations and predictive insights.
Implementation Method 1
A thermal scanning device is used to collect data for determining a temperature distribution, of a region of interest, on an external surface of a manufacturing vessel
Data Source
AI summary
Disclosed is a system and a method for estimating a level of risk of operation of a manufacturing vessels used in the formation of certain materials. The system and method are operative to determine a condition and level of degradation of the refractory material of the vessel to early warn a user of the operational risk of continuing operating the vessel, based on thermal scanning and the use of artificial intelligence. The system is capable of determining the presence of certain flaws within the refractory material and the remaining thickness of such material by correlating the results of processing thermal data corresponding to the external surface of the vessel with a machine learning-based mathematical model, according to a set of operational parameters related to the melting process and data from the user.