Two-Stage Furnace Flooding Detection System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Furnace flooding, characterized by unstable combustion and potential explosion risks, is difficult to detect timely and accurately with existing methods, which often result in late warnings and frequent shutdowns, disrupting industrial processes and causing economic losses.
Innovation Solution
A two-stage detection method using mathematical models to identify true and false positive indicators of furnace flooding, allowing for timely alerts and reducing false positives through data processing and classification, enabling operators to take preventive measures without full shutdowns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing detection methods are used, then furnace flooding detection is provided, but detection timeliness and accuracy are insufficient leading to late warnings
Solution Approach 1:
The detection process is divided into two distinct stages: a first stage that generates initial indicators of potential flooding conditions, and a second stage that classifies these indicators into true positives and false positives. This segmentation allows each stage to focus on specific detection tasks, improving overall accuracy and timeliness of warnings.
Solution Approach 2:
The system performs preliminary detection in the first stage to identify potential flooding conditions before they develop into full-scale events. By generating early indicators and classifying them in advance, the system provides timely warnings that enable preventive action before actual flooding occurs.
2Reliability
If existing detection methods are used, then flooding detection is provided, but false positives are frequent causing unnecessary shutdowns
Solution Approach 1:
The classification process is segmented into multiple stages with different functions. The first stage identifies potential indicators, while the second stage carefully classifies them into true positives and false positives. This segmentation reduces false alarms by subjecting each indicator to rigorous classification before triggering shutdowns.
Solution Approach 2:
The patent introduces an intermediary classification process between raw detection indicators and final alarm generation. This intermediary stage acts as a filter that distinguishes true flooding conditions from false positives, preventing unnecessary production shutdowns while maintaining detection reliability.
3Measurement precision
If two-stage detection with classification is implemented, then detection accuracy is improved, but system complexity increases
Solution Approach 1:
The complex detection task is segmented into two manageable stages: indicator generation and indicator classification. Each stage handles a specific aspect of the detection process, making the overall complex system more manageable and maintainable while improving accuracy through specialized processing at each stage.
Data Source
AI summary
A method includes processing data associated with operation of equipment in an industrial process to repeatedly (i) identify one or more models that mathematically represent the operation of the equipment using training data and (ii) generate first indicators potentially identifying at least one specified condition of the equipment using evaluation data and the one or more models. The method also includes classifying the first indicators into multiple classes. The multiple classes include true positive indicators and false positive indicators. The true positive indicators identify that the equipment is suffering from the at least one specified condition. The false positive indicators identify that the equipment is not suffering from the at least one specified condition. The method further includes generating a notification indicating that the equipment is suffering from the at least one specified condition in response to one or more first indicators being classified into the class of true positive indicators.