Steel Processing Line Monitoring for Abnormality Cause Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing steel processing methods fail to accurately identify process parameter drifts or actuator malfunctions, leading to deviations in microstructure and properties, and do not allow for timely maintenance or parameter adjustments to maintain product quality.
Innovation Solution
A method and device for monitoring a steel processing line using sensors, actuators, and an electronic device with a control module and abnormality detector, which acquires chemical composition and target properties, determines line control signals, and uses a trained classifier to detect abnormalities in line control signals, identifying the cause of deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If feedback control is used to regulate steel processing operations, then product quality is maintained despite deviations, but the ability to identify specific process parameter drifts or actuator malfunctions is lost
Solution Approach 1:
The patent introduces an abnormality detector as an intermediary component that operates in parallel with the feedback control system. This detector analyzes control signals and sensor data to identify specific abnormality causes without interfering with the primary quality control function. The intermediary structure allows simultaneous achievement of quality maintenance and abnormality identification.
Solution Approach 2:
The control system is segmented into two functional parts: the feedback control module that maintains product quality, and the abnormality detector module that identifies specific deviations. This segmentation allows each module to specialize in its function without compromising the other, resolving the contradiction between quality maintenance and abnormality identification.
2Measurement precision
If multiple sensors and control signals are monitored to identify abnormality causes, then detection accuracy is improved, but system complexity increases
Solution Approach 1:
The abnormality detector is designed as a universal analysis unit that processes multiple types of inputs (control signals, sensor readings, process parameters) through a single trained classifier. This multi-functional approach improves detection accuracy across various abnormality types without proportionally increasing system complexity, as the core detection engine remains unified rather than requiring separate detectors for each abnormality cause.
Data Source
AI summary
A method for monitoring a steel processing line that includes: a control module which determines line control signals for controlling the steel processing line, the line control signals being determined depending on a chemical composition of a steel semi-product being processed and depending on a target property for the semi-product, and an abnormality detector, which determines an abnormality indicator which specifies whether the line control signals are normal or abnormal, an abnormality cause selected in a list of predetermined abnormality causes being then specified, the abnormality indicator being determined using a trained classifier whose inputs comprise at least: the chemical composition, the target property, and the line control signals.