Adaptive Strip Chew Prediction for Hot Rolling Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The occurrence of strip chew in hot rolling processes is difficult to predict accurately, relying heavily on operator experience and intuition, and existing control methods are ineffective in preventing this phenomenon, leading to reduced productivity and roll intensity.
Innovation Solution
A prediction system using adaptive models constructed through machine learning and statistical methods to predict the occurrence and location of strip chew by collecting and analyzing data from preceding rolling paths, allowing for pre-emptive adjustments to prevent strip chew, such as controlling entrance side guides.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If operator experience and intuition are used to predict strip chew occurrence, then no additional equipment is needed, but prediction accuracy is insufficient leading to reduced productivity
Solution Approach 1:
The patent replaces the mechanical reliance on operator experience and intuition with an automated information processing system. The prediction device collects rolling condition data, processes it through a prediction model, and outputs predictions automatically, substituting human sensory and cognitive mechanisms with computational algorithms that provide objective, repeatable, and accurate predictions without being constrained by human limitations.
Solution Approach 2:
The system enables self-service prediction by automatically collecting rolling condition data from sensors, processing it through the prediction model, and generating predictions without requiring operator intervention. The device autonomously monitors rolling parameters, performs calculations, and outputs predictions, allowing the system to serve itself in the prediction task while freeing operators from manual prediction efforts.
2Ease of operation
If existing control methods are used to prevent strip chew, then simple operations are required, but they are ineffective leading to roll inspections and reduced productivity
Solution Approach 1:
The prediction device performs preliminary action by predicting strip chew occurrence before it actually happens during rolling. By analyzing rolling condition data in advance and outputting predictions ahead of time, the system allows operators to take preventive measures proactively rather than reactively, preventing strip chew incidents before they compromise productivity or require roll inspections.
Solution Approach 2:
The system implements feedback by continuously monitoring rolling condition data, processing it through the prediction model, and outputting predictions that feed back to operators. This closed-loop feedback mechanism provides real-time or near-real-time information about potential strip chew risks, enabling operators to adjust operations dynamically based on predicted conditions and maintain high productivity.
3Reliability
If strip chew occurs and rolls are extracted for inspection, then roll surface quality is maintained, but productivity is reduced due to operation stoppage
Solution Approach 1:
The prediction device applies preliminary anti-action by predicting strip chew occurrence before it happens, allowing operators to take preventive measures to avoid the harmful effect. By anticipating potential strip chew based on rolling condition analysis, the system enables operators to adjust operations in advance, preventing the strip chew that would otherwise lead to roll surface degradation and subsequent productivity-lossinducing inspections.
Solution Approach 2:
The system performs preliminary action by providing advance prediction of strip chew occurrence, giving operators time to implement preventive measures before the actual strip chew happens. This proactive approach maintains roll surface quality by preventing damage before it occurs, eliminating the need for productivity-reducing stoppages and inspections while ensuring continuous high-quality production.
4Productivity
If a prediction system is implemented to improve prediction accuracy, then productivity can be improved, but device complexity increases
Solution Approach 1:
The prediction device achieves multi-functionality by integrating data collection, data processing, prediction modeling, and output generation into a single unified system. Rather than requiring separate equipment for each function, the device performs multiple tasks - collecting rolling condition data from sensors, processing it through prediction algorithms, and outputting predictions - thereby improving productivity while minimizing the increase in device complexity through functional integration.
Solution Approach 2:
The system achieves self-service by automatically collecting rolling condition data, processing it through the prediction model, and generating predictions without requiring additional complex equipment or manual operations. The device serves itself by autonomously performing all prediction tasks, reducing the need for complex external systems while improving productivity through automated, accurate predictions.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
The prediction system of strip chew collects and stores first data and second data as adaptive model construction data. The first data indicates the occurrence or non-occurrence of the strip chew in an object rolling path and the occurrence point of the strip chew. The second data includes information on a preceding rolling path and attribute information on an object strip. The system constructs an adaptive model using the stored adaptive model construction data, and stores the constructed adaptive model as an adapted model. The system collects prediction data similar to the second data. Then, the system inputs the prediction data to the adapted model to predict the occurrence or non-occurrence of the strip chew in the object rolling path and all or some of the occurrence points of the strip chew before the prediction object strip reaches the object rolling path.