Cold Rolling Condition Setting for Sheet Crown Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to maintain stability and productivity during cold rolling of difficult-to-roll materials with high loads and small pre-rolling sheet thickness, leading to fluctuations in sheet crown and potential defects or breakage.
Innovation Solution
A cold rolling mill rolling condition setting method using a prediction model that transforms pre-cold rolling data into multi-dimensional information, predicts the post-cold rolling state, and adjusts rolling conditions to ensure stability and productivity by estimating and adjusting the post-rolling shape of the material.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic control is used for cold rolling, then productivity is improved, but the ability to handle sheet crown fluctuations and maintain stability deteriorates
Solution Approach 1:
The system performs preliminary analysis of sheet crown fluctuations using learned models before the actual rolling process, predicting the magnitude and pattern of fluctuations. This allows the control system to pre-adjust rolling conditions and shape control actuator settings in advance, ensuring stability is maintained even during high-speed automatic operation.
Solution Approach 2:
The system implements a feedback mechanism where the learned sheet crown fluctuation patterns are continuously used to adjust control decisions. The control system monitors actual rolling conditions, compares them with learned patterns, and dynamically adjusts shape control actuator settings to compensate for predicted fluctuations, maintaining stability throughout the rolling process.
2Reliability
If operator experience is relied upon for setting pass schedule and shape control, then cold rolling stability is improved, but productivity varies and cannot be maximized
Solution Approach 1:
The system enables self-service by automatically learning sheet crown fluctuation patterns from historical data and using this learned knowledge to autonomously determine optimal pass schedules and shape control settings. This eliminates dependency on operator experience while consistently achieving stable rolling results, allowing the system to operate at maximum productivity without human intervention.
Solution Approach 2:
The system transforms qualitative operator experience into quantitative learned parameters that can be systematically applied. By converting expert knowledge into learnable patterns of sheet crown fluctuations, the system can automatically adjust multiple control parameters (pass schedule, shape control actuator settings) to achieve both stability and maximum productivity consistently.
3Productivity
If high rolling load is applied to thin pre-rolling sheet, then productivity is improved, but shape defects and breakage occur
Solution Approach 1:
The system performs preliminary analysis of the relationship between rolling load and resulting sheet crown fluctuations using learned models. By predicting the magnitude and pattern of shape defects before they occur, the system can pre-adjust shape control actuator settings to counteract the expected defects, allowing high rolling loads to be applied without sacrificing shape accuracy.
Solution Approach 2:
The system uses learned knowledge to predict sheet crown fluctuations caused by high rolling loads before the actual rolling occurs. This allows the control system to pre-adjust rolling conditions and shape control settings in advance, preventing shape defects and breakage while maintaining high productivity rolling speeds.
Data Source
AI summary
A cold rolling mill rolling condition setting method using a prediction model being generated with an explanatory variable being first multi-dimensional data obtained by transforming past rolling performance data including pre-cold rolling data of a roll material on an entry side of the cold rolling mill into multi-dimensional data, and an objective variable being post-cold rolling data of the roll material on a delivery side of the cold rolling mill, the method includes: estimating a post-rolling shape of a roll target material by inputting, to the prediction model, second multi-dimensional data generated from information including the pre-cold rolling data of the roll target material on the entry side of the cold rolling mill and a target rolling condition of the cold rolling mill; and changing the target rolling condition of the cold rolling mill such that the estimated post-rolling shape of the roll target material satisfies a predetermined condition.


