Cold Rolling Condition Prediction for High Si Al Steel Stability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods struggle to maintain rolling stability and productivity when processing difficult-to-roll materials with high Si and Al content, as variations in residual oxide scale lead to frictional coefficient changes, affecting mill operation and potentially causing shape defects or fractures.

Innovation Solution

A prediction model is trained using past operation records to predict and adjust cold rolling conditions, incorporating annealing, pickling, and work roll usage, to ensure stable rolling by managing asymmetric components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a prediction model is trained using past operation records to predict asymmetric components, then rolling stability is improved, but device complexity increases

Engineering Contradiction:
Improverolling stabilityVSAvoidprediction model complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The prediction model is trained in advance using historical operation records to learn the relationship between process parameters and asymmetric components. This preliminary training enables the model to predict and compensate for asymmetric effects before actual rolling occurs, improving stability without adding real-time complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The model uses past operation track records as training data, creating a feedback loop where historical performance informs future predictions. This allows the system to continuously improve rolling stability by learning from previous operations while maintaining a manageable model structure

Inventive Principle:
Principle #23Feedback

2Manufacturing precision

If cold rolling conditions are adjusted to compensate for residual oxide scale variations, then manufacturing precision is improved, but productivity decreases

Engineering Contradiction:
Improveshape accuracyVSAvoidrolling speed
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The model predicts asymmetric components and adjusts rolling conditions by changing key parameters such as roll force distribution and rolling speed. This allows precise compensation for oxide scale variations while maintaining overall productivity through targeted rather than universal parameter adjustments

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The correction focuses specifically on asymmetric components caused by residual oxide scale rather than applying uniform adjustments across all rolling parameters. This localized approach maintains shape accuracy while minimizing impact on overall rolling speed and productivity

Inventive Principle:
Principle #3Local quality

3Manufacturing precision

If operators manually set pass schedule and shape control actuators, then manufacturing precision is improved, but ease of operation decreases

Engineering Contradiction:
Improveshape control accuracyVSAvoidoperator workload
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The prediction model automatically performs the complex task of analyzing past operation records, predicting asymmetric components, and determining optimal rolling condition adjustments. This self-service capability maintains high shape control accuracy while significantly reducing operator workload and dependency on manual expertise

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual operator decision-making process is replaced with an automated prediction model that uses machine learning algorithms to analyze historical data and determine optimal settings. This substitution maintains manufacturing precision while improving ease of operation by eliminating complex manual adjustments

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4647188A1Cold rolling condition-setting method, cold rolling method, cold rolled steel sheet manufacturing method, cold rolling condition-calculating device, and cold rolling mill
Publication Date: 2025.11.12 JFE STEEL CORP
  • EP4647188A1 patent drawingFigure 1
  • EP4647188A1 patent drawingFigure 2
  • EP4647188A1 patent drawingFigure 3

AI summary

A cold rolling condition setting method is a method of setting, using a prediction model, a condition when cold rolling a steel sheet. The prediction model is a model trained using, as explanatory variables, information about each rolling target material, an annealing condition, a pickling condition, and a cold rolling condition from among past operation track records and using, as an objective variable, an asymmetric component from among rolling track records at the first rolling stand. The cold rolling condition setting method comprises: inputting an annealing condition, a pickling condition, and a set cold rolling condition at the first rolling stand for a rolling target material to be rolled to the prediction model to predict an asymmetric component at the first rolling stand; and changing the set cold rolling condition so that the predicted asymmetric component will satisfy a predetermined condition.