Rolled Product Material Property Prediction With Offline Approximate Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing material properties prediction methods for rolled products face challenges in achieving high-speed and high-accuracy predictions due to computational load and limited predictive accuracy, particularly when modeling complex material behaviors and temperature distributions in the width direction of the material-to-be-rolled.
Innovation Solution
A material properties prediction device that creates an approximate model offline using a dataset of rolling conditions and metallurgical phenomena, allowing for online prediction of material properties in individual three-dimensional mesh-shaped areas of the rolled product, reducing computational load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a process model is used to simulate manufacturing steps offline to predict material properties, then prediction accuracy is improved, but prediction speed deteriorates due to computational load
Solution Approach 1:
The patent pre-calculates material properties for various rolling conditions offline before actual production, storing these results in a database. During online operation, the system directly retrieves pre-calculated results based on actual rolling parameters, avoiding real-time computational load while maintaining high prediction accuracy.
Solution Approach 2:
The patent creates a virtual copy of the manufacturing process through detailed process models that simulate heating, rolling, and cooling steps. This virtual model allows offline prediction of material properties without requiring actual production runs, enabling accurate predictions to be made in advance and stored for rapid online retrieval.
2Ease of operation
If target values for process parameters are determined based on experience, then ease of operation is improved, but manufacturing precision deteriorates when product specifications become sophisticated and diversified
Solution Approach 1:
The patent replaces experience-based manual setting of target values with an automated information processing system. The system uses process models and databases to automatically determine optimal target values for heating temperatures, cooling rates, and rolling parameters based on desired product specifications, eliminating reliance on operator experience while maintaining operational simplicity.
Solution Approach 2:
The patent implements a feedback mechanism where actual material properties measurements are compared with predicted values, and the system learns from discrepancies to improve future predictions. This continuous refinement allows the system to automatically adapt to varying product specifications while maintaining ease of operation.
3Ease of operation
If conventional tolerance ranges are used for material properties, then ease of operation is improved, but productivity deteriorates due to unachieved parts requiring cutting
Solution Approach 1:
The patent performs preliminary prediction of material properties before the rolling process completes, allowing operators to identify potential unachieved parts in advance. This enables proactive adjustments to be made during the process or targeted cutting only where necessary, rather than conservative cutting based on conventional tolerance ranges, thereby improving yield rate.
Solution Approach 2:
The patent applies different quality control strategies to different regions of the rolled product based on predicted material properties. Instead of uniformly applying conventional tolerance ranges across the entire product, the system identifies specific areas with substandard properties and targets only those regions for cutting or reprocessing, minimizing waste and improving overall productivity.
Data Source
AI summary
A material properties prediction device for rolled products includes: an approximate model creation unit that creates an approximate model offline that comprehensively predicts material properties of a group of rolled products to be manufactured on a rolling line; and a material properties prediction unit that online predicts material properties in individual three-dimensional mesh-shaped areas of a rolled product manufactured on the rolling line, by using the approximate model. The approximate model creation unit includes: a dataset creation unit that creates a dataset to be used to create approximate model, in which the dataset creation unit has a condition setting unit that sets rolling conditions for the group of rolled products, and a material calculation unit that calculates metallurgical phenomena and material properties under the rolling conditions; and a model parameter determination unit that determines parameters expressing the approximate model by using the dataset.