Development of Numerical Model Based Deep Learning for the Temperature Prediction of the Hot Rolling Process
Bibliographic record
Abstract
In the hot rolling mill, the thermal history experienced by the strip during processing is one of the most important parameters influencing the product quality.Especially, for the hot rolling process, the temperature prediction is the key technology because the metallurgical properties of product are substantially affected by it.During the several decades, the models for the temperature of the strip are demonstrated for the precise prediction on the basis of the finite difference models [1-4] and the finite element (FE) models [5][6][7][8] than on the basis of the elementary models which inherently involve many simplifying assumptions.However, a precise model such as a FE process model tends to require a large time for the calculation.In this paper, a numerical model based deep learning is presented for the prediction of the temperature distributions during the hot rolling.The hot rolling process consists of reheating furnace, roughing mill, induction heater and finishing mill.There exist several reheating furnaces to heat the slab for the rolling temperature, the roughing mill to reduce the thickness, the induction heater for additional heating and the finishing mill to produce the product of desired thickness.For the hot rolling process, sound prediction of the temperature is vital for achieving the desired temperature because the metallurgical properties of product are substantially affected by it.In addition, by achieving the desired rolling temperature, we can ensure rolling stability.In this paper, mathematical model is presented for the prediction of the temperature distributions during the rolling, the cooling, and the heating.The model consists of a model for the prediction of temperature distributions in bite zone, a model for the prediction of temperature distributions in the cooling regions and a model for the prediction of temperature distributions at the induction heater.The model in bite zone considers the energy terms of deformation, friction, and the heat transfer from the strip to the roll.The model in the cooling regions considers the radiation and the convection.The model of the induction heater considers the heat generation due to the induced eddy current.From the combination of these mathematical models, the temperature distributions can be predicted in the whole regions between the exit of the reheating furnace and the exit of the finishing mill.Furthermore, by using the presented prediction model of the temperature, we can optimize the process conditions for the desired rolling temperature.The prediction accuracy of the proposed model is examined through comparison with actual data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".