Prediction of mechanical properties of microalloyed hot rolled steels using machine learning techniques
Bibliographic record
Abstract
The goal of this research was to develop a mechanical property prediction model using machine learning applied at the hot rolling processing stage for microalloyed steel strip produced at the Algoma steel mill located in Ontario, Canada. A neural network model was created to provide predictions of the lower yield strength (LYS) and ultimate tensile strength (UTS). The as-received dataset for prediction of mechanical properties comprised chemical composition and hot rolling processing parameters of temperature, roll speed, roll gap, and strip speed. The model was able to predict the LYS of 88% of the test data with an error of less than or equal to ± 5% and the UTS of 99% of the test data within the same error range. The model results were then used to determine the relative influence of each element in the chemical composition and each hot rolling process parameter on the LYS and UTS. Important features for the determination of strength were the strain at the roughing stand, strain at finishing stand number 2, nitrogen (for LYS) and niobium (UTS) concentrations, and the bar entry temperature. The importance of these features can be rationalized on the basis of physical metallurgy principles based on the effect of hot deformation on the formation of Nb(C,N) precipitates. Precipitation start time is expected to be influenced by the grain size of recrystallized austenite inherited from strain at the roughing stand. Depending on the precipitation start time, strain accumulation in austenite begins as early as after finishing stand number 2 and ultimately influences UTS and LYS by the mechanism of grain refinement. The bar entry temperature will influence the temperature profile through the entire hot rolling stage. A potential application of the model is to reduce the variation of mechanical properties. To demonstrate a possible application of this model, it was shown that variations in chemical composition observed in the as-received dataset will lead to mechanical property variations, but these can be countered by modifying the hot rolling process details, thus reducing mechanical property variations
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".