High-Temperature Deformation Constitutive Model of Zircaloy-4 Based on the Support Vector Regression Algorithm during Hot Rolling
Due to the small range of plastic deformation temperatures during hot rolling of Zircaloy-4 plates, it is important to determine the appropriate flow behaviors for plate profile control of Zircaloy-4 plates. The developed microstructures and mechanical properties of Zircaloy-4 are evaluated by metal...
Saved in:
| Published in: | Journal of materials engineering and performance Vol. 31; no. 12; pp. 10237 - 10247 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
Springer US
01.12.2022
|
| Subjects: | |
| ISSN: | 1059-9495, 1544-1024 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Due to the small range of plastic deformation temperatures during hot rolling of Zircaloy-4 plates, it is important to determine the appropriate flow behaviors for plate profile control of Zircaloy-4 plates. The developed microstructures and mechanical properties of Zircaloy-4 are evaluated by metallographic observations and Gleeble-3800 thermal simulation tester. To meet the need of data with small-sample properties, the support vector regression (SVR) algorithm is adopted to predict the constitutive model of Zircaloy-4, and the improved particle swarm optimization algorithm (IPSO) is used to optimize parameters of SVR algorithm. Meanwhile, results indicate that the correlation coefficient (
R
2
) value of zirconium alloy constitutive model is 96.805%. Based on employed algorithm, comparing with modified Arrhenius model, the results show the superiority of IPSO-SVR algorithm. This provides an important theoretical basis for FE simulation of controlling the Zircaloy-4 plate shape during hot rolling process. |
|---|---|
| ISSN: | 1059-9495 1544-1024 |
| DOI: | 10.1007/s11665-022-06987-y |