Modeling of Flow Stress of As-Rolled 7075 Aluminum Alloy during Hot Deformation by Artificial Neural Network and Application

• Published in: Journal of materials engineering and performance 2023-06, Vol.32 (12), p.5666-5677
• Main Authors: Yang, Hongbin, Li, Mengnie, Bu, Hengyong, Lu, Xin, Yang, Hongmei, Qian, Zhuo
• Format: Article
• Language: English
• Subjects: Characterization and Evaluation of Materials; Chemistry and Materials Science; Corrosion and Coatings; Engineering Design; Materials Science; Quality Control; Reliability; Safety and Risk; Technical Article; Tribology
• ISSN: 1059-9495; 1544-1024
• DOI: 10.1007/s11665-022-07474-0

To analyze deformation behavior and construct a valid constitutive relationship using an ANN model. Hot compression studies on as-rolled 7075 aluminum alloy were carried out using a TA DIL805 D thermal simulator at a temperature ranging from 573 to 733 K and a strain rate ranging from 0.001 to 1.0 s −1 . Subsequently, the predicted flow stress data were applied to perform finite element simulations of hot compression experiments. The correlation coefficient and error analysis findings reveal that the ANN model has a high prediction accuracy for flow stress. The effective strain distribution in the hot-compressed specimens is not uniform, and it gradually decreases from the center of the deformed specimen to the side and end faces. The uniformity of the effective strain distribution and the tendency of crack generation are influenced by deformation parameters. Within the experimental circumstances of this study, the optimal deformation parameters are obtained, which are the temperature above 653 K and the strain rate between 0.01 and 0.1 s −1 .