Constitutive Model of TNM Alloy Using Arrhenius-Type Model and Artificial Neural Network Model. Issue 1 (1st January 2023)

• Record Type: Journal Article
• Authors: Zhou, Yaoqing; Yang, Gang; He, Xiaomao; Zhou, LeYu; Zhai, Yuewen
• Is Part Of: Journal of physics. Volume 2437 Issue 1(2023)
• Publication Date: 2023-01-01
• Subjects: TNM alloy -- Arrhenius-Type model -- BP neural network model -- High-temperature flow behavior; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2437/1/012062
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: TNM alloys are frequently employed in automotive and aeronautical applications. Hot compression experiments on a Gleeble-3800 testing apparatus were conducted at a range of temperatures (1150°C–1250°C) and strain rates (0.001s-1 - 1s-1) to investigate the high temperature deformation behavior of TNM alloys. The complex deformation mechanisms of TNM alloys at various temperatures and strain rates were studied using the experimentally discovered true stress-true strain curves. The constitutive relationships between deformation parameters and flow stresses were constructed using two methods, Arrhenius model and neural network model respectively. The results demonstrated that the correlation coefficient R and root mean square error (RSME) achieved by BPNN are, respectively, 0.9982 and 4.7784, and are notably better than those anticipated by the Arrhenius-type model. In terms of the distribution of relative errors, the BPNN findings are similarly more concentrated, and the bulk of them fall inside the 10% range. Therefore, the BP neural network is a useful tool for forecasting the elevated temperature flow behavior of TNM alloys.