Modelling of the Steel High-Temperature Deformation Behaviour Using Artificial Neural Network

Abstract

Hot forming is an essential part of the manufacturing of most steel products. The hot deformation behaviour is determined by temperature, strain rate, strain and chemical composition of the steel. To date, constitutive models are constructed for many steels; however, their specific chemical composition limits their application. In this paper, a novel artificial neural network (ANN) model was built to determine the steel flow stress with high accuracy in the wide range of the concentration of the elements in high-alloyed, corrosion-resistant steels. The additional compression tests for stainless Cr12Ni3Cu steel were carried out at the strain rates of 0.1–10 s−1 and the temperatures of 900–1200 °C using thermomechanical simulator Gleeble 3800. The ANN-based model showed high accuracy for both training (the error was 6.6%) and approvement (11.5%) datasets. The values of the effective activation energy for experimental (410 ± 16 kJ/mol) and predicted peak stress values (380 ± 29 kJ/mol) are in good agreement. The implementation of the constructed ANN-based model showed a significant influence of the Cr12Ni3Cu chemical composition variation within the grade on the flow stress at a steady state of the hot deformation.

Artificial Neural Network Modelling of the Effect of Vanadium Addition on the Tensile Properties and Microstructure of High-Strength Tempcore Rebars

“…ANN is a statistical learning algorithm that simplifies and mimics a biological nervous system such as the brain [ 25 ]. Multi-layered perceptron (MLP) is the ANN structure mostly used to determine the approximation of a function; Figure 1 shows the architecture of a typical MLP structure.…”

“…Recently, artificial neural network (ANN) modelling, which is based on learning the relationships between the input and output parameter for complex problems, has been applied to predict and analyse various material phenomena [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 ]. The most remarkable feature of ANN modelling is the understanding of relationships using input and output data, and it can be implemented if there is sufficient learnable parameter data.…”

Automatic Featurization Aided Data-Driven Method for Estimating the Presence of Intermetallic Phase in Multi-Principal Element Alloys

“…In this new era of informatics where machine learning and artifical intelligence can be found being used ubiquitously in almost every field of research and development, the material science community is also gearing up with the trend of these new state-ofthe-art technologies to accelerate materials design and discovery. Especially, artificial neural network (ANN) has been very popular in the composition-based and mechanical property-based design of alloys [6,7]. Different statistical tools and machine learning tools are being used by many research works for the general phase classification of the HEAs [8].…”

Prediction of the Sound Absorption Coefficient of Three-Layer Aluminum Foam by Hybrid Neural Network Optimization Algorithm

“…With the development of intelligent algorithms and neural networks, more and more researchers are choosing neural networks to predict the acoustic properties of materials. Artificial neural networks (ANN) [ 22 , 23 , 24 , 25 , 26 , 27 ], radial basis function neural networks (RBF) [ 9 ], and generalized regression neural networks (GRNN) [ 28 ], are commonly used to predict sound absorption coefficients.…”