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

Characterization of Flow Behaviors by a PSO-BP Integrated Model for a Medium Carbon Alloy Steel

In order to characterize the flow behaviors of SAE 5137H steel, isothermal compression tests at the temperatures of 1123 K, 1213 K, 1303 K, 1393 K, and 1483 K, and the strain rates of 0.01 s^-1, 0.1 s^-1, 1 s^-1, and 10 s^-1 were performed using a Gleeble 3500 thermo-mechanical simulator. The analysis results of true stress-strain curves show that the flow stress decreases with temperature increasing and strain rate decreasing. In order to accurately and efficiently characterize the complex flow behaviors, the intelligent learning method backpropagation-artificial neural network (BP-ANN) was combined with the particle swarm optimization (PSO), namely, the PSO-BP integrated model. Detailed comparisons of the semi-physical model with improved Arrhenius-Type, BP-ANN, and PSO-BP integrated model for the flow behaviors of SAE 5137H steel in terms of generative ability, predictive ability, and modeling efficiency were presented. The comparison results show that the PSO-BP integrated model has the best comprehensive ability, BP-ANN is the second, and semi-physical model with improved Arrhenius-Type is the lowest. It indicates that the PSO-BP integrated model can accurately describe the flow behaviors of SAE 5137H steel.

Prediction of True Stress at Hot Deformation of High Manganese Steel by Artificial Neural Network Modeling

The development of new lightweight materials is required for the automotive industry to reduce the impact of carbon dioxide emissions on the environment. The lightweight, high-manganese steels are the prospective alloys for this purpose. Hot deformation is one of the stages of the production of steel. Hot deformation behavior is mainly determined by chemical composition and thermomechanical parameters. In the paper, an artificial neural network (ANN) model with high accuracy was constructed to describe the high Mn steel deformation behavior in dependence on the concentration of the alloying elements (C, Mn, Si, and Al), the deformation temperature, the strain rate, and the strain. The approval compression tests of the Fe-28Mn-8Al-1C were made at temperatures of 900-1150 °C and strain rates of 0.1-10 s^-1 with an application of the Gleeble 3800 thermomechanical simulator. The ANN-based model showed high accuracy, and the low average relative error of calculation for both training (5.4%) and verification (7.5%) datasets supports the high accuracy of the built model. The hot deformation effective activation energy values for predicted (401 ± 5 kJ/mol) and experimental data (385 ± 22 kJ/mol) are in satisfactory accordance, which allows applying the model for the hot deformation analysis of the high-Mn steels with different concentrations of the main alloying elements.

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

The combination of multilayer aluminum foam can have high sound absorption coefficients (SAC) at low and medium frequencies, and predicting its absorption coefficient can help the optimal structural design. In this study, a hybrid EO-GRNN model was proposed for predicting the sound absorption coefficient of the three-layer composite structure of the aluminum foam. The generalized regression neural network (GRNN) model was used to predict the sound absorption coefficient of three-layer composite structural aluminum foam due to its outstanding nonlinear problem-handling capability. An equilibrium optimization (EO) algorithm was used to determine the parameters in the neuronal network. The prediction results show that this method has good accuracy and high precision. The calculation result shows that this proposed hybrid model outperforms the single GRNN model, the GRNN model optimized by PSO (PSO-GRNN), and the GRNN model optimized by FOA(FOA-GRNN). The prediction results are expressed in terms of root mean square error (RMSE), absolute error, and relative error, and this method performs well with an average RMSE of only 0.011.