Back-propagation neural network-based approximate analysis of true stress-strain behaviors of high-strength metallic material

• Published in: Journal of mechanical science and technology Vol. 30; no. 3; pp. 1233 - 1241
• Main Authors: Doh, Jaehyeok, Lee, Seung Uk, Lee, Jongsoo
• Format: Journal Article
• Language: English
• Published: Seoul Korean Society of Mechanical Engineers 01.03.2016; Springer Nature B.V; 대한기계학회
• Subjects: Approximation; Automotive bodies; Back propagation; Back propagation networks; Chassis; Control; Diffusion; Dynamical Systems; Engineering; Finite difference method; Finite element method; Industrial and Production Engineering; Mathematical analysis; Mathematical models; Mechanical Engineering; Model accuracy; Necking; Neural networks; Plastic properties; Root-mean-square errors; Sensitivity analysis; Stress propagation; Stress-strain curves; Stress-strain relationships; True stress; Vibration; 기계공학; Back-propagation neural network; Meta-model; Diffusion necking; Sensitivity analysis; DP590; Weighted-average method
• ISSN: 1738-494X; 1976-3824
• DOI: 10.1007/s12206-016-0227-1

In this study, a Back-propagation neural network (BPN) is employed to conduct an approximation of a true stress-strain curve using the load-displacement experimental data of DP590, a high-strength material used in automobile bodies and chassis. The optimized interconnection weights are obtained with hidden layers and output layers of the BPN through intelligent learning and training of the experimental data; by using these weights, a mathematical model of the material’s behavior is suggested through this feed-forward neural network. Generally, the material properties from the tensile test cannot be acquired until the fracture regions, since it is difficult to measure the cross-section area of a specimen after diffusion necking. For this reason, the plastic properties of the true stress-strain are extrapolated using the weighted-average method after diffusion necking. The accuracies of BPN-based meta-models for predicting material properties are validated in terms of the Root mean square error (RMSE). By applying the approximate material properties, the reliable finite element solution can be obtained to realize the different shapes of the finite element models. Furthermore, the sensitivity analysis of the approximate meta-model is performed using the first-order approximate derivatives of the BPN and is compared with the results of the finite difference method. In addition, we predict the tension velocity’s effect on the material property through a first-order sensitivity analysis.