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

Published on Mar 12, 2016in Journal of Mechanical Science and Technology1.345
· DOI :10.1007/S12206-016-0227-1
Jaehyeok Doh5
Estimated H-index: 5
(Yonsei University),
Seung Uk Lee6
Estimated H-index: 6
,
Jongsoo Lee17
Estimated H-index: 17
(Yonsei University)
Sources
Abstract
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.
📖 Papers frequently viewed together
6 Authors (Yuyao Sun, ..., Y.G. Zhou)
43 Citations
103 Citations
10 Citations
References12
Newest
#1Hong Chul Hyun (Sogang University)H-Index: 7
#2Minsoo Kim (Sogang University)H-Index: 8
Last. Hyungyil Lee (Sogang University)H-Index: 21
view all 4 authors...
In this study, we obtain true stress–strain (SS) curves for a sheet specimen under consideration of local necking and material anisotropy. We first extract the SS curve up to the diffuse necking point from the tensile test load–displacement data. The curve's part after the onset of diffuse necking is extrapolated by the weighted-average method proposed by Ling [Y. Ling, AMP J. Technol . 5 , 37–48 (1996)]. Initiation of local necking is predicted by means of the minor-to-major strain ratio in the...
19 CitationsSource
#1M. El-ZeghayarH-Index: 2
#1M. El-ZeghayarH-Index: 1
Last. R. SohmshettyH-Index: 1
view all 4 authors...
Dual phase 590 steel belongs to the family of advanced high strength steels (AHSS) that has gained popularity in the automotive industry as lightweight vehicle components. An experimental study on dual phase (DP) 590 as-received steel was conducted to study the effect of variable amplitude loading on the fatigue life and construct the effective strain-life curve for the material. Overloads were applied in the form of large near yield stress cycles that decreased the crack opening stress for the ...
1 Citations
#1Hyun-Kyu Kim (Samsung)H-Index: 3
#1H Kim (Samsung)H-Index: 1
Last. Jongsoo LeeH-Index: 17
view all 2 authors...
This article investigates an optimal design for a paper-feeding system that minimizes both jamming and simultaneous feeding of multiple papers, hereafter referred to as the multi-feeding rate. A total of 11 design parameters for the paper transfer device, the paper separation device, and the paper guide path are selected and analysed in this study. A test jig for feeding and transferring papers is manufactured to obtain experimental data for use in parameter analysis and design optimization. Bac...
4 CitationsSource
In this work, we investigated the theoretical forming limit models for Zircaloy-4 and Zirlo used for spacer grid of nuclear fuel rods. Tensile and anisotropy tests were performed to obtain stress-strain curves and anisotropic coefficients. The experimental forming limit diagrams (FLD) for two materials were obtained by dome stretching tests following NUMISHEET 96. Theoretical FLD depends on FL models and yield criteria. To obtain the right hand side (RHS) of FLD, we applied the FL models (Swift'...
7 CitationsSource
#1Pyokyoung Han (Yonsei University)H-Index: 1
#2Jongsoo Lee (Yonsei University)H-Index: 17
When a traditional response surface method (RSM) is used as a meta-model for inequality constraint functions, an approximate optimal solution is sometimes actually infeasible in a case where it is active at the constraint boundary. The paper proposes a new RSM that ensures the constraint feasibility with respect to an approximate optimal solution. Constraint-shifting is suggested in order to secure the constraint feasibility during the sequential approximate optimization process. A central compo...
2 CitationsSource
Stress-strain curves based on Ramberg-Osgood and Hollomon relations are strongly dependent upon the regressed range of strain. This work investigates mathematical expressions of true stress-strain curves of metallic materials. We first observe the variation of yield strength, strain hardening exponent and stress-strain curve with regressed range of stain. Based on sectional regression and expression using one or two parameters, we propose an optimal strain range for which yield strength and nonl...
12 CitationsSource
#1Jongsoo Lee (Yonsei University)H-Index: 17
#2Heeseok Jeong (Yonsei University)H-Index: 3
Last. Dimitri N. Mavris (Georgia Institute of Technology)H-Index: 32
view all 5 authors...
Back-propagation neural networks (BPN) have been extensively used as global approximation tools in the context of approximate optimization. A traditional BPN is normally trained by minimizing the absolute difference between target outputs and approximate outputs. When BPN is used as a meta-model for inequality constraint function, approximate optimal solutions are sometimes actually infeasible in a case where they are active at the constraint boundary. The paper explores the development of the e...
22 CitationsSource
#1Rob J. Hyndman (Monash University)H-Index: 58
#2Anne B. Koehler (Miami University)H-Index: 20
We discuss and compare measures of accuracy of univariate time series forecasts. The methods used in the M-competition and the M3-competition, and many of the measures recommended by previous authors on this topic, are found to be inadequate, and many of them are degenerate in commonly occurring situations. Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
3,320 CitationsSource
#1H. Sudarsana Rao (Jawaharlal Nehru Technological University, Hyderabad)H-Index: 4
#2Vaishali G. Ghorpade (Jawaharlal Nehru Technological University, Hyderabad)H-Index: 3
Last. Abhijit Mukherjee (IITB: Indian Institute of Technology Bombay)H-Index: 61
view all 3 authors...
Ceramic-matrix-composites (CMCs) are fast replacing other materials in many applications where the higher production costs can be offset by significant improvement in performance. In applications such as cutting and forming tools, wear parts in machinery, nozzles, valve seals and bearings, improvement in toughness and hardness translate into longer life. However, the recent resurgence in the field of development of CMCs has been due to their potential use for the Space Transport systems, Combust...
15 CitationsSource
#1Yun LingH-Index: 1
#2Amp IncorporatedH-Index: 1
A weighted-average method for determining uniaxial, true tensile stress vs. strain relation after necking is presented for strip shaped samples. The method requires identification of a lower and an upper bound for the true stress-strain function after necking and expresses the true stress-strain relation as the weighted average of these two bounds. The weight factor is determined iteratively by a finite element model until best agreement between calculated and experimental loadextension curves i...
188 Citations
Cited By10
Newest
#1Hailong Shao (Yonsei University)
#2Jongsoo Lee (Yonsei University)H-Index: 17
This study proposes an optimal design of a dolphin structure under offshore load conditions such as berthing, mooring, wind, wave, and current loads. The design objective is to reduce the total wei...
Source
#1Jaehyeok DohH-Index: 5
#2Su Haeng HurH-Index: 1
Last. Jongsoo LeeH-Index: 17
view all 3 authors...
1 CitationsSource
#1Jaehyeok Doh (Yonsei University)H-Index: 5
#2Sang-Woo Kim (Hyundai Motor Group)H-Index: 1
Last. Jongsoo Lee (Yonsei University)H-Index: 17
view all 3 authors...
This study focuses on the design of polymer components considering their degradation under designed operating conditions in automobiles. We use stochastic and statistical methods to ensure that suc...
Source
#1Jung Chu Ting (NCUE: National Changhua University of Education)H-Index: 2
#2Der-Fa Chen (NCUE: National Changhua University of Education)H-Index: 11
Compared with the classical linear controller, the nonlinear controller can result better control performance for the nonlinear uncertainties of the continuously variable transmission (CVT) system which is spurred by the synchronous reluctance motor (SynRM). The better control performance obtained by use of the proposed novel mingled reformed recurrent Hermite polynomial neural network (MRRHPNN) control system can be presented dynamic behavior for the nonlinear uncertainties of CVT system. The n...
6 CitationsSource
#1Mahmoud Nili (Bu-Ali Sina University)H-Index: 14
#2Alireza Azarioon (Bu-Ali Sina University)H-Index: 2
Last. Ali Deihimi (Bu-Ali Sina University)H-Index: 10
view all 4 authors...
In the present study, the effectiveness of fiber inclusion on enhancing frost durability was experimentally examined. Polypropylene fiber of 0.2, 0.3, 0.4, and 0.5% and steel fiber of 0.2, 0.4, 0.6, 0.8, and 1.0% by volume fraction were used. Additionally, reference and air-entrained specimens (with 5% air content) were prepared to compare the results. The water/cement ratio for all concrete mixtures was 0.465. The compressive and tensile strengths, and longitudinal strains of frost-exposed spec...
10 CitationsSource
#1Jaehyeok Doh (Yonsei University)H-Index: 5
#2Younghoon Kim (Yonsei University)H-Index: 16
Last. Jongsoo Lee (Yonsei University)H-Index: 17
view all 3 authors...
ABSTRACTIn this study, the design optimization of the gap size of annular nuclear fuels used in pressurized water reactors (PWRs) was performed. For this, thermoelastic–plasticity–creep (TEPC) analysis of PWR annular fuels was carried out using an in-house code to investigate the performance of nuclear fuels. Surrogate models based on the kriging and inverse distance weighting models were generated using computational performance data based on optimal Latin hypercube design. Using these surrogat...
6 CitationsSource
#1Zora JančíkováH-Index: 6
#2Pavel KoštialH-Index: 5
Last. Hana ŠpačkováH-Index: 1
view all 9 authors...
Source
#1Ivan RužiakH-Index: 7
#2Pavel Koštial (Technical University of Ostrava)H-Index: 5
Last. Peter Polakovič (Slovak University of Agriculture)H-Index: 3
view all 7 authors...
Artificial neural networks (ANN) have been used for characterization of rubber blend mixtures ageing and for prediction of mechanical properties according to chemical composition. Strength Rm and modulus M100 have been evaluated. The ANN application was tested by statistical function RMSE (root mean square error) and R2 (coefficient of determination) which value for all predictions was higher than 0.93.
3 CitationsSource
#1Mohd. Faridh Ahmad Zaharuddin (Hanyang University)H-Index: 1
#1Mohd Faridh Ahmad Zaharuddin (Hanyang University)H-Index: 1
Last. Sehun Rhee (Hanyang University)H-Index: 8
view all 3 authors...
Artificial intelligence (AI) is a modern approach which has the ability to capture nonlinear relationships and interaction effects. Frequently, AI methods have been used by researchers to predict output responses of the Resistance spot welding (RSW) due to the complex- ity during the welding process and numerous interferential factors, especially the short-time property of the process. The present study is to investigate the weld strength of spot weld for high strength steel sheets of CR780 usin...
16 CitationsSource
Jul 26, 2015 in HiPC (IEEE International Conference on High Performance Computing, Data, and Analytics)
#1Xingxing Zhou (Nanjing Normal University)H-Index: 7
#2Guangshuai Zhang (JLU: Jilin University)H-Index: 4
Last. Yudong Zhang (Nanjing Normal University)H-Index: 73
view all 5 authors...
(Aim) Tea plays a significant role because of its high value throughout the world. Computer vision techniques were successfully employed for rapid identification of teas. (Method) In our work, we present a computer assisted discrimination system on the basis of two steps: (i) two-dimensional wavelet-entropy for feature extraction; (ii) the feedforward Neural Network (FNN) for classification. Specifically, the wavelet entropy features were fed into a FNN classifier. (Results) The 10 runs of 75 im...
9 CitationsSource