Microstructure prediction in low and high strain deformation of Al6063 using artificial neural network and finite element simulation

被引:0
作者
Carlos Montenegro
Sepideh Abolghasem
Juan Camilo Osorio-Pinzon
Juan Pablo Casas-Rodriguez
机构
[1] Universidad de los Andes,Department of Mechanical Engineering
[2] Universidad de los Andes,Department of Industrial Engineering
来源
The International Journal of Advanced Manufacturing Technology | 2020年 / 106卷
关键词
Microstructure; Deformation; Finite element; Neural network; Back propagation;
D O I
暂无
中图分类号
学科分类号
摘要
The final microstructure of materials under interactive effects of critical elements of deformation: strain, strain-rate, and temperature, often follows complex trajectories. Capturing the existing process-structure linkages is fundamental for controlling product outcomes, yet it calls for establishing the constitutive relationships that describe material behavior. In this paper, a backpropagation Artificial Neural Network (ANN) is proposed for microstructure prediction for a wide range of strain, strain-rate, and temperature conditions. Microstructural changes in Al6063 are experimentally examined using (i) quasi-static universal testing apparatus, Drop Weight Impact Tester (DWIT), and Split Hopkinson Pressure Bar (SHPB) tests for low strain regimes at elevated temperatures, and (ii) Plane Strain Machining (PSM) for high strain, high strain-rate, and the accompanied temperature rise conditions. Two ANNs are established to predict microstructure responses, grain and subgrain sizes, in low and high strain regimes, respectively. Additionally, the stress-strain results obtained from the low strain regime are used to calculate the Johnson–Cook (J-C) material model constants, which are then incorporated in the finite element (FE) simulation along with the developed ANN algorithm, to predict microstructure response for different cutting conditions. The performance of the ANNs and the FE simulations was evaluated using statistical indices. The comparative assessment of the models’ outcomes indicates close agreements with the experimental results in both low- and high-level deformations. The accurate predictions from PSM conditions can potentially be applicable for microstructural prediction of the machined surface.
引用
收藏
页码:2101 / 2117
页数:16
相关论文
共 50 条
[41]   A Surrogate Model for Wave Prediction Based on an Artificial Neural Network Using High-fidelity Synthetic Hurricane Modelling [J].
Mun, Jongyoon ;
Kim, Seung-Woo ;
Melby, Jeffrey A. .
JOURNAL OF COASTAL RESEARCH, 2018, :876-880
[42]   Simulation of Material Stress-Strain Curve and Creep Deformation Response of Nickel Based Superalloys Using Crystal Plasticity Based Finite Element Models [J].
Samal, M. K. .
TRANSACTIONS OF THE INDIAN INSTITUTE OF METALS, 2016, 69 (04) :949-960
[43]   Prediction of static recrystallization in a multi-pass hot deformed low-alloy steel using artificial neural network [J].
Lin, Y. C. ;
Liu, Ge ;
Chen, Ming-Song ;
Zhong, Jue .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2009, 209 (09) :4611-4616
[44]   Thermal performance prediction of wickless heat pipe with Al2O3/water nanofluid using artificial neural network [J].
Kahani, Mostafa ;
Vatankhah, Gholamhossein .
CHEMICAL ENGINEERING COMMUNICATIONS, 2019, 206 (04) :509-523
[45]   Prediction of wear rates of Al-TiO2 nanocomposites using artificial neural network modified with particle swarm optimization algorithm [J].
Najjar, Ismail ;
Sadoun, Ayman ;
Alam, M. N. ;
Fathy, Adel .
MATERIALS TODAY COMMUNICATIONS, 2023, 35
[46]   Determining Optimum Butt-Welding Parameters of 304 Stainless-Steel Plates Using Finite Element, Particle Swarm and Artificial Neural Network [J].
Mohammadi, Masoud ;
Golabi, Sa'id ;
Amirsalari, Behzad .
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF MECHANICAL ENGINEERING, 2021, 45 (03) :787-800
[47]   Determining Optimum Butt-Welding Parameters of 304 Stainless-Steel Plates Using Finite Element, Particle Swarm and Artificial Neural Network [J].
Masoud Mohammadi ;
Sa’id Golabi ;
Behzad Amirsalari .
Iranian Journal of Science and Technology, Transactions of Mechanical Engineering, 2021, 45 :787-800
[48]   A comparative study on phenomenological and artificial neural network models for high temperature flow behavior prediction in Ti6Al4V alloy [J].
Uz, Murat Mert ;
Yoruc, Afife Binnaz Hazar ;
Cokgunlu, Okan ;
Aydogan, Cahit Sertac ;
Yapici, Guney Guven .
MATERIALS TODAY COMMUNICATIONS, 2022, 33
[49]   Integrated finite element and artificial neural network methods for constructing asphalt concrete dynamic modulus master curve using deflection time-history data [J].
Hamim, Asmah ;
Yusoff, Nur Izzi Md ;
Omar, Hend Ali ;
Jamaludin, Nor Azliana Akmal ;
Hassan, Norhidayah Abdul ;
El-Shafie, Ahmed ;
Ceylan, Halil .
CONSTRUCTION AND BUILDING MATERIALS, 2020, 257
[50]   Analysis and prediction of slurry erosion wear response of silicon carbide reinforced Al2124 composite using Taguchi - artificial neural network approach [J].
Annamalai, S. ;
Anand Ronald, B. ;
Mohamed Ameer Batcha, S. .
MATERIALWISSENSCHAFT UND WERKSTOFFTECHNIK, 2025, 56 (03) :399-418