Springback analysis in bending through finite element method based artificial neural networks

Download
2013
Şenol, Özgü
Springback prediction is vital in order to obtain the desired part shape in metal forming processes. In most of the applications, springback amount is determined by trial and error procedures, and recently by using numerical methods or through handbook tables. Artificial Neural Network (ANN) is a helpful tool for the engineers and applied in this study to determine the springback amounts in air, V-die and wipe bending processes. For this purpose, bending processes are analyzed by commercial finite element (FE) software and springback amounts are collected for different parameters such as thickness, die radius, bending angle, etc. Then, by developing a feedforward neural network with backpropagation learning algorithm, the springback amounts for bending applications are determined. ANN results of three bending operations are combined to analyze an industrial workpiece. In addition to this, an experimental bending operation is analyzed for air bending process. It is shown that ANN can be effectively applied to determine springback amount in air, V-die and wipe bending.

Suggestions

Springback analysis in air bending process through experiment based artificial neural networks
Senol, Ozgu; Esat, Volkan; Darendeliler, Haluk (2014-10-24)
Sheet metal bending is one of the most frequently used sheet metal forming processes in manufacturing industry. This study investigates bending parameters and springback phenomenon of a stainless-steel sheet in air bending process. In most of the applications, springback is determined either by trial and error procedures or by using numerical methods. Artificial Neural Network (ANN) approach has proved to be a helpful tool for the engineers. ANN is used in this study to predict the springback amounts of sta...
Effect of hardening models on different ductile fracture criteria in sheet metal forming
Dizaji, Shahram Abbasnejad; Darendeliler, Haluk; KAFTANOĞLU, BİLGİN (2016-07-01)
Prediction of the fracture is one of the challenging issues which gains attention in sheet metal forming as numerical analyses are being extensively used to simulate the process. To have better results in predicting the sheet metal fracture, appropriate ductile fracture criterion (DFC), yield criterion and hardening rule should be chosen. In this study, the effects of different hardening models namely isotropic, kinematic and combined hardening rules on the various uncoupled ductile fracture criteria are in...
Numerical analysis of thermo-mechanical behavior in flow forming
Günay, Enes; Fenercioglu, Tevfik Ozan; Yalçınkaya, Tuncay (2021-01-01)
Flow forming is a metal forming process for cylindrical workpieces where high velocity deformation leads to radial thinning and axial extension. In the current study, a thermomechanical, dynamic and explicit finite element model of a flow forming process is developed on ABAQUS software. The model is validated through the comparison of reaction forces and geometry obtained from the experiments. Coolant convection effect is analyzed in conjunction with roller and mandrel conduction cooling to study the therma...
Mixed mode fatigue crack growth path and life prediction under variable amplitude loading through extended finite element method
Dirik, Haydar; Yalçınkaya, Tuncay; Department of Aerospace Engineering (2017)
The main purpose of this study is to predict the crack growth path trajectories and fatigue crack growth (FCG) life under variable amplitude loading (VAL) by using Extended Finite Element Method (XFEM). For this purpose a computational algo- rithm is developed in Fortran which interacts with a commercial finite element soft- ware (Abaqus) and automatically propagates cracks which is initially modelled as stationary crack. Nasgro FCG equation is used for FCG life calculation which has a great accuracy among t...
Powder metal development for electrical motor applications
Bayramli, E; Golgelioglu, O; Ertan, Hulusi Bülent (2005-04-10)
In this paper, first the development process of a soft magnetic composite material for use in motor applications is described. Various mixtures are prepared to identify an optimum mix. It is found that highest packing is achieved for a mixing ratio of 45 % of 170 mesh particle size with 55 % 325 mesh particle size. The coating of the particles is obtained by using the "wetting method". The mechanical properties of the samples; such as stress versus strain, Strain% versus composition%, etc. are given, also s...
Citation Formats
Ö. Şenol, “Springback analysis in bending through finite element method based artificial neural networks,” M.S. - Master of Science, Middle East Technical University, 2013.