Forming and springback prediction in press brake air bending combining finite element analysis and neural networks

2018 ◽  
Vol 53 (8) ◽  
pp. 584-601 ◽  
Author(s):  
Sara S Miranda ◽  
Manuel R Barbosa ◽  
Abel D Santos ◽  
J Bessa Pacheco ◽  
Rui L Amaral
Keyword(s):  
Neural Networks ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Sheet Metal ◽  
Computer Numerical Control ◽  
Numerical Control ◽  
Forming Process ◽  
Element Analysis ◽  
Air Bending ◽  
Springback Prediction

Press brake air bending, a process of obtaining products by sheet metal forming, can be considered at first sight a simple geometric problem. However the accuracy of the obtained geometries involves the combination of multiple parameters directly associated with the tools and the processing parameters, as well as with the sheet metal materials and dimensions. The main topic herein presented deals with the capability of predicting the punch displacement process parameter that enables the product to be accurately shaped to a desired bending angle, in press brake air bending. In our approach, it is considered separately the forming process and the elastic recovery (i.e. the springback effect). Current solutions in press brake numerical control (computer numerical control) are normally configured by analytical models developed from geometrical analysis and including correcting factors. In our approach, it is proposed to combine the use of a learning tool, artificial neural networks, with a simulation and data generation tool (finite element analysis). This combination enables modeling the complex nonlinear behavior of the forming process and springback effect, including the validation of results obtained. A developed model taking into account different process parameters and tool geometries allow extending the range of applications with practical interest in industry. The final solution is compatible with its incorporation in a computer numerical control press brake controller. It was concluded that, using this methodology, it is possible to predict efficient and accurate final geometries after bending, being also a step forward to a “first time right” solution. In addition, the developed models, methodologies and obtained results were validated by comparison with experimental tests.

A Study on the Nose Radius Influence in Press Brake Bending Operations by Finite Element Analysis

2013 ◽  
Vol 554-557 ◽  
pp. 1432-1442 ◽  
Author(s):  
J. Bessa Pacheco ◽  
Abel D. Santos
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Sheet Metal ◽  
Computer Control ◽  
Nose Radius ◽  
Forming Process ◽  
Element Analysis ◽  
Bending Angle ◽  
Air Bending ◽  
Bending Radius

The sheet metal bending is one of the metal forming processes with the simplest geometric interpretation and usually a 2D analysis is considered. The bend over a sheet metal blank consists of a V shape forming by using a punch, with a certain nose radius, forcing the plate against an open die, with a V section. The forming result is a part with an angle obtained between the V legs, flanges, which is known as bending angle. The operation to get the required V angle is called air bending, or free bending. The most common used machines for this forming process are press brakes, special long presses, where the tools, punch and die, are attached to. With the spread use of CNC machines, and their computer control capabilities, most of them using graphical user interface (GUI), became important to get the required shape at first trial. Beyond the required bending angle obtained with just one hit, it is also important to position the gauge system in order to get the successive flange lengths to complete the programmed shape. The main variables controlled by the CNC are the punch penetration inside the die and the position of the back gauge, which is determined by the bend allowance. However this penetration is not the only responsible for the resulting bending angle and the gauging position is not the only responsible for the flange length. Additionally, the radius inside the V shape edge, known as bending radius, influences the geometry and correspondingly the bend allowance. Some authors believe that the punch nose radius has direct influence, both in the bending angle and bend allowance. In this paper, results are presented describing the use of finite element analysis as an aid in the prediction of the inside bending radius, that influences both punch penetration for the final bending angle and the bend allowance for the final flange length. From the air bending analysis, a natural inside bending radius is presented as an important variable in these kind of processes, as well as its minor dependence on the punch nose radius.

Sheet Metals Forming Die Design Using Finite Element Analysis and the Taguchi Method

2014 ◽  
Vol 621 ◽  
pp. 195-201
Author(s):  
Surangsee Dechjarern ◽  
Maitri Kamonrattanapisut
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Friction Coefficient ◽  
Taguchi Method ◽  
Finite Element Model ◽  
Sheet Metal ◽  
Element Model ◽  
Die Design ◽  
Forming Process ◽  
Element Analysis

Sheet metal deep-draw die is primarily constructed with draw bead, which is then modified based on trial and error to obtain a successful forming without splitting. This work aims at a robust design of forming die using numerical analysis and the Taguchi method. A three dimensional elastoplastic finite element model of a sheet metal forming process of SPCEN steel has been successfully developed using the material flow stress obtained from the modified Erichsen cup test. The model was validated with the actual forming experiment and the results agreed well. The influence of draw bead parameters on splitting and thinning distributions were examined using the Taguchi method. Four parameters, namely the friction coefficient, draw bead height, radius and shoulder radius were investigated. The Taguchi main effect analysis and ANOVA results show that the height and shoulder radius of the draw bead are the most important factor influencing the thinning distribution. Applying the Taguchi method and using the minimum thinning percentage as the design criteria, the optimum die design was identified as height, radius, shoulder radius and the friction coefficient of 4, 8, 8 mm and 0.125 respectively. The verified finite element model using the optimum die design was conducted. The predicted Taguchi response was within 5.9% from finite element analysis prediction. The improvement in the reduction of thinning percentage was 22.35%.

scholarly journals Experimental And Theoretical Determination Of Forming Limit Curve

2015 ◽  
Vol 60 (3) ◽  
pp. 1881-1886
Author(s):  
J. Adamus ◽  
K. Dyja ◽  
M. Motyka
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Sheet Metal ◽  
Sheet Metal Forming ◽  
Metal Forming ◽  
Fracture Initiation ◽  
Forming Limit ◽  
Forming Process ◽  
Element Analysis ◽  
Metal Forming Process

Abstract The paper presents a method for determining forming limit curves based on a combination of experiments with finite element analysis. In the experiment a set of 6 samples with different geometries underwent plastic deformation in stretch forming till the appearance of fracture. The heights of the stamped parts at fracture moment were measured. The sheet - metal forming process for each sample was numerically simulated using Finite Element Analysis (FEA). The values of the calculated plastic strains at the moment when the simulated cup reaches the height of the real cup at fracture initiation were marked on the FLC. FLCs for stainless steel sheets: ASM 5504, 5596 and 5599 have been determined. The resultant FLCs are then used in the numerical simulations of sheet - metal forming. A comparison between the strains in the numerically simulated drawn - parts and limit strains gives the information if the sheet - metal forming process was designed properly.

Finite Element Analysis of Origami-Based Sheet Metal Folding Process

2016 ◽  
Author(s):  
Muhammad Ali Ablat ◽  
Ala Qattawi
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Sheet Metal ◽  
High Stress ◽  
Final Part ◽  
Isotropic Hardening ◽  
Forming Process ◽  
Element Analysis ◽  
Folding Process ◽  
Bending Force

There are challenges in the conventional sheet metal folding for mass production; those are summarized by high tooling and energy costs and lack of dimensional accuracy. High cost per product is due to the need of specific manufacturing tools and equipment like dies and molds that are shape dedicated to certain product range and specifications. Lack of high accuracy is resulted from involved forming process, machine structure and springback effects in workpiece. Origami-based Sheet Metal (OSM) folding fabrication process has been utilized to overcome these challenges. This novel approach is an extension of the origami technique to sheet metal folding process and it requires creating numerous features along the bend line, called Material Discontinuities (MD). MD are fabricated by removal of material completely or partially through thickness direction of sheet metal along the bend line using laser cutting process or progressive stamping. MD can also be created by stamping where no material removal is present, rather stamping creates deformed pattern along the bend line to guide the folding. MD controls the material deformation during bending and results in reduced bending force, minimal tooling and machinery requirements. Despite the promising potential of OSM, there is little understating of the effect of the selected MD shape and geometry on the final workpiece, specifically this is of interest when comparing the energy and cost allocations for OSM with a well-establish process for sheet metal such as stamping. In this work, the effect of several types of MD on sheet metal folding process is investigated using Finite Element Analysis (FEA). In particular, wiping die bending of aluminum sheet with different MD shapes and geometries along the bend line is compared to the traditional sheet bending of final part in terms of stress distribution along the bending line and required bending force. FE simulations are carried out using structural and thermo-mechanical FE solver Code_Aster. Aluminum 2036-T4 is chosen as sheet metal material. Constitutive model in the simulation is J2 flow theory plasticity with isotropic hardening. The FEA results are validated by comparing it to the available empirical models in terms of bending forces. This study finds that the OSM technique reduced the required bending force significantly, which has important significance in energy and cost reduction. It also ranked the MD in terms of the required force to bend the same sheet metal type and thickness for further future investigation. However, the MD leads to localized high stress regions along the bending line, which may affect load-bearing capability of the final part. In addition, it may lead to cracks or fractures of sheet metal part in the high stress region, especially if MD are densely arranged along the bend line.

Finite Element Analysis of Reinforcement Rocker Part Made from JAC780Y Steel Sheets

2021 ◽  
Vol 877 ◽  
pp. 83-89
Author(s):  
Aeksuwat Nakwattanaset ◽  
Surasak Suranuntchai
Keyword(s):  
Finite Element ◽  
Sheet Metal ◽  
High Strength Steel ◽  
High Strength ◽  
Material Model ◽  
Advanced High Strength Steel ◽  
Forming Process ◽  
Element Analysis ◽  
Steel Sheets ◽  
Springback Prediction

The manufacturing industries for automotive parts aim to develop technologies for reducing vehicle weight in order to decrease fuel consumption. However, passive safety function for drivers and passengers must not be impaired or should be even improved. Therefore, advanced high strength steel sheet plays more and more important role in designing automotive components. Nowadays, prediction of formability for sheet metal stamping has high capability more than the past. The major challenge is springback prediction. Moreover, it assists in the tooling design to correctly compensate for springback. Especially in automotive production, springback effects have been generally exhibited distinct after forming process of the high strength steel sheets. The springback effect occurred in the deformed state of metal parts must be taken into account by designing any sheet metal panels. Then, the purpose of the present research is to investigate the springback phenomenon of an automotive part named Reinforcement Rocker RL made from an advanced high strength steel grade JAC780Y, after stamping. In addition, the tools design has been carried out. Finite Element (FE) program known as DYNAFORM (based on LS-DYNA solver), has been applied to analyze and improve the springback effect on such forming part. An anisotropic material model according to type 36 (MAT_036 3-PARAMETER_BARAT) was applied. The results obtained from simulations were compared with required parts in each section. Then, the die surface from compensation in 2nd step forming was modified to use. Finally, the simulation part was verified with the real stamping part. It was found that the finite element simulation showed high capability for prediction and compensation of springback in high strength steel sheets forming.

scholarly journals A Machine Learning Approach as a Surrogate for a Finite Element Analysis: Status of Research and Application to One Dimensional Systems

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1654
Author(s):  
Poojitha Vurtur Badarinath ◽  
Maria Chierichetti ◽  
Fatemeh Davoudi Kakhki
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Stress Distribution ◽  
Maintenance Scheduling ◽  
Element Analysis ◽  
One Dimensional ◽  
Artificial Neural

Current maintenance intervals of mechanical systems are scheduled a priori based on the life of the system, resulting in expensive maintenance scheduling, and often undermining the safety of passengers. Going forward, the actual usage of a vehicle will be used to predict stresses in its structure, and therefore, to define a specific maintenance scheduling. Machine learning (ML) algorithms can be used to map a reduced set of data coming from real-time measurements of a structure into a detailed/high-fidelity finite element analysis (FEA) model of the same system. As a result, the FEA-based ML approach will directly estimate the stress distribution over the entire system during operations, thus improving the ability to define ad-hoc, safe, and efficient maintenance procedures. The paper initially presents a review of the current state-of-the-art of ML methods applied to finite elements. A surrogate finite element approach based on ML algorithms is also proposed to estimate the time-varying response of a one-dimensional beam. Several ML regression models, such as decision trees and artificial neural networks, have been developed, and their performance is compared for direct estimation of the stress distribution over a beam structure. The surrogate finite element models based on ML algorithms are able to estimate the response of the beam accurately, with artificial neural networks providing more accurate results.

Sign in / Sign up

Export Citation Format

Share Document