Setup of a Parameterized FE Model for the Die Roll Prediction in Fine Blanking using Artificial Neural Networks

Setup of a Parameterized FE Model for the Die Roll Prediction in Fine Blanking using Artificial Neural Networks
复制标题

使用人工神经网络建立用于精冲模滚动预测的参数化有限元模型

DOI:
10.1088/1742-6596/896/1/012096
复制
发表时间:
--
期刊:
Journal of Physics: Conference Series
影响因子:
--
通讯作者:
Klocke
Klocke
中科院分区:
--
文献类型:
--
作者:
Stanke Joachim;Trauth;Daniel;Klocke

文献摘要

参考文献

被引文献

相似文献

模辊是细毛坯剪切边的一种形态特征。模辊减少了剪切边的功能部分。为了补偿模辊,必须使用较厚的金属板和二次加工。然而,为了避免这一现象,人们对各种精冲工艺参数对模辊的影响进行了实验和数值研究,但对某些因素,特别是因素间的交互作用对模辊的影响还缺乏了解。人工智能领域的最新变化促使有限元方法和人工神经网络的混合使用,以解决这些未考虑的参数。因此,首先利用一套经过验证的精冲有限元模型进行模拟,以训练人工神经网络。然后,通过数千次实验对人工神经网络进行训练。因此,这项贡献的目标是开发一种能够可靠地预测模辊的人工神经网络。因此,在这一贡献中,提出了一个完全参数化的2D有限元模型的建立,该模型将用于人工神经网络的批量训练。在16MnCr5的Hensel-Spittel模型(1.7131,AISI/SAE5115)中,有限元模型能够自动改变毛坯凸模和模板的边缘半径、对角力和压边力、板材厚度和零件直径、V形环高度和位置、切割速度以及材料参数。通过实验对有限元模型进行了验证。这一贡献的结果是一个适合进行9.623次模拟的有限元模型,并将模拟的模辊宽度和高度自动传递给人工神经网络。
Die roll is a morphological feature of fine blanked sheared edges. The die roll reduces the functional part of the sheared edge. To compensate for the die roll thicker sheet metal strips and secondary machining must be used. However, in order to avoid this, the influence of various fine blanking process parameters on the die roll has been experimentally and numerically studied, but there is still a lack of knowledge on the effects of some factors and especially factor interactions on the die roll. Recent changes in the field of artificial intelligence motivate the hybrid use of the finite element method and artificial neural networks to account for these non-considered parameters. Therefore, a set of simulations using a validated finite element model of fine blanking is firstly used to train an artificial neural network. Then the artificial neural network is trained with thousands of experimental trials. Thus, the objective of this contribution is to develop an artificial neural network that reliably predicts the die roll. Therefore, in this contribution, the setup of a fully parameterized 2D FE model is presented that will be used for batch training of an artificial neural network. The FE model enables an automatic variation of the edge radii of blank punch and die plate, the counter and blank holder force, the sheet metal thickness and part diameter, V-ring height and position, cutting velocity as well as material parameters covered by the Hensel-Spittel model for 16MnCr5 (1.7131, AISI/SAE 5115). The FE model is validated using experimental trails. The results of this contribution is a FE model suitable to perform 9.623 simulations and to pass the simulated die roll width and height automatically to an artificial neural network.
精冲过程中的 FEM 和 ANN 分析
DOI: --
发表时间: 2010
期刊:
影响因子: --
作者:
F. Djavanroodi;A. Pirgholi;E. Derakhshani
通讯作者: E. Derakhshani
Umformen und Feinschneiden: Handbuch für Verfahren, Stahlwerkstoffe, Teilegestaltung
DOI: --
发表时间: 2006
期刊:
影响因子: --
作者:
R. Schmidt
通讯作者: R. Schmidt