...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>The Journal of Strain Analysis for Engineering Design >Forming and springback prediction in press brake air bending combining finite element analysis and neural networks
【24h】

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

机译：结合有限元分析和神经网络的折弯机弯曲成形和回弹预测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

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.
机译：乍一看，折弯机空气弯曲是一种通过钣金成型获得产品的过程，乍一看可以认为是一个简单的几何问题。但是，获得的几何形状的精度涉及直接与工具和加工参数以及钣金材料和尺寸相关的多个参数的组合。本文介绍的主要主题涉及预测冲头位移过程参数的能力，该参数可使产品在折弯机空气弯曲中准确成形为所需的弯曲角度。在我们的方法中，将成型过程和弹性恢复（即回弹效应）分别考虑。折弯机数控系统（计算机数控系统）中的当前解决方案通常由从几何分析得出的分析模型（包括校正因子）进行配置。在我们的方法中，建议将学习工具，人工神经网络的使用与仿真和数据生成工具（有限元分析）结合起来。这种组合可以对成型过程和回弹效果的复杂非线性行为进行建模，包括对所得结果的验证。考虑到不同的工艺参数和工具几何形状的开发模型可以扩展工业领域的实际应用范围。最终解决方案与其并入计算机数控折弯机控制器中是兼容的。结论是，使用这种方法，可以预测弯曲后有效且准确的最终几何形状，这也是向“首次正确使用”解决方案迈出的一步。此外，通过与实验测试的比较，验证了所开发的模型，方法和获得的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号