Can I read Using FEM and neural network prediction on hydrodynamic deep drawing of T-piece maximum length on EtoBox?

Using FEM and neural network prediction on hydrodynamic deep drawing of T-piece maximum length by J.C. Lin is a scholarly article available to read on EtoBox.

What is Using FEM and neural network prediction on hydrodynamic deep drawing of T-piece maximum length about?

The incremental updated Lagrangian elasto-plastic ÿnite element method and abductive network was applied in this study to analyze hydrodynamic deep drawing of 3D T-piece design. A series of 24 sets of di erent geometry tools were used for a 3D T-piece deep drawing process, with di erence variations in the die radius, material radius and matching the di erent thickness of product. The results of the deep-drawing maximum length from FEM-simulation are then input to a neural network to establish a model for the T-piece deep-drawing variables. The neural network is composed of a number of functional nodes. Once the T-piece control parameters (material thickness, material radius and die radius) are given, the drawing processing performance (deep-drawing maximum length) can be accurately predicted by this developed network. This research achieved a satisfactory result based on demonstration of simulation, proving that it is a new and feasible approach used in control of T-piece drawing process of materials.

Author

J.C. Lin

Publisher

Elsevier Science; Elsevier ; Elsevier BV (ISSN 0168-874X)

Published

2003

Language

EN