Abstract
Warm stamping techniques have been employed to solve the formability problem in forming aluminium alloy panels. The formability of sheet metal is a crucial measure of its ability for forming complex-shaped panel components and is often evaluated by forming limit diagram (FLD). Although the forming limit is a simple tool to predict the formability of material, determining FLD experimentally at warm/hot forming condition is quite difficult. This paper presents the artificial neural network (ANN) modelling of the process based on experimental results (different temperature, 20°C-300°C and different forming rates, 5-300 mm.s-1) is introduced to predict FLDs. It is shown that the ANN can predict the FLDs at extreme conditions, which are out of the defined boundaries for training the ANN. According to comparisons, there is a good agreement between experimental and neural network results
| Original language | English |
|---|---|
| Pages (from-to) | 770-778 |
| Number of pages | 9 |
| Journal | Key Engineering Materials |
| Volume | 716 |
| Early online date | 17 Oct 2016 |
| DOIs | |
| Publication status | E-pub ahead of print - 17 Oct 2016 |
| Event | Metal Forming - 16th International Conference - AGH University of Science and Technology, Kraków, Poland Duration: 18 Sept 2016 → 21 Sept 2016 http://metalforming2016.jordan.pl/ |
Keywords
- aluminium alloys
- warm forming
- forming limit diagram (FLD),
- artificial neural network (ANN)