| About this Abstract |
| Meeting |
13th International Conference on the Technology of Plasticity (ICTP 2021)
|
| Symposium
|
13th International Conference on the Technology of Plasticity (ICTP 2021)
|
| Presentation Title |
Machine Learning Based Prediction and Compensation of Springback for Tube Bending |
| Author(s) |
Jun Ma, Heng Li, Guang-yao Chen, Torgeir Welo, Guang-jun Li |
| On-Site Speaker (Planned) |
Heng Li |
| Abstract Scope |
Bent tubes are extensively used in the manufacturing industry to meet demands on lightweight and high performance. As one of the most significant phenomena affecting the dimensional accuracy in tube bending, springback causes problems in tube assembly and service, making the manufacturing process complex, time-consuming and difficult to control. This paper attempts to present an accurate, efficient and flexible strategy to control springback based on Machine Learning (ML) modeling. An enhanced PSO-BP network-based ML model is firstly established, providing a strong ability to account for the influences of material, geometry and process parameters on springback. For the supervised learning, training sample data can be collected from the historical production process or, alternatively, finite element simulation and laboratory type experiments. Using cold bending of aluminum tubes as the application case, the ML model is evaluated with high reliability and efficiency in springback prediction and compensation strategy of springback. |
| Proceedings Inclusion? |
Definite: At-meeting proceedings |