Small data-driven modeling of forming force in single point incremental forming using neural networks
- PDF / 1,420,059 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 31 Downloads / 179 Views
ORIGINAL ARTICLE
Small data‑driven modeling of forming force in single point incremental forming using neural networks Zhaobing Liu1,2,3 · Yanle Li4 Received: 21 July 2018 / Accepted: 17 May 2019 © Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract Single point incremental forming (SPIF) has revolutionized sheet shaping for small-batch production, providing an economical and effective alternative to sheet stamping and pressing, which can be cumbersome and expensive. Efficient data-driven prediction of forming forces can significantly benefit process design, development and optimization in SPIF. However, the nature of localized plastic deformation makes SPIF a time-consuming process which means it is difficult to obtain rich experimental data (or samples) in the early period of forming process design. To build an efficient data-driven model for forming force prediction using the back propagation neural networks, this paper proposes a virtual data generation approach based on mega trend diffusion function and particle swarm optimization algorithm to improve the accuracy of SPIF force prediction given small experimental data problems. The proposed modeling methodology is verified using small amount of force data obtained from pyramidal shape forming. It is found that the accuracy of the established prediction model can be improved by adding the generated virtual data to actual experimental small datasets, which provides a good predictive capability in modeling the forming force of SPIF under different process conditions. Keywords Single point incremental forming · Neural networks · Virtual data · Prediction · Forming force
1 Introduction Since the inception in 1990s, Single Point Incremental Forming (SPIF), as an advanced sheet material forming operation, has attracted extensive attentions from both academics and industries due to its intrinsic advantages such as increased formability, reduced tooling cost and process flexibility. To accelerate its practical applications, a number of researchers have performed comprehensive studies trying to improve the process formability, forming accuracy and * Yanle Li [email protected] 1
School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan 430070, China
2
Institute of Advanced Materials and Manufacturing Technology, Wuhan University of Technology, Wuhan 430070, China
3
Hubei Provincial Engineering Technology Research Center for Magnetic Suspension, Wuhan University of Technology, Wuhan 430070, China
4
School of Mechanical Engineering, Shandong University, Jinan 250061, China
surface quality over the past decades, which are the main evaluation indicators for the products formed by SPIF [1–4]. Forming force, as an important process variable in SPIF, is of particular interest to help researchers understand the deformation mechanics, thereby benefiting the process design, development and optimization to enhance the performance of products mentioned above. This motivates the researches on the measurement and p
Data Loading...
