A wavelet neural network model optimized by gray wolf algorithm for springback prediction of metal tube bending

Lidi Quan; Jiajie Du; Bing Li; Liangyou Li; Yuanbin Wang

doi:10.1117/12.3014764

4 March 2024 A wavelet neural network model optimized by gray wolf algorithm for springback prediction of metal tube bending

Lidi Quan, Jiajie Du, Bing Li, Liangyou Li, Yuanbin Wang

Author Affiliations +

Proceedings Volume 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023); 129816A (2024) https://doi.org/10.1117/12.3014764
Event: 9th International Symposium on Sensors, Mechatronics, and Automation (ISSMAS 2023), 2023, Nanjing, China

Abstract

The compensation of springback in meta tube bending process is essential for improving product accuracy. In this paper, a metal tube springback model based on the wavelet neural network and the improved gray wolf algorithm (IGWO) is proposed to predict the compensation value of springback. Firstly, the dimension of gray wolf for the GWO is defined, and the parameters of the metal tube are taken as the inputs of WNN, then the non-linear mapping relationship between them and the springback is established. Secondly, to search a globally optimal solution, the initial weights and biases of the WNN are optimized with the IGWO algorithm. Thirdly, polynomial weight and the convergence factor are introduced to prevent the predicted value from falling into local optimization. Finally, experiments were carried out with 2414 sets of metal tube springback samples to evaluate the prediction accuracy of the IGWO-WNN model proposed in this article. The results showed that the IGWO-WNN algorithm is far better than GWO-WNN in terms of convergence speed and accuracy, prevent the training from fall into a local optimal solution.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Lidi Quan, Jiajie Du, Bing Li, Liangyou Li, and Yuanbin Wang "A wavelet neural network model optimized by gray wolf algorithm for springback prediction of metal tube bending", Proc. SPIE 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023), 129816A (4 March 2024); https://doi.org/10.1117/12.3014764

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available