Rapid thickness distribution prediction of superplastic formed parts based on geometry adapted PSO-BP neural network surrogate model

Muqi Sun, Chengyue Xiong, Yuwei Zhou, Xicheng Zhang, Aoming Yuan, Yan Sun, Yongbing Li · 2025

Read Rapid thickness distribution prediction of superplastic formed parts based on geometry adapted PSO-BP neural network surrogate model by Muqi Sun, Chengyue Xiong, Yuwei Zhou, Xicheng Zhang, Aoming Yuan, Yan Sun, Yongbing Li (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12847917.txt.

Description

Muqi Sun and co-authors described a fast way in 2025 to predict how thick a shaped metal part will be. The parts are made by a hot forming process used for light, strong sheets. The usual computer method is slow and needs exact edge settings, so it cannot guide the work while it runs. The team built a stand-in model that learns from past results instead.

The new model sorts input points with a swarm search and then feeds them to a simple neural network. A shape-based score cuts large errors near round corners. Mean error fell from 1.3 percent to 0.8 percent in their tests. A box-shaped part made of a titanium mix was mapped in half a second, close to the slow method.

Catalog record

CREATORMuqi Sun, Chengyue Xiong, Yuwei Zhou, Xicheng Zhang, Aoming Yuan, Yan Sun, Yongbing Li
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE29 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12847917

Browse the full library · About the Tower of Babel