Energy absorption prediction and optimization of corrugation-reinforced multicell square tubes based on machine learning

Abstract

An energy absorbing tube combining multi-corner and multi-cell configurations was designed in this study. Machine learning was adopted to predict and optimize the crashworthiness of the proposed tube because it can handle both numerical and categorical responses. The results showed the increases in the considered geometric parameters caused the increases in the specific energy absorption and peak crushing force, while also made the unstable deformation mode prone to appear. Besides, with the help of machine learning, the accurate optimization results were obtained, in which the unstable deformation was removed. This work highlights the prospect of machine learning in structural optimizations.

Keywords:

• Energy absorption
• corrugation-reinforced structure
• optimization
• deformation mode
• machine learning

Disclosure statement

We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.

Additional information

Funding

The present work was supported by the National Natural Science Foundation of China (Grant number: 51675537), Natural Science Foundation of Hunan Province of China (Grant number: S2021JJMSXM3148), and the Open Sharing Fund for the Large-scale Instruments and Equipment of Central South University.