A machine learning-based crashworthiness optimization for a novel pine cone-inspired multi-cell tubes under bending

Aug 5, 2026

Upload by Ivy

Bionic tubes offer strong crashworthiness potential for vehicle engineering. This study investigates crashworthiness responses and develops machine learning-based multi-objective optimization for pine cone-inspired multi-celled tubes (PCMTs). A baseline PCMT geometry is correlated with existing experiments, then dynamic responses across geometric and thickness variations are evaluated for structural performance. Surrogate models quantify main and interaction effects, while NSGA-II finds Pareto-optimal designs. Results show thickness changes dominate IPF and MCF, and embedded inner tubes substantially increase energy absorption with limited IPF rise.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Energy absorption and thin-walled tube crashworthiness background

Collapse mechanisms and bending-related studies

Motivation for bionic multi-celled tube optimization

Article overview (method and key findings)

Baseline correlation and dynamic response evaluation

Surrogate modeling and effects analysis

Multi-objective optimization using NSGA-II

Comparative performance results and implications

A machine learning-based crashworthiness optimization for a novel pine cone-inspired multi-cell tubes under bending Liang, R., Tang, X., Huang, J., Bastien, C., Zhang, C. & Tuo, W. Published PDF deposited in Coventry University’s Repository Original citation: Liang, R, Tang, X, Huang, J, Bastien, C, Zhang, C & Tuo, W 2024, 'A machine learningbased crashworthiness optimization for a novel pine cone-inspired multi-cell tubes under bending', Heliyon, vol. 10, no. 18, e37828 . [https://dx.doi.org/10.1016/j.heliyon.2024.e37828](https://dx.doi.org/10.1016/j.heliyon.2024.e37828) [DOI 10.1016/j.heliyon.2024.e37828](DOI 10.1016/j.heliyon.2024.e37828)[ ](DOI 10.1016/j.heliyon.2024.e37828)[ISSN 2405-8440](ISSN 2405-8440) Publisher: Elsevier This is an open access article under the CC BY-NC license ( [http://creativecommons.org/licenses/by-nc/4.0/](http://creativecommons.org/licenses/by-nc/4.0/)) . Heliyon 10 (2024) e37828 Contents lists available at ScienceDirect Heliyon journal [homepage:](homepage: www.cell.com/heliyon)[ www.cell.com/heliyon](homepage: www.cell.com/heliyon) | Research article
A machine learning-based crashworthiness optimization for a novel pine cone-inspired multi-cell tubes under bending
Rui Lianga, Xuebang Tang b,*, Jie Huang c,d, Christophe Bastien e, Cheng Zhang a, Wangjie Tuof
a School of Automobile Engineering, Guilin University of Aerospace Technology, Guilin, 541004, China b Academic Affairs Office, Guilin University of Aerospace Technology, Guilin, 541004, China
c State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing, 401133, China d China Automotive Engineering Research Institute Co Ltd, Chongqing, 401122, China e Centre for Future Transport and Cities, Coventry University, Coventry, CV1 2TE, UK
f School of Vehicle Engineering, Chongqing Industry and Trade Polytechnic, Chongqing, 408000, China | | | | | --- | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords: Bionic
Multi-celled tube
Crashworthiness Pine cone Machine learning | | Bionic tubes are of interest in vehicle engineering due to their superior crashworthiness potential. This study proposes a crashworthiness response investigation and machine learning-based multiobjective optimization of pine cone-inspired muti-celled tubes (PCMTs). The base computer PCMT model was correlated using existing experiments, followed by a dynamic response evaluation of different PCMT geometrical and thickness configurations to assess their structural performance. Surrogate models of these PCMTs were then constructed using machine learning algorithms, and their main and interaction effects were analyzed. A non-dominated sorting genetic algorithm II (NSGA-II) approach was employed to perform a multi-objective optimization. The results demonstrate that thickness change had more effect on the initial peak force (IPF) and the mean crushing force (MCF) than the specific energy absorption (SEA). Besides, due to the coupling effect, IPF, MCF and SEA of the optimal design solution of the PCMTs could reach a 36.82 %, 61.66 % and 72.95 % increase than the sum case, suggesting that embedding inner tubes could significantly increase energy absorption with a relative minor IPF increase. Moreover, the MCF and SEA of optimal design gave an average difference of 18.01 % and 5.91 % from the original tubes. PCMTs, therefore, could be used as an ideal energy absorption structure in the vehicle body structures. | | 1. Introduction Thin-walled tubes are widely utilized as energy absorption components in vehicles owing to their superior ability to balance energy absorption and lightweight [1–5]. The experimental, theoretical, and numerical studies on thin-walled tubes’ collapse and energy-absorption mechanisms have been of interest to engineers [6–12], because of their complex crushing and folding behaviors. Murray and Khoo [13] were concerned about the tests of channel structures and proposed

FAQs

What structure is studied in this paper?

The paper studies pine cone-inspired multi-celled tubes (PCMTs), including configurations with different numbers of inner circular tubes, evaluated under bending.

How is machine learning used in the optimization workflow?

Machine learning surrogate models are built for the PCMT designs to analyze main and interaction effects and to support multi-objective optimization.

What optimization method is used for multi-objective design?

A non-dominated sorting genetic algorithm II (NSGA-II) approach is employed to search for Pareto-optimal PCMT design solutions.

Aug 5, 2026

Upload by Ivy