Hailun Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hailun Tan has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
A.G. Cheng
1 shared publicationAiguo Cheng
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, China
1 shared publicationAnmin Huang
CRRC Group Zhuzhou Times New Material Technology Co., Ltd. Zhuzhou 412007 P. R. China
1 shared publicationB. Xu
Technology Development Center, SAIC GM Wuling Automobile Co., Ltd, Liuzhou, People’s Republic of China
1 shared publicationE. Li
School of Science, Engineering and Design, Teesside University, Middleborough, United Kingdom
1 shared publicationEric Li
School of Computing, Engineering & Digital Technologies Teesside University Tees Valley Middlesbrough TS1 3BX UK
1 shared publication
Latest Publications
- 8 September 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (20)
Machine Learning‐Based Strategy for Predicting the Multiscale Mechanical Properties of Helical Carbon Fiber Composites
Inspired by biological structures, multilevel helical configurations enhance material toughness and strength. This study develops high‐performance helical twisted carbon fiber composites (HTCFCs) and introduces a machine learning (ML)‐based multiscale performance prediction method to bridge mesoscale parameters with macroscopic properties. HTCFC specimens undergo experimental testing, validate through finite element method (FEM) simulations. A dataset of 480 material configurations is generated, incorporating helix angle, volume fraction, resin modulus, and Poisson's ratio. A three‐step ML optimization process—combining cross‐validation, random grid search, and Bayesian optimization—is applied to 16 ML models, yielding a highly accurate predictive framework. Compared to FEM, the ML model reduces computation time to 0.01%–0.03% of the original. In addition to accelerating large‐scale parametric exploration, the model also enables sensitivity‐based interpretation of structural mechanisms, supporting both efficient design and physical understanding. SHapley Additive exPlanations (SHAP) analysis identifies key structural parameters, confirming high model accuracy and alignment with experimental results. This study demonstrates that ML‐driven multiscale modeling is a fast and effective tool for optimizing next‐generation composite materials, advancing lightweight and high‐strength engineering applications.
- 8 September 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (20)
Machine Learning‐Based Strategy for Predicting the Multiscale Mechanical Properties of Helical Carbon Fiber Composites
Inspired by biological structures, multilevel helical configurations enhance material toughness and strength. This study develops high‐performance helical twisted carbon fiber composites (HTCFCs) and introduces a machine learning (ML)‐based multiscale performance prediction method to bridge mesoscale parameters with macroscopic properties. HTCFC specimens undergo experimental testing, validate through finite element method (FEM) simulations. A dataset of 480 material configurations is generated, incorporating helix angle, volume fraction, resin modulus, and Poisson's ratio. A three‐step ML optimization process—combining cross‐validation, random grid search, and Bayesian optimization—is applied to 16 ML models, yielding a highly accurate predictive framework. Compared to FEM, the ML model reduces computation time to 0.01%–0.03% of the original. In addition to accelerating large‐scale parametric exploration, the model also enables sensitivity‐based interpretation of structural mechanisms, supporting both efficient design and physical understanding. SHapley Additive exPlanations (SHAP) analysis identifies key structural parameters, confirming high model accuracy and alignment with experimental results. This study demonstrates that ML‐driven multiscale modeling is a fast and effective tool for optimizing next‐generation composite materials, advancing lightweight and high‐strength engineering applications.
- 5 June 2024
- Published by Elsevier in Composite Structures
- Vol. 342, 118260
Energy absorption characteristics of modular assembly structures under quasi-static compression load
- 5 June 2024
- Published by Elsevier in Composite Structures
- Vol. 342, 118260
Energy absorption characteristics of modular assembly structures under quasi-static compression load
- 30 March 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 137
Dynamic bending behavior of double-hat beams filled with alloy hierarchical structure
- 30 March 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 137
Dynamic bending behavior of double-hat beams filled with alloy hierarchical structure
- 10 June 2022
- Published by Taylor & Francis in Mechanics of Advanced Materials and Structures
- Vol. 30 (19) , 3923-3936
Energy absorption characteristics and multi-objective optimization of a novel reentrant hierarchical honeycomb bumper system
This paper aims to introduce the hierarchy design into sandwich beams and bumper systems to improve their mechanical performance. Two kinds of reentrant hierarchical sandwich beams are proposed and their energy absorption characteristics have been systematically investigated. Based on its excellent energy absorption ability, the reentrant hierarchical honeycombs with equilateral triangle substructures (RHT) core are introduced to the design of the bumper system, and the hierarchical bumper system exhibits better mechanical properties than the traditional bumper and the aluminum foam-filled bumper under different loading conditions. Then, the multi-objective optimization model of the hierarchical bumper system is established by combining the optimal Latin hypercube design method (OLHD) and the response surface model (RSM). The non-dominated sorting genetic algorithm-II (NSGA-II) algorithm is adopted to optimize the design parameters. The optimization results show that the objectives are optimized efficiently, and it performs remarkable performances in bumper system design.
- 10 June 2022
- Published by Taylor & Francis in Mechanics of Advanced Materials and Structures
- Vol. 30 (19) , 3923-3936
Energy absorption characteristics and multi-objective optimization of a novel reentrant hierarchical honeycomb bumper system
This paper aims to introduce the hierarchy design into sandwich beams and bumper systems to improve their mechanical performance. Two kinds of reentrant hierarchical sandwich beams are proposed and their energy absorption characteristics have been systematically investigated. Based on its excellent energy absorption ability, the reentrant hierarchical honeycombs with equilateral triangle substructures (RHT) core are introduced to the design of the bumper system, and the hierarchical bumper system exhibits better mechanical properties than the traditional bumper and the aluminum foam-filled bumper under different loading conditions. Then, the multi-objective optimization model of the hierarchical bumper system is established by combining the optimal Latin hypercube design method (OLHD) and the response surface model (RSM). The non-dominated sorting genetic algorithm-II (NSGA-II) algorithm is adopted to optimize the design parameters. The optimization results show that the objectives are optimized efficiently, and it performs remarkable performances in bumper system design.
- 3 August 2021
- Published by Taylor & Francis in International Journal of Crashworthiness
- Vol. 27 (5) , 1401-1411
Study on energy absorption characteristics of a novel lotus root multi-cellular structure under axial crushing condition
The lotus root multi-cellular structure is a novel filling structure with good energy-absorbing properties. In this paper, the relationship between cell geometry and mechanical properties of lotus root multi-cellular structure, and the relationship between cell arrangement and mechanical properties of lotus root multi-cellular structure are studied in detail. Firstly, the 3D printer was used to make the sample and carry out the quasi-static compression test to illustrate the accuracy of the finite element simulation analysis and the feasibility of the manufacturing process of the lotus root multi-cellular structure. Then, by combining the basic tube (BT) and the lotus root filled core, the lotus root filled tube (LFT) is established. And by changing the geometrical parameters of cell structure and the arrangement of cell structure, the energy absorption characteristics of LFT were studied in detail. The results show that the energy absorption ability of LFT is positively correlated with the number of filled columns, while the peak force of LFT is negatively correlated with the number of filled columns. The relationship between energy absorption and angle of cell structure is a quadratic parabola.
- 3 August 2021
- Published by Taylor & Francis in International Journal of Crashworthiness
- Vol. 27 (5) , 1401-1411
Study on energy absorption characteristics of a novel lotus root multi-cellular structure under axial crushing condition
The lotus root multi-cellular structure is a novel filling structure with good energy-absorbing properties. In this paper, the relationship between cell geometry and mechanical properties of lotus root multi-cellular structure, and the relationship between cell arrangement and mechanical properties of lotus root multi-cellular structure are studied in detail. Firstly, the 3D printer was used to make the sample and carry out the quasi-static compression test to illustrate the accuracy of the finite element simulation analysis and the feasibility of the manufacturing process of the lotus root multi-cellular structure. Then, by combining the basic tube (BT) and the lotus root filled core, the lotus root filled tube (LFT) is established. And by changing the geometrical parameters of cell structure and the arrangement of cell structure, the energy absorption characteristics of LFT were studied in detail. The results show that the energy absorption ability of LFT is positively correlated with the number of filled columns, while the peak force of LFT is negatively correlated with the number of filled columns. The relationship between energy absorption and angle of cell structure is a quadratic parabola.
- Top Cited Papers
- 1 November 2020
- Published by Elsevier in Aerospace Science and Technology
- Vol. 106
Energy absorption characteristics of three-layered sandwich panels with graded re-entrant hierarchical honeycombs cores
- 1 November 2020
- Published by Elsevier in Aerospace Science and Technology
- Vol. 106
Top Cited PapersEnergy absorption characteristics of three-layered sandwich panels with graded re-entrant hierarchical honeycombs cores