To address the limitations of traditional optimization algorithms in the design of complex energy-absorbing structures—specifically their poor convergence and limited population diversity—this study proposes a Contrastive Learning-based Non-dominated Sorting Genetic Algorithm (NSGA-II-CL). The proposed method is applied to the multi-objective optimization of a three-dimensional double-layer pyramidal lattice structure. Compared with conventional single-layer pyramidal lattices, the proposed design introduces double-layer pyramid units reinforced with vertical struts and stiffening ribs, thereby enhancing structural stability and energy absorption capacity. The samples were fabricated using Selective Laser Melting and hot-press molding techniques. Both quasi-static compression tests and finite element simulations were conducted to validate the structural performance. The specific energy absorption (SEA) and peak crushing force (PCF) were defined as optimization objectives, and a Response Surface surrogate model was constructed. The leg size, leg inclination angle, and carbon fiber ply orientation were selected as design variables. The proposed NSGA-II-CL introduces a contrastive learning mechanism, where positive and negative sample pairs are constructed based on the non-dominated hierarchy. Through multi-dimensional feature fusion and an adaptive parameter adjustment strategy, the algorithm achieves a dynamic balance between exploration and convergence during the evolutionary process. Results demonstrate that, compared with the conventional NSGA-II, the proposed NSGA-II-CL achieves improvements of 11.7% in Spacing, 1.0% in Convergence, and 1.2% in HV performance, resulting in a more uniform Pareto front distribution. Both simulation and experimental validation confirm the reliability of the optimized results, with SEA and PCF prediction errors of 2.51% and 2.26%, respectively. These findings verify the effectiveness of the proposed algorithm and structural design methodology, providing a novel approach and technical pathway for intelligent optimization of energy-absorbing structures.
SunLHeZJiaN, et al.Local chemical order enables an ultrastrong and ductile high-entropy alloy in a cryogenic environment. Sci Adv2024; 10(48): eadq6398.
2.
SimõesS. High-performance advanced composites in multifunctional material design: state of the art, challenges, and future directions. Materials2024; 17(23): 5997.
3.
ShiSWangGHuC, et al.Impact response of carbon fiber/aluminum honeycomb sandwich structures under multiple low-velocity loads. Compos Sci Technol2025; 261: 111027.
4.
BaiYGaoJHuangC, et al.Topology optimized design and validation of sandwich structures with pure-lattice/solid-lattice infill by additive manufacturing. Compos Struct2023; 319: 117152.
5.
HanJMaXYangR, et al.Compressive properties of composite sandwich structure with fractal tree-inspired lattice core. Materials2025; 18(3): 606.
6.
KheyabaniAMassarwaEKefalA. Multiscale structural analysis of thick sandwich structures using parametric HFGMC micromechanics and isogeometric plate formulation based on refined zigzag theory. Compos Struct2022; 297: 115988.
7.
NovakNBorovinšekMAl-KetanO, et al.Impact and blast resistance of uniform and graded sandwich panels with TPMS cellular structures. Compos Struct2022; 300: 116174.
8.
TewariKPanditMKMahapatraMM, et al.Honeycomb-spiderweb-inspired self-similar hybrid cellular structures for impact applications. Def Technol2025; 43: 182–200.
9.
TarkashvandADaneshjouKGolmohammadiA. FG and viscoelastic models combination for vibroacoustic modeling of sandwich structures made of open and closed cell foam materials. Compos Struct2021; 259: 113438.
10.
SuMMaQZhangA, et al.Mechanical properties of sandwich structures with different webs enhanced by filling polyurethane foam and encasing rectangular tube. Mater Today Commun2024; 40: 110058.
11.
LuoYFanH. Energy absorbing ability of rectangular self-similar multi-cell sandwich-walled tubular structures. Thin-Walled Struct2018; 124: 88–97.
12.
ZhaoJCuiZWangS, et al.Flexural response of additively manufactured honeycomb sandwich structures with continuous density-gradient variations. Thin-Walled Struct2024; 197: 111642.
13.
KhanAUSadhyaSKumarAB, et al.Investigation on dual wire TIG Arc additive manufacturing of IN625 and SS316L FGM for continuous gradient and sandwich structures. Thin-Walled Struct2024; 200: 111881.
14.
QinYXiongCZhuX, et al.Failure mechanism and impact resistance of a novel all-composite double-corrugated sandwich plate under low-velocity impact. Case Stud Constr Mater2024; 20: e02724.
15.
DongWPanHSunY, et al.The sandwich-structured advanced high strength steel to resist the liquid metal embrittlement. J Mater Res Technol2023; 25: 3167–3176.
16.
PatelMPatelSAhmadS. Blast analysis of efficient honeycomb sandwich structures with CFRP/Steel FML skins. Int J Impact Eng2023; 178: 104609.
17.
UmHJRhoHJJeonNH, et al.Mechanical performance of novel curved sandwich structures featuring 3D printed continuous carbon fiber/polyamide 6 composite corrugated core with rail interlocking. Compos B Eng2025; 295: 112222.
18.
ChenYJinZKangW, et al.3D printed bio-inspired self-similar carbon fiber reinforced composite sandwich structures for energy absorption. Compos Sci Technol2024; 248: 110453.
19.
LiuYZhouHYinC, et al.Experimental investigation on the residual bending capacity of carbon fiber corrugated sandwich structures under the repeated impact. Thin-Walled Struct2024; 199: 111754.
20.
WowkDReynoTYeungR, et al.An experimental and numerical investigation of core damage size in honeycomb sandwich panels subject to low-velocity impact. Compos Struct2020; 254: 112739.
21.
YuYFuTWangS, et al.Dynamic response of novel sandwich structures with 3D sinusoid-parallel-hybrid honeycomb auxetic cores: the cores based on negative Poisson’s ratio of elastic jump. Eur J Mech Solid2025; 109: 105449.
22.
LiuHLiD. Study on the energy absorption effect and impact resistance of a composite sandwich panel with carbon fiber reinforced re-entrant hexagonal honeycomb core with negative Poisson’s ratio. Eur J Mech Solid2025; 109: 105447.
23.
ZhangYCaiDPengJ, et al.On low-velocity impact behavior of sandwich composites with negative Poisson’s ratio lattice cores. Compos Struct2022; 299: 116078.
24.
ZhouYJiangDWangL, et al.Cushioning performance of origami negative poisson’s ratio honeycomb steel structure. Thin-Walled Struct2024; 204: 112284.
25.
LiXLiuPChengH, et al.Experimental and numerical analysis of low-velocity impact damage of CFRP laminates with negative Poisson ratio (NPR) rubber protective layer. Thin-Walled Struct2023; 191: 111066.
26.
YueZHanBWangZ, et al.Data-driven multi-objective optimization of ultralight hierarchical origami-corrugation meta-sandwich structures. Compos Struct2023; 303: 116334.
27.
Perroni-ScharfMFergusonZButruilleT, et al.Data-Efficient discovery of hyperelastic TPMS metamaterials with extreme energy dissipation[C]. In: Proceedings of the Special Interest Group on computer graphics and interactive techniques conference conference papers, 2025, pp. 1–12. August 10–14, 2025, Vancouver, British Columbia, Canada.
28.
HuangHYangXYanQ, et al.Crashworthiness analysis and multiobjective optimization of bio-inspired sandwich structure under impact load. Thin-Walled Struct2022; 172: 108840.
29.
YanQHuangHXuS, et al.Crashworthiness analysis and multi-objective optimisation of a multilayer bio-inspired sandwich structure under impact load. Int J Crashworthiness2025; 30: 1–15.
30.
AndikaSSPWidagdoD, et al.Design and multi-objective optimization of auxetic sandwich panels for blastworthy structures using machine learning method. Applied Sciences2024; 14(23): 10831.
31.
ZhangYLiuZHuangQ. A contrastive learning-based fault diagnosis method for rotating machinery with limited and imbalanced labels. IEEE Sens J2023; 23(14): 16402–16412.
32.
ZhuWLiWDorseyER, et al.Unsupervised anomaly detection by densely contrastive learning for time series data. Neural Netw2023; 168: 450–458.
33.
MaWChangYCYangJ, et al. Contrastive learning-based agent modeling for deep reinforcement learning. IEEE Trans Emerg Top Comput Intell. 2025; 9(5).
34.
ZhangXXuBMaF, et al.Rethinking contrastive learning in session-based recommendation. Pattern Recogn2025; 169: 111924.
35.
MaBCaoXFengY, et al.A comparative study on the low velocity impact behavior of UD, woven, and hybrid UD/woven FRP composite laminates. Compos B Eng2024; 271: 111133.
KodagaliKRadCVSockalingamS, et al.Low velocity impact and compression-after-impact response of hybrid pseudo-woven meso-architectured carbon/epoxy composite laminates manufactured via automated fiber placement. Compos B Eng2024; 271: 111154.
38.
YinDZhengJXiongC, et al.Experimental and numerical studies of perforated CFRP laminates under quasi-static tensile load. IOP Conf Ser Mater Sci Eng2021; 1040(1): 012011. IOP Publishing.
39.
UmbrelloDM’saoubiROuteiroJC. The influence of Johnson–cook material constants on finite element simulation of machining of AISI 316L steel. Int J Mach Tool Manufact2007; 47(3-4): 462–470.
40.
HeNZhangYChenTT, et al.Study on crashworthiness of window-type multi-wall structure. Journal of Mechanical Engineering2019; 55(10): 142–150.
41.
BaroutajiAArjunanASinghG, et al.Crushing and energy absorption properties of additively manufactured concave thin-walled tubes. Results Eng2022; 14: 100424.
42.
AlbakEİ. Crashworthiness design and optimization of nested structures with a circumferentially corrugated circular outer wall and inner ribs. Thin-Walled Struct2021; 1: 167.
43.
ZhouBZhangHHanS, et al.Crashworthiness analysis and optimization of a novel thin-walled multi-cell structure inspired by bamboo. Structures2024; 59: 105827.
44.
BaroutajiAArjunanAStanfordM, et al.Deformation and energy absorption of additively manufactured functionally graded thickness thin-walled circular tubes under lateral crushing. Eng Struct2021; 226: 111324.
45.
ZhaYWangSMaQ, et al.Study on the axial impact of Al‐CFRP thin‐walled tubes with induced design. Polym Compos2022; 43(7): 4660–4686.
46.
ZhangJLinGYinX, et al.Application of artificial neural network (ANN) and response surface methodology (RSM) for modeling and optimization of the contact angle of rice leaf surfaces. Acta Physiol Plant2020; 42(4): 51.
47.
SunHWangCHuZ. A dual strategy of adaptive knee-point guidance and niche sampling for non-cyclic dynamic multiobjective optimization problems. Eng Appl Artif Intell2024; 133: 108144.
48.
HeMWangXChenH, et al.A knee point‐driven many‐objective evolutionary Algorithm with adaptive switching mechanism. J Appl Math2024; 2024(1): 4737604.
49.
LiWZhangTWangR, et al.A knee-point driven multi-objective evolutionary algorithm for flexible job shop scheduling[C]. In: 2019 IEEE symposium Series on Computational Intelligence (SSCI). IEEE, 2019, pp. 1716–1722.
