Lattice structures enable tailored mechanical properties for aerospace, biomedical, and energy applications, yet navigating their vast design space while meeting complex performance requirements remains challenging. Here, we introduce DeepSeek-Lattice-KG, an intelligent framework synergistically integrating a domain-adapted 14B-parameter large language models with knowledge graphs for lattice structure design. The model was fine-tuned on 2500 peer-reviewed articles and integrated with a knowledge graph containing 658,623 entities from 50,000 publications, enabling both generative reasoning and graph-based knowledge validation. Evaluation on 2100 expert-curated questions across six technical domains demonstrates 94.8% accuracy, surpassing DeepSeek-R1-670B (88.2%) and conventional fine-tuning approaches, while ensuring data privacy and computational efficiency. Through dynamic knowledge augmentation, the framework maintains 93% accuracy on 2025 emerging topics versus 77% for static systems, enabling real-time updates without retraining. Engineering case studies demonstrate the framework's capability to synthesize knowledge across thousands of publications for design exploration. This work establishes a paradigm that domain-specialized small models combined with structured knowledge provide an efficient alternative to large general-purpose systems for specialized engineering domains.
| [1] |
B. Wang, D. Ruan, G. Lu, and T. X. Yu, “In-Plane Dynamic Crushing of Honeycombs—A Finite Element Study,” International Journal of Impact Engineering 28, no. 2 (2003): 161–182, https://doi.org/10.1016/s0734-743x(02)00056-8.
|
| [2] |
C. Qi, F. Jiang, and S. Yang, “Advanced Honeycomb Designs for Improving Mechanical Properties: A Review,” Composites, Part B: Engineering 227 (2021): 109393, https://doi.org/10.1016/j.compositesb.2021.109393.
|
| [3] |
L. J. Gibson, “Modelling the Mechanical Behavior of Cellular Materials,” Materials Science and Engineering A 110 (1989): 1–36, https://doi.org/10.1016/0921-5093(89)90154-8.
|
| [4] |
M. E. Korkmaz, M. K. Gupta, G. Robak, K. Moj, G. M. Krolczyk, and M. Kuntoğlu, “Development of Lattice Structure With Selective Laser Melting Process: A State of the Art on Properties, Future Trends and Challenges,” Journal of Manufacturing Processes 81 (2022): 1040–1063, https://doi.org/10.1016/j.jmapro.2022.07.051.
|
| [5] |
W. Wu, R. Xia, G. Qian, et al., “Mechanostructures: Rational Mechanical Design, Fabrication, Performance Evaluation, and Industrial Application of Advanced Structures,” Progress in Materials Science 131 (2023): 101021, https://doi.org/10.1016/j.pmatsci.2022.101021.
|
| [6] |
T. Maconachie, M. Leary, B. Lozanovski, et al., “SLM Lattice Structures: Properties, Performance, Applications and Challenges,” Materials & Design 183 (2019): 108137, https://doi.org/10.1016/j.matdes.2019.108137.
|
| [7] |
J. B. Berger, H. N. G. Wadley, and R. M. McMeeking, “Mechanical Metamaterials at the Theoretical Limit of Isotropic Elastic Stiffness,” Nature 543, no. 7646 (2017): 533–537, https://doi.org/10.1038/nature21075.
|
| [8] |
D. Jang, L. R. Meza, F. Greer, and J. R. Greer, “Fabrication and Deformation of Three-Dimensional Hollow Ceramic Nanostructures,” Nature Materials 12, no. 10 (2013): 893–898, https://doi.org/10.1038/nmat3738.
|
| [9] |
T. Frenzel, C. Findeisen, M. Kadic, P. Gumbsch, and M. Wegener, “Tailored Buckling Microlattices as Reusable Light-Weight Shock Absorbers,” Advanced Materials 28 (2016): 5865–5870, https://doi.org/10.1002/adma.201600610.
|
| [10] |
T. Bückmann, N. Stenger, M. Kadic, et al., “Tailored 3D Mechanical Metamaterials Made by Dip-In Direct-Laser-Writing Optical Lithography,” Advanced Materials 24, no. 20 (2012): 2710–2714, https://doi.org/10.1002/adma.201200584.
|
| [11] |
H. Yang and L. Ma, “1D to 3D Multi-Stable Architected Materials With Zero Poisson's Ratio and Controllable Thermal Expansion,” Materials & Design 188 (2020): 108430, https://doi.org/10.1016/j.matdes.2019.108430.
|
| [12] |
T. Bückmann, R. Schittny, M. Thiel, M. Kadic, G. W. Milton, and M. Wegener, “On Three-Dimensional Dilational Elastic Metamaterials,” New Journal of Physics 16, no. 3 (2014): 033032, https://doi.org/10.1088/1367-2630/16/3/033032.
|
| [13] |
T. Tancogne-Dejean, M. Diamantopoulou, M. B. Gorji, C. Bonatti, and D. Mohr, “3D Plate-Lattices: An Emerging Class of Low-Density Metamaterial Exhibiting Optimal Isotropic Stiffness,” Advanced Materials 30, no. 45 (2018): 1803334, https://doi.org/10.1002/adma.201803334.
|
| [14] |
M. Benedetti, A. du Plessis, R. O. Ritchie, M. Dallago, S. M. J. Razavi, and F. Berto, “Architected Cellular Materials: A Review on Their Mechanical Properties Towards Fatigue-Tolerant Design and Fabrication,” Materials Science and Engineering: R: Reports 144 (2021): 100606, https://doi.org/10.1016/j.mser.2021.100606.
|
| [15] |
X. Cao, Y. Jiang, T. Zhao, et al., “Compression Experiment and Numerical Evaluation on Mechanical Responses of the Lattice Structures With Stochastic Geometric Defects Originated From Additive-Manufacturing,” Composites, Part B: Engineering 194 (2020): 108030, https://doi.org/10.1016/j.compositesb.2020.108030.
|
| [16] |
X. Chen, P. Yu, H. Ma, et al., “A Class of Elastic Isotropic Plate Lattice Materials With Near-Isotropic Yield Stress,” Acta Materialia 276 (2024): 120085, https://doi.org/10.1016/j.actamat.2024.120085.
|
| [17] |
X. Chen, Q. Ji, J. Wei, et al., “Light-Weight Shell-Lattice Metamaterials for Mechanical Shock Absorption,” International Journal of Mechanical Sciences 169 (2020): 105288, https://doi.org/10.1016/j.ijmecsci.2019.105288.
|
| [18] |
P. Zhang, X. Chen, P. Yu, et al., “Grid Hollow Octet Truss Lattices That Are Stable at Low Relative Density,” Journal of the Mechanics and Physics of Solids 197 (2025): 106068, https://doi.org/10.1016/j.jmps.2025.106068.
|
| [19] |
W. W. S. Ma, H. Yang, Y. Zhao, et al., “Multi-Physical Lattice Metamaterials Enabled by Additive Manufacturing: Design Principles, Interaction Mechanisms, and Multifunctional Applications,” Advanced Science 12, no. 8 (2025): 2405835, https://doi.org/10.1002/advs.202405835.
|
| [20] |
K. R. Gawande, A. Sur, S. M. Tondre, N. N. Raja, G. Kale, and Y. Razoumny, “Advances and Challenges in Micro-Lattice Structures: Properties, Applications, and Future Directions,” AIMS Mater Sci 12, no. 3 (2025): 649–685, https://doi.org/10.3934/matersci.2025028.
|
| [21] |
H. Naveed, A. U. Khan, S. Qiu, et al., “A Comprehensive Overview of Large Language Models,” arXiv (2023): arXiv:2307.06435, https://doi.org/10.48550/arXiv.2307.06435.
|
| [22] |
S. Miret and N. M. A. Krishnan, “Enabling Large Language Models for Real-World Materials Discovery,” Nature Machine Intelligence 7, no. 7 (2025): 1–8, https://doi.org/10.1038/s42256-025-01058-y.
|
| [23] |
S. Liu, T. Wen, B. Ye, et al., “Large Language Models for Material Property Predictions: Elastic Constant Tensor Prediction and Materials Design,” Digestive Diseases 4, no. 6 (2025): 1625–1638, https://doi.org/10.1039/d5dd00061k.
|
| [24] |
A. N. Rubungo, C. Arnold, B. P. Rand, and A. B. Dieng, “LLM-Prop: Predicting the Properties of Crystalline Materials Using Large Language Models,” npj Computational Materials 11, no. 1 (2025): 186, https://doi.org/10.1038/s41524-025-01536-2.
|
| [25] |
M. C. Swain and J. M. Cole, “Chemdataextractor: A Toolkit for Automated Extraction of Chemical Information From the Scientific Literature,” Journal of Chemical Information and Modeling 56, no. 10 (2016): 1894–1904, https://doi.org/10.1021/acs.jcim.6b00207.
|
| [26] |
S. Huang and J. M. Cole, “BatteryBERT: A Pretrained Language Model for Battery Database Enhancement,” Journal of Chemical Information and Modeling 62, no. 24 (2022): 6365–6377, https://doi.org/10.1021/acs.jcim.2c00035.
|
| [27] |
J. Dagdelen, A. Dunn, S. Lee, et al., “Structured Information Extraction From Scientific Text With Large Language Models,” Nature Communications 15, no. 1 (2024): 1418, https://doi.org/10.1038/s41467-024-45563-x.
|
| [28] |
M. J. Buehler, “Accelerating Scientific Discovery With Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning,” Machine Learning: Science and Technology 5, no. 3 (2024): 035083, https://doi.org/10.1088/2632-2153/ad7228.
|
| [29] |
V. Venugopal and E. Olivetti, “MatKG: An Autonomously Generated Knowledge Graph in Material Science,” Scientific Data 11, no. 1 (2024): 217, https://doi.org/10.1038/s41597-024-03039-z.
|
| [30] |
X. Bai, S. He, Y. Li, et al., “Construction of a Knowledge Graph for Framework Material Enabled by Large Language Models and Its Application,” npj Computational Materials 11, no. 1 (2025): 51, https://doi.org/10.1038/s41524-025-01540-6.
|
| [31] |
M. J. Buehler, “Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks,” Journal of Materials Research 40, no. 15 (2025): 1–39, https://doi.org/10.1557/s43578-025-01652-1.
|
| [32] |
R. K. Luu and M. J. Buehler, “BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and bio-inspired Materials,” Advanced Science 11, no. 10 (2024): 2306724, https://doi.org/10.1002/advs.202306724.
|
| [33] |
Z. Lin, H. Akin, R. Rao, et al., “Evolutionary-Scale Prediction of Atomic-Level Protein Structure With a Language Model,” Science. 379, no. 6637 (2023): 1123–1130, https://doi.org/10.1126/science.ade2574.
|
| [34] |
N. Matsumoto, J. Moran, H. Choi, et al., “KRAGEN: A Knowledge Graph-Enhanced RAG Framework for Biomedical Problem Solving Using Large Language Models,” Bioinformatics 40, no. 6 (2024): btae353, https://doi.org/10.1093/bioinformatics/btae353.
|
| [35] |
J. Jiang, K. Zhou, W. X. Zhao, et al., “Kg-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning Over Knowledge Graph,” arXiv (2024): arXiv:2402.11163, https://doi.org/10.48550/arXiv.2402.11163.
|
| [36] |
Z. Shu, H. Li, and L. Gao, “An Efficient Data-Driven Optimization Framework for Elastically Isotropic Lattice Structures,” Materials & Design 253 (2025): 113976, https://doi.org/10.1016/j.matdes.2025.113976.
|
| [37] |
Y. Wang, F. Xu, H. Gao, and X. Li, “Elastically Isotropic Truss-Plate-Hybrid Hierarchical Microlattices With Enhanced Modulus and Strength,” Small 19, no. 18 (2023): 2206024, https://doi.org/10.1002/smll.202206024.
|
| [38] |
J. Feng, B. Liu, Z. Lin, and J. Fu, “Isotropic Octet-Truss Lattice Structure Design and Anisotropy Control Strategies for Implant Application,” Materials & Design 203 (2021): 109595, https://doi.org/10.1016/j.matdes.2021.109595.
|
| [39] |
E. Andreassen and C. S. Andreasen, “How to Determine Composite Material Properties Using Numerical Homogenization,” Computational Materials Science 83 (2014): 488–495, https://doi.org/10.1016/j.commatsci.2013.09.006.
|
| [40] |
International Organization for Standardization (ISO); ASTM International. ISO/ASTM 52900, Additive Manufacturing—General Principles—Fundamentals and Vocabulary, (2021): Published 2021, https://www.iso.org/obp/ui/#iso:std:iso-astm:52900:ed-2:v1:en.
|
| [41] |
ASTM International. ASTM F2924-14, Standard Specification for Additive Manufacturing Titanium-6 Aluminum-4 Vanadium With Powder Bed Fusion, (2021): Published 2021, https://store.astm.org/f2924-14r21.html.
|
| [42] |
T. Pasang, B. Tavlovich, O. Yannay, et al., “Directionally-Dependent Mechanical Properties of Ti6Al4V Manufactured by Electron Beam Melting (EBM) and Selective Laser Melting (SLM),” Materials 14, no. 13 (2021): 3603, https://doi.org/10.3390/ma14133603.
|
| [43] |
C. García-Hernández, C. García-Cabezón, F. González-Diez, et al., “Effect of Processing on Microstructure, Mechanical Properties, Corrosion and Biocompatibility of Additive Manufacturing Ti-6Al-4V Orthopaedic Implants,” Scientific Reports 15, no. 1 (2025): 14087, https://doi.org/10.1038/s41598-025-98349-6.
|
| [44] |
H. K. Rafi, N. V. Karthik, H. Gong, T. L. Starr, and B. E. Stucker, “Microstructures and Mechanical Properties of Ti6Al4V Parts Fabricated by Selective Laser Melting and Electron Beam Melting,” Journal of Materials Engineering and Performance 22, no. 12 (2013): 3872–3884, https://doi.org/10.1007/s11665-013-0658-0.
|
| [45] |
J. Youn, N. Rai, and I. Tagkopoulos, “Knowledge Integration and Decision Support for Accelerated Discovery of Antibiotic Resistance Genes,” Nature Communications 13, no. 1 (2022): 2360, https://doi.org/10.1038/s41467-022-29993-z.
|
| [46] |
J. Pasternack and D. Roth, “Knowing What to Believe (When You Already Know Something),” in Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), (2010), 877–885, https://aclanthology.org/C10-1099/.
|
| [47] |
A. Ghafarollahi and M. J. Buehler, “SciAgents: Automating Scientific Discovery Through Bioinspired Multi-Agent Intelligent Graph Reasoning,” Advanced Materials 37, no. 22 (2025): 2413523, https://doi.org/10.1002/adma.202413523.
|
| [48] |
Y. Song, R. Y. Tay, J. Li, et al., “3D-Printed Epifluidic Electronic Skin for Machine Learning-Powered Multimodal Health Surveillance,” Science Advances 9, no. 37 (2023): eadi6492, https://doi.org/10.1126/sciadv.adi6492.
|
| [49] |
R. Zhang, D. Jiang, Y. Zhang, et al., “MATHVERSE: Does Your Multi-Modal LLM Truly See the Diagrams in Visual Math Problems?,” in European Conference on Computer Vision (Springer Nature Switzerland, 2024), 169–186, https://doi.org/10.1007/978-3-031-73242-3_10.
|
Rights & permissions
2026 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.
PDF
(5268KB)
