ACTA AERONAUTICAET ASTRONAUTICA SINICA >
Prediction of bearing strength for composite bolted joint structures based on MCI-PINN
Received date: 2025-06-16
Revised date: 2025-07-10
Accepted date: 2025-07-23
Online published: 2025-07-25
Supported by
National Commercial Aircraft Manufacturing Engineering and Technology Research Center Innovation Fund(COMAC-SFGS-2023-2353)
Although deep learning based black-box models demonstrate high efficiency and accuracy in establishing input-output mappings for composite bolted joint strength prediction, their inherent lack of physical interpretability obscures model decision logic, ultimately compromising reliability and generalizability. Based on the fusion of physical law constraints of composite materials and nonlinear identification constraints, a Multi-Constraint Identification Physics-Informed Neural Network (MCI-PINN) is proposed. Firstly, the constraints of physical laws apply the engineering estimation formula for the extrusion strength of composite material bolt connections. Secondly, using linear, polynomial, power, exponential, and logarithmic functions as basic functional forms, nonlinear relationships between material parameters, mechanical parameters, structural parameters, and extrusion strength are established, and the mapping relationship with the highest accuracy is identified to serve as a constraint for nonlinear identification. Then, the physical law constraints and nonlinear identification constraints are embedded in the neural network in the form of loss functions to guide the model training. Finally, in the case verification, the single-pin connection extrusion strength prediction of two layers of X850 material was carried out. The analysis results show that the prediction error index MRE of the extrusion strength of the two layers is 1.24% and 1.27% respectively. In terms of discreteness prediction, interpretability and generalization ability, MCI-PINN shows superiority compared with ANN and PINN.
Yue LIU , Hantao REN , Xiaofeng XUE , Zhicen SONG , Cheng LU , Yunwen FENG . Prediction of bearing strength for composite bolted joint structures based on MCI-PINN[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2026 , 47(5) : 232422 -232422 . DOI: 10.7527/S1000-6893.2025.32422
| [1] | 山美娟, 赵丽滨. 复合材料螺栓连接的增强设计与分析研究进展[J]. 复合材料学报, 2023, 40(7): 3771-3784. |
| SHAN M J, ZHAO L B. Research progress in reinforcement design and analysis of composite bolted joints[J]. Acta Materiae Compositae Sinica, 2023, 40(7): 3771-3784 (in Chinese). | |
| [2] | 董慧民, 李小刚, 马绪强, 等. 聚合物基复合材料凸头螺栓连接研究进展[J]. 北京航空航天大学学报, 2023, 49(4): 745-760. |
| DONG H M, LI X G, MA X Q, et al. Research progress in mechanically fastened polymer-matrix composite joints with protruding-head bolts[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(4): 745-760 (in Chinese). | |
| [3] | 豆广征, 刘峰, 王卓煜, 等. 复合材料螺栓连接结构力学性能研究进展[J]. 新技术新工艺, 2022(9): 1-5. |
| DOU G Z, LIU F, WANG Z Y, et al. Research progress of bolted joints structure mechanical performance of composite materials[J]. New Technology & New Process, 2022(9): 1-5 (in Chinese). | |
| [4] | 孙涛, 周金宇. 碳纤维复合材料螺栓连接性能综述[J]. 现代制造工程, 2018(9): 154-160. |
| SUN T, ZHOU J Y. Summary for the connection performance of carbon fiber composite bolt[J]. Modern Manufacturing Engineering, 2018(9): 154-160 (in Chinese). | |
| [5] | 梁乐乐, 杨胜春, 宋贵宾, 等. 复合材料机械连接强度分析研究[J]. 塑料工业, 2022, 50(3): 90-94. |
| LIANG L L, YANG S C, SONG G B, et al. Analysis of mechanical bonding strength of composite materials[J]. China Plastics Industry, 2022, 50(3): 90-94 (in Chinese). | |
| [6] | 吴义韬, 姚卫星, 沈浩杰. 复合材料宏观强度准则预测能力分析[J]. 复合材料学报, 2015, 32(3): 864-873. |
| WU Y T, YAO W X, SHEN H J. Prediction ability analysis of macroscopic strength criteria for composites[J]. Acta Materiae Compositae Sinica, 2015, 32(3): 864-873 (in Chinese). | |
| [7] | 宁蕙, 谭志勇, 张宏宇. 复合材料螺栓连接结构疲劳问题研究进展[J]. 强度与环境, 2023, 50(3): 1-9. |
| NING H, TAN Z Y, ZHANG H Y. Research progress on fatigue properties of composite bolted structures[J]. Structure & Environment Engineering, 2023, 50(3): 1-9 (in Chinese). | |
| [8] | TALAEI K T, OULD S H, KAABOUCH N. Deep learning: systematic review, models, challenges, and research directions[J]. Neural Computing and Applications, 2023, 35(31): 23103-23124. |
| [9] | 闫海, 邓忠民. 基于深度学习的短纤维增强聚氨酯复合材料性能预测[J]. 复合材料学报, 2019, 36(6): 1413-1420. |
| YAN H, DENG Z M. Prediction of properties of short fiber reinforced urethane polymer composites based on deep learning[J]. Acta Materiae Compositae Sinica, 2019, 36(6): 1413-1420 (in Chinese). | |
| [10] | 刘子琦, 陈刚, SU Zhoucheng, 等. 基于细观力学和机器学习的纤维增强复合材料热-力多物理性能预测[J/OL]. 复合材料学报, 2025: 1-17. (2025-03-12). . |
| LIU Z Q, CHEN G, SU Z C, et al. Thermo-mechanical multiphysical properties prediction of fiber-reinforced composites based on micromechanics and machine learning[J/OL]. Acta Materiae Compositae Sinica, 2025: 1-17. (2025-03-12). (in Chinese). | |
| [11] | 彭凡, 邹司农, 任毅如. 基于深度学习的复合材料螺栓连接失效预测[J]. 机械强度, 2023, 45(2): 447-453. |
| PENG F, ZOU S N, REN Y R. Failure prediction of bolted connection of composite materials based on deep learning[J]. Journal of Mechanical Strength, 2023, 45(2): 447-453 (in Chinese). | |
| [12] | YANG Z Z, YU C H, GUO K, et al. End-to-end deep learning method to predict complete strain and stress tensors for complex hierarchical composite microstructures[J]. Journal of the Mechanics and Physics of Solids, 2021, 154: 104506. |
| [13] | SEPASDAR R, KARPATNE A, SHAKIBA M. A data-driven approach to full-field nonlinear stress distribution and failure pattern prediction in composites using deep learning[J]. Computer Methods in Applied Mechanics and Engineering, 2022, 397: 115126. |
| [14] | ZHANG Y, TI?O P, LEONARDIS A, et al. A survey on neural network interpretability[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2021, 5(5): 726-742. |
| [15] | 严如强, 商佐港, 王志颖, 等. 可解释人工智能在工业智能诊断中的挑战和机遇: 先验赋能[J]. 机械工程学报, 2024, 60(12): 1-20. |
| YAN R Q, SHANG Z G, WANG Z Y, et al. Challenges and opportunities of XAI in industrial intelligent diagnosis: priori-empowered[J]. Journal of Mechanical Engineering, 2024, 60(12): 1-20 (in Chinese). | |
| [16] | WANG W X, THAI H T. A physics-informed neural network framework for laminated composite plates under bending[J]. Thin-Walled Structures, 2025, 210: 113014. |
| [17] | HEDAYATRASA S, FINK O, VAN PAEPEGEM W, et al. K-space physics-informed neural network (k-PINN) for compressed spectral mapping and efficient inversion of vibrations in thin composite laminates[J]. Mechanical Systems and Signal Processing, 2025, 223: 111920. |
| [18] | LINGHU J, GAO W F, DONG H, et al. Higher-order multi-scale physics-informed neural network (HOMS-PINN) method and its convergence analysis for solving elastic problems of authentic composite materials[J]. Journal of Computational and Applied Mathematics, 2025, 456: 116223. |
| [19] | LI Y, WAN D T, WANG Z, et al. Physics-constrained deep learning approach for solving inverse problems in composite laminated plates[J]. Composite Structures, 2024, 348: 118514. |
| [20] | YAO L J, WANG J X, CHUAI M Y, et al. Physics-informed machine learning for loading history dependent fatigue delamination of composite laminates[J]. Composites Part A: Applied Science and Manufacturing, 2024, 187: 108474. |
| [21] | ZHOU K, SUN H T, ENOS R, et al. Harnessing deep learning for physics-informed prediction of composite strength with microstructural uncertainties[J]. Computational Materials Science, 2021, 197: 110663. |
| [22] | SHEN Y A, HAN Z L, LIANG Y C, et al. Mesh reduction methods for thermoelasticity of laminated composite structures: Study on the B-spline based state space finite element method and physics-informed neural networks[J]. Engineering Analysis with Boundary Elements, 2023, 156: 475-487. |
| [23] | 杜轲, 林志鹏, 吴文贤, 等. 物理信息神经网络方法求解平面应力问题[J]. 固体力学学报, 2025, 46(2): 230-243. |
| DU K, LIN Z P, WU W X, et al. Physics-informed neural network method for solving plane stress problems[J]. Chinese Journal of Solid Mechanics, 2025, 46(2): 230-243 (in Chinese). | |
| [24] | 田松岩, 黄鑫格, 段焰辉, 等. 面向流体力学的物理神经网络综述[J]. 计算机应用, 2024, 44(): 133-141. |
| TIAN S Y, HUANG X G, DUAN Y H, et al. A survey of physical neural networks oriented to fluid mechanics[J]. Journal of Computer Applications, 2024, 44(Sup 1): 133-141 (in Chinese). | |
| [25] | 王飞, 党浩宁, 尚勇, 等. 从传统数值方法到神经网络: 偏微分方程数值解的演进与展望[J]. 现代应用物理, 2025, 16(1): 41-66. |
| WANG F, DANG H N, SHANG Y, et al. From traditional numerical methods to neural networks: evolution and prospect of numerical solution of partial differential equations[J]. Modern Applied Physics, 2025, 16(1): 41-66 (in Chinese). | |
| [26] | 杨显昆, 郑锡涛, 成李南, 等. 复合材料层合板单钉双剪连接挤压强度的一种工程估算方法[J]. 复合材料学报, 2012, 29(6): 225-229. |
| YANG X K, ZHENG X T, CHENG L N, et al. An engineering approach to predict the bearing strength of single-bolted double-lapped joints in composite laminate[J]. Acta Materiae Compositae Sinica, 2012, 29(6): 225-229 (in Chinese). |
/
| 〈 |
|
〉 |