航空学报2026，Vol.47Issue(5)：157-170,14.DOI:10.7527/S1000-6893.2025.32422
基于MCI-PINN的复合材料螺栓连接结构挤压强度预测
Prediction of bearing strength for composite bolted joint structures based on MCI-PINN
摘要
Abstract
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 ob-scures 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 esti-mation 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 pa-rameters,mechanical parameters,structural parameters,and extrusion strength are established,and the mapping re-lationship 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 extru-sion 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.关键词
非线性辨识/物理信息神经网络/复合材料/挤压强度/性能预测Key words
nonlinear identification/physics-informed neural network/composite/extrusion strength/performance prediction分类
航空航天引用本文复制引用
刘月,任翰韬,薛小锋,宋祉岑,路成,冯蕴雯..基于MCI-PINN的复合材料螺栓连接结构挤压强度预测[J].航空学报,2026,47(5):157-170,14.基金项目
国家商用飞机制造工程技术研究中心创新基金(COMAC-SFGS-2023-2353) National Commercial Aircraft Manufacturing Engineering and Technology Research Center Innovation Fund(COMAC-SFGS-2023-2353) （COMAC-SFGS-2023-2353）
