航空学报2026，Vol.47Issue(12)：328-348,21.DOI:10.7527/S1000-6893.2025.32866
融合多源数据的防热多孔材料渗透率预测方法
Permeability prediction method for thermal protective porous materials by integrating multi-source data
摘要
Abstract
Ablative thermal protection is an important thermal protection method for hypersonic vehicles.Porous pyro-lyzed carbon for thermal protection materials are a type of ablative thermal protective material,whose permeability sig-nificantly influences transport characteristics.To address the issue of difficulty in obtaining empirical coefficients in per-meability formulas for thermal protective porous materials,a multi-source heterogeneous dataset is constructed,incor-porating material microstructure images and macroscopic structural characteristic parameters(maximum flow and frac-tal dimension).A particle-based method named direct simulation Monte Carlo is employed to calculate the permeabil-ity of the microstructure.Based on this,three permeability prediction methods using multi-source heterogeneous data fusion strategies are proposed:a decision-level fusion strategy,a fusion strategy based on direct concatenation of multi-source data features,and a fusion strategy based on a cross-modal attention mechanism for multi-source data.By comparing the predictive performance of the three fusion strategies,the strategy based on the cross-modal atten-tion mechanism demonstrates the best performance.This strategy captures the relationship between image convolu-tional features and structural parameters and dynamically adjusts the weights between them.On the test set,the coef-ficient of determination is 0.949 7,and the Mean Absolute Percentage Error is 5.29%.Compared with single-source data-driven permeability prediction models,the coefficient of determination improves by 6%,and the Mean Absolute Percentage Error decreases by 41%.This method enables efficient and accurate prediction of permeability,providing technical support for the refined design of thermal protection structures in actual hypersonic vehicles.关键词
防热多孔材料/多源异构数据融合/渗透率/深度学习/多尺度表征Key words
thermal protective porous materials/multi-source heterogeneous data fusion/permeability/deep learning/multi-scale characterization分类
航空航天引用本文复制引用
辛炜华,田宇豪,张起鸣,郭京辉,林贵平..融合多源数据的防热多孔材料渗透率预测方法[J].航空学报,2026,47(12):328-348,21.基金项目
国家自然科学基金(12572380) （12572380）
中央高校基本科研业务费专项资金(501XYGG2025105029) National Natural Science Foundation of China(12572380) （501XYGG2025105029）
the Fundamental Research Funds for the Central Universities(501XYGG2025105029) （501XYGG2025105029）
