重庆理工大学学报（自然科学版）2025，Vol.39Issue(3)：154-162,9.DOI:10.3969/j.issn.1674-8425(z).2025.02.019
航空管路无扩口管接头寿命预测方法研究
Study on life prediction method of aviation flareless pipe joint
摘要
Abstract
To improve the accuracy and efficiency of degradation prediction for flareless joints of aviation pipelines,we propose a feature fusion model based on Temporal Convolutional Network(TCN)and Transformer.First,it extracts the enhanced feature information through the TCN module,and then uses the fusion convolutional Transformer module for further processing,adding a pooling layer at the end of the encoder to reduce the risk of overfitting,and finally obtains the prediction results through the fully connected layer.In order to verify the effectiveness of our method,the unidirectional fluid-structure coupling method is employed to build the leakage rate model and obtain the data for the sealing performance of the flareless joints of aviation pipelines.Our results show compared with those of CNN,RNN,LSTM and Transformer models,the prediction error of our model decreases by 3.53％,6.08％,1.63％and 1.75％respectively,effectively improving the accuracy of the degradation prediction of flareless joints of aviation pipelines.Thus,our model is of great significance for the safe flight of aircraft.关键词
时间序列预测/密封特性/TCN/Transformer/寿命预测Key words
time series prediction/sealing characteristics/TCN/Transformer/life prediction分类
信息技术与安全科学引用本文复制引用
唐杰,孙茹..航空管路无扩口管接头寿命预测方法研究[J].重庆理工大学学报（自然科学版）,2025,39(3):154-162,9.基金项目
国家自然科学基金中国民航联合重点项目(U2233212) （U2233212）
中国民航大学实验技术创新基金项目(2023YJSKC01019) （2023YJSKC01019）
