航空科学技术2024，Vol.35Issue(7)：40-48,9.DOI:10.19452/j.issn1007-5453.2024.07.004
基于DAM-QLSTM混合模型的辅助动力装置性能参数预测方法
Prediction Method of Auxiliary Power Unit Performance Parameter Based on DAM-QLSTM Mixed Model
摘要
Abstract
Accurate prediction of the Exhaust Gas Temperature(EGT)of the aircraft Auxiliary Power Unit(APU)can effectively monitor the future operating status of the APU and prevent from safety accidents.An APU exhaust gas temperature prediction model incorporating Dual-stage Attention Mechanism(DAM)and quantile-loss guided Long Short-Term Memory(LSTM)network is proposed.The DAM is introduced to effectively quantify the correlation of input variables with EGT and to enhance the effects of historical key information on the output.Secondly,quantile-loss is used to optimize the loss function of the LSTM network to improve the prediction ability of the model further.The experimental results show that for single-step and multi-step prediction of EGT,the prediction accuracy of the proposed model is improved to a large extent compared with other prediction models,which provides a certain reference for short-term APU performance trend prediction.关键词
辅助动力装置/排气温度/长短期记忆网络/注意力机制/分位数损失Key words
APU/EGT/LSTM/attention mechanism/quantile-loss分类
航空航天引用本文复制引用
王坤,朱一扬..基于DAM-QLSTM混合模型的辅助动力装置性能参数预测方法[J].航空科学技术,2024,35(7):40-48,9.基金项目
国家自然科学基金(62173331) National Natural Science Foundation of China(62173331) （62173331）
