基于DAM-QLSTM混合模型的辅助动力装置性能参数预测方法OA

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.