Study on Advance Prediction Model of Exhaust Gas Temperature Based on LSTM

The advance prediction of exhaust gas temperature (EGT) can judge the performance states of the engine in advance and provide decision supports for engine fault diagnosis and preventive maintenance, which is of great significance for the normal operation of the engine and the safety of aircraft. In this paper, a prediction model based on LSTM is proposed to realize the advance prediction of EGT. Firstly, the principle of LSTM model is introduced. Secondly, the modeling and training process of EGT advance prediction model based on LSTM is discussed. Finally, by using the QAR data of A320, a case study is carried out. The results of case study show that the model in this paper can realize the advance prediction of EGT effectively.