基于LSTM的航空发动机排气温度预测

Aero Engine Exhaust Gas Temperature Prediction Based on LSTM

为了提高航空发动机排气温度的预测精度,提出了基于LSTM的航空发动机排气温度预测方法;采用LSTM构建航空发动机排气温度预测模型,利用包含前向计算和误差反传更新的按时间展开的反向传播算法训练预测模型,探究排气温度随飞机运行时间的变化规律,实现对排气温度未来时刻数据的预测;实例验证结果表明,LSTM适用于航空发动机排气温度预测研究,相较于RNN和SVM方法能获得更高的预测精度。

In order to improve the prediction accuracy of aero engine exhaust gas temperature,a method based on LSTM is proposed,and a prediction model based on LSTM is constructed. Then use back propagation Through Time algorithm to finished the prediction model training for explore the varying with plane running time of exhaust gas temperature and realize exhaust gas temperature prediction,which contained forward computing and error reverse transfer update. The example verification results show the proposed method is feasible for aero engine exhaust gas temperature prediction study,and it can get higher prediction accuracy than RNN and SVM method.