基于选择性深度神经网络集成的涡扇发动机剩余寿命预测

韩冬阳,林泽宇,郑宇,郑美妹,夏唐斌

Remaining useful life estimation of turbofan engine based on selective ensemble of deep neural networks

Dong-yang HAN,Ze-yu LIN,Yu ZHENG,Mei-mei ZHENG,Tang-bin XIA

表 7 集成模型与个体学习器预测能力比较

Tab.7 Comparison of prediction ability between ensemble model and individual model

方法 RMSE SCORE FD001 FD003 FD001 FD003 LSTM 14.28 16.97 362.00 674.00 CNN 13.32 14.23 324.00 350.00 CNN-LSTM[ 14.01 17.19 354.00 731.00 选择性神经网络集成 12.00 13.08 282.00 314.00