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 8 是否包含联合扰动多样性方法结果比较

Tab.8 Comparison of results of diversity methods with or without joint perturbation

方法 RMSE SCORE FD001 FD003 FD001 FD003 无多样性方法 12.96 14.47 292.00 340.00 多扰动多样性提升 12.00 13.08 282.00 314.00