Aeroengine Remaining Life Prediction Using Feature Selection and Improved SE Blocks

Table 2

Comparison of ablation experiment results.

Dataset	FD001		FD002		FD003		FD004
Evaluation	RMSE	Score	RMSE	Score	RMSE	Score	RMSE	Score
CNN	14.75	433.3	17.95	3124.7	13.58	398.0	20.23	5803.9
RF_CNN	14.69	416.5	17.84	3045.2	13.50	344.3	20.19	3488.3
RF_SE_CNN	14.51	373.0	17.76	2380.7	13.55	351.8	19.94	4442.5
Our method	13.46	265.9	16.54	1465.1	11.79	222.0	19.39	2036.2

The bold contents represent the optimal experimental results. The ablation experiments show that our proposed method can effectively improve the prediction performance of the model.