Aeroengine Remaining Life Prediction Using Feature Selection and Improved SE Blocks

Table 3

Comparison with other state-of-the-art methods on the CMPASS dataset.

Dataset	FD001		FD002		FD003		FD004
Evaluation	RMSE	Score	RMSE	Score	RMSE	Score	RMSE	Score
Hybrid [16]	14.53	322.4	NA	NA	NA	NA	27.08	5649.1
DCNN [8]	12.61	274	22.36	10412	12.64	284	23.31	12466
MOBNE [32]	15.04	334	25.05	5585	12.51	422	28.66	6558
Deep LSTM [17]	16.14	338.0	24.49	4450.0	16.18	852.0	28.17	5550.0
BiLSTM [33]	13.65	261	23.18	4130	12.74	317	24.86	5430
SBRNN [34]	13.58	228	19.59	2650	19.16	1727	22.15	2901
BiGRU [35]	12.65	213	18.9	2264	12.5	233	20.5	3610
Tafcn [12]	13.99	336	17.06	1946	12.01	251	19.79	3671
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. This table shows excellent performance by comparing the results of the multiple research methods and comparing our method with other state-of-the-art methods.