Table 9 Comparison of life prediction performance of different methods.

From: Deep multiscale feature fusion network with dual attention for rolling bearing remaining useful life prediction

Method

Bearing2_2

Bearing2_5

RMSE

MAE

R2

RMSE

MAE

R2

Transformer-encoder

0.10622

0.09614

0.87133

0.11719

0.09361

0.83622

SE-transformer-encoder

0.12456

0.10782

0.85599

0.16832

0.15123

0.65434

GCU-transformer

0.13046

0.11596

0.85614

0.13621

0.10994

0.77396

TCN-MA

0.10580

0.09077

0.89611

0.25935

0.21668

0.19472

Informer-encoder

0.17937

0.15950

0.65753

0.19575

0.15516

0.53203

This paper

0.05301

0.04159

0.96186

0.07505

0.06182

0.93149

  1. Significance values are bold.
Back to article page