Research Article
An Improved Recursive ARIMA Method with Recurrent Process for Remaining Useful Life Estimation of Bearings
Table 3
Parameters of ARIMA-R and algorithm associated.
| ARIMA-R | Random forest and rotation forest | AdaBoost and Gradient Boost | ARNN |
| p | 20 | Estimators | 800 | Estimators | 200 | Hidden layer | (10, 30) | q | 20 | | | Max depth | 10 | Activation | ReLU | d | 2 | | | Learning rate | 0.2 | Solver | Adam | r | 2 | | | | | Learning rate | Adaptive |
|
|