Research Article
Prediction of Bending Force in the Hot Strip Rolling Process Using Multilayer Extreme Learning Machine
Table 2
The RMSE of different activation functions and node number combinations of ELM.
| Activation function | Number of hidden layer node | 10 | 40 | 80 | 90 | 100 | 140 | 180 |
| Radbas | 55.2617 | 19.0126 | 16.1132 | 15.8309 | 15.6568 | 15.2251 | 15.1812 | Sin | 55.2617 | 14.4886 | 13.9327 | 13.7969 | 13.9768 | 14.0701 | 14.4754 | Sigmoid | 55.2617 | 13.8739 | 13.7326 | 13.2417 | 13.7331 | 14.0202 | 14.3876 | Hardlim | 55.2617 | 23.6476 | 19.4240 | 18.5305 | 18.6029 | 17.5579 | 17.3333 | Tribas | 55.2617 | 24.0597 | 18.6536 | 18.1056 | 17.7518 | 17.1867 | 16.6234 |
|
|