| Título: | Bayesian Neural Network of Rolling Force Prediction for Hot-Strip Mill |
| Autores: |
Zhang, Xiaodan; Beihua University LI, Rui; USTB YE, Yanliang; Beihua University |
| Fecha: | 2014-05-01 |
| Publicador: | TELKOMNIKA: Indonesian journal of electrical engineering |
| Fuente: |
 |
| Tipo: |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| Tema: |
Electrical and Information Engineering Department Beihua University, Jilin,132013, P. R. China Hot continuous rolling, Rolling force prediction, Neural network, Bayesian regularization |
| Descripción: | For obtaining relative accurate rolling-mill model is difficulty by the simple mathematical method, due to the complexity of the actual production scene and the non-linear relationship between variables, this paper firstly proposes an improved Bayesian regularization neural network model according to these measured data of 1580 production line. In this model, the paper constructs the improved Bayesian neural networks by the introduction of bound terms that represents the network complexity in the objective function. At last, the simulation result proves the effectiveness and validity of the model and the prediction accuracy of the model algorithm is superior to the traditional model. |
| Idioma: | No aplica |