Bayesian Neural Network of Rolling Force Prediction for Hot-Strip Mill

Xiaodan Zhang, Rui LI, Yanliang YE

Abstract


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.

 

DOI : http://dx.doi.org/10.11591/telkomnika.v12i5.5097


Keywords


Hot continuous rolling, Rolling force prediction, Neural network, Bayesian regularization

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics