Extended Kalman Filter Based Neural Networks Controller For Hot Strip Rolling mill

Journal Article · Thu Jun 12 04:00:00 EDT 2008 · AIP Conference Proceedings

DOI:https://doi.org/10.1063/1.2952985· OSTI ID:21143558

Moussaoui, A K ^[1]; Abbassi, H A; Bouazza, S ^[2]

---

1. Electrical Engineering Laboratory of Guelma (LGEG), BP.401, University of Guelma, 24000 (Algeria)
2. Universite Badji Mokhtar BP 12--23000-Annaba Algerie (Algeria)

The present paper deals with the application of an Extended Kalman filter based adaptive Neural-Network control scheme to improve the performance of a hot strip rolling mill. The suggested Neural Network model was implemented using Bayesian Evidence based training algorithm. The control input was estimated iteratively by an on-line extended Kalman filter updating scheme basing on the inversion of the learned neural networks model. The performance of the controller is evaluated using an accurate model estimated from real rolling mill input/output data, and the usefulness of the suggested method is proved.

• OSTI ID: 21143558
• Journal Information: AIP Conference Proceedings, Journal Name: AIP Conference Proceedings Journal Issue: 1 Vol. 1019; ISSN APCPCS; ISSN 0094-243X
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
ALGORITHMS
CONTROL
CONTROL SYSTEMS
FILTERS
FUZZY LOGIC
MILLING MACHINES
NEURAL NETWORKS
NONLINEAR PROBLEMS
PERFORMANCE
ROLLING