A NEW RBF NEURAL NETWORK FOR PREDICTION IN INDUSTRIAL CONTROL

Achraf Jabeur Telmoudi (), Hatem Tlijani, Lotfi Nabli, Maaruf Ali and Radhi M'Hiri
Additional contact information
Achraf Jabeur Telmoudi: Higher Institute of Applied Sciences and Technology, Gafsa University, Campus Universitaire Sidi Ahmed Zarrouk, 2112 Gafsa, Tunisia;
Hatem Tlijani: Higher Institute of Applied Sciences and Technology, Gafsa University, Campus Universitaire Sidi Ahmed Zarrouk, 2112 Gafsa, Tunisia
Lotfi Nabli: ATSI, National Engineering School of Monastir, Monastir University, Rue Ibn Eljazar, 5019 Monastir, Tunisia
Maaruf Ali: Department of Computer Science and Engineering, University of Ha'il, Ha'il, Kingdom of Saudi Arabia
Radhi M'Hiri: Department of Electrical Engineering, Ecole de Technologie Supérieure, University of Quebec, 110 Notre Dame Street West, Montreal, Quebec, Canada H3C1K3, Canada

International Journal of Information Technology & Decision Making (IJITDM), 2012, vol. 11, issue 04, 749-775

Abstract: A novel neural architecture for prediction in industrial control: the 'Double Recurrent Radial Basis Function network' (R2RBF) is introduced for dynamic monitoring and prognosis of industrial processes. Three applications of the R2RBF network on the prediction values confirmed that the proposed architecture minimizes the prediction error. The proposed R2RBF is excited by the recurrence of the output looped neurons on the input layer which produces a dynamic memory on both the input and output layers. Given the learning complexity of neural networks with the use of the back-propagation training method, a simple architecture is proposed consisting of two simple Recurrent Radial Basis Function networks (RRBF). Each RRBF only has the input layer with looped neurons using the sigmoid activation function. The output of the first RRBF also presents an additional input for the second RRBF. An unsupervised learning algorithm is proposed to determine the parameters of the Radial Basis Function (RBF) nodes. TheK-means unsupervised learning algorithm used for the hidden layer is enhanced by the initialization of these input parameters by the output parameters of the RCE algorithm.

Keywords: Neural network; radial basis function; R2RBF; prediction; learning (search for similar items in EconPapers)
Date: 2012
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219622012500198
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijitdm:v:11:y:2012:i:04:n:s0219622012500198

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219622012500198

Access Statistics for this article

International Journal of Information Technology & Decision Making (IJITDM) is currently edited by Yong Shi

More articles in International Journal of Information Technology & Decision Making (IJITDM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().