PL EN
FRICTION MODELING OF Al-Mg ALLOY SHEETS BASED ON MULTIPLE REGRESSION ANALYSIS AND NEURAL NETWORKS
 
Więcej
Ukryj
1
University of Stavanger, P.O. Box 8600 FORUS, N-4036 Stavanger, Norway
 
2
Department of Materials Forming and Processing, Rzeszow University of Technology, Al. Powstańców Warszawy 8, 35-959 Rzeszów, Poland
 
3
Department of Manufacturing and Production Engineering, Rzeszow University of Technology, Al. Powstańców Warszawy 8, 35-959 Rzeszów, Poland
 
4
Stanisław Pigon State School of Higher Vocational Education in Krosno, ul. Rynek 1, 38-400 Krosno, Poland
 
 
Data publikacji: 01-03-2017
 
 
Autor do korespondencji
Hirpa G. Lemu   

University of Stavanger, P.O. Box 8600 FORUS, N-4036 Stavanger, Norway
 
 
Adv. Sci. Technol. Res. J. 2017; 11(1):48-57
 
SŁOWA KLUCZOWE
DZIEDZINY
 
STRESZCZENIE
This article reports a proposed approach to a frictional resistance description in sheet metal forming processes that enables determination of the friction coefficient value under a wide range of friction conditions without performing time-consuming experiments. The motivation for this proposal is the fact that there exists a considerable amount of factors affect the friction coefficient value and as a result building analytical friction model for specified process conditions is practically impossible. In this proposed approach, a mathematical model of friction behaviour is created using multiple regression analysis and artificial neural networks. The regression analysis was performed using a subroutine in MATLAB programming code and STATISTICA Neural Networks was utilized to build an artificial neural networks model. The effect of different training strategies on the quality of neural networks was studied. As input variables for regression model and training of radial basis function networks, generalized regression neural networks and multilayer networks the results of strip drawing friction test were utilized. Four kinds of Al-Mg alloy sheets were used as a test material.
Journals System - logo
Scroll to top