Use of neural network to evaluate rebar corrosion in continental environment (CROSBI ID 508202)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Ukrainczyk, Neven ; Ukrainczyk, Velimir
engleski
Use of neural network to evaluate rebar corrosion in continental environment
Data on the effects of the structure and properties of concrete onto the degree of damage caused by steel corrosion have been gathered on seven concrete bridge structures in Croatian moderate continental climate. The damages were classified into five categories based on the type of necessary remedial works. The artificial neural network for feature categorization was used as tool for classification of damage and prediciton of damage degree. It was demonstrated that the developed model could predict degree of damage confidently within the observed period. The model is able to recognize and evaluate the effect of individual parameters on the damages. Interactions and sensitivites among parameters were investigated. The developed model could be useful for planning the maintenance of investigated strucutres and design of remedial works.
rebar corrosion; continental climate; damages categorization; simulation; classification artificial neural network
Puni tekst rada objavljen na CD-u.
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
268-268.
2005.
objavljeno
Podaci o matičnoj publikaciji
Banthia, N ; Uomoto, T. ; Bentur, A ; Shah, S. P.
Vancouver: The University of British Columbia
Podaci o skupu
International Conference on Construction Materials : Performance, Innovations and Structural Implications (3 ; 2005)
predavanje
22.08.2005-24.08.2005
Vancouver, Kanada