Modeling of compressive strength parallel to grain of heat treated scotch pine s pomocu umjetne neuronske mreze

• Published in: Drvna industrija p. 347
• Main Authors: Yapici, Fatih, Esen, Rasit, Erkaymaz, Okan, Bas, Hasan
• Format: Journal Article
• Language: English
• Published: Sveuciliste U Zagrebu 01-12-2015
• ISSN: 0012-6772
• DOI: 10.5552/drind.2015.1434

In this study, the compressive strength of heat treated Scotch Pine was modeled using artificial neural network. The compressive strength (CS) value parallel to grain was determined after exposing the wood to heat treatment at temperature of 130, 145, 160, 175, 190 and 205°C for 3, 6, 9, 12 hours. The experimental data was evaluated by using multiple variance analysis. Secondly, the effect of heat treatment on the CS of samples was modeled by using artificial neural network (ANN). Key words: wood, heat treatment, Artificial Neural Network, compressive strength Rad prikazuje numericku proceduru za analizu struktura izradenih od kompleksnih laminata. PostuU radu se obraduje modeliranje tlacne cvrstoce toplinski obradenog drva skotskog bora uz pomoc umjetne neuronske mreze. Vrijednost tlacne cvrstoce (CS) paralelno s vlakancima odredena je nakon toplinske obrade pri temperaturi 130, 145, 160, 175, 190 i 205°C tijekom 3, 6, 9 i 12 sati. Eksperimentalni podaci analizirani su primjenom visestruke analize varijance. Osim toga, ucinak toplinske obrade na tlacnu cvrstocu uzoraka modeliran je uz pomoc umjetne neuronske mreze (ANN). Kljucne rijeci: drvo, toplinska obrada, umjetna neuronska mreza, tlacna cvrstoca