Akademik Veri Yönetim Sistemi
JOURNAL OF ADHESION SCIENCE AND TECHNOLOGY, cilt.29, sa.23, ss.2521-2536, 2015 (SCI-Expanded)
Adhesive bond strength of solid wood plays a key role in the efficient use of wood in a large number of engineering applications. In this study, the effects of amount of adhesive, pressing pressure, and pressing time on bonding strength of beech wood bonded with polyvinyl acetate adhesive were investigated and predicted by developing an artificial neural network (ANN) model. Experimental results have showed that bonding strength of wood samples increased generally by increasing amount of adhesive, pressing pressure, and pressing time. Besides, ANN analysis has yielded highly satisfactory results. The designed neural network model allows predicting the bonding strength of wood samples with mean absolute percentage error of 2.454% and correlation coefficient of 97.8% for testing phase. It is clear from the results that the model has a good learning and generalization ability. This model therefore can be used to predict bonding strength of beech samples bonded with polyvinyl acetate adhesive under given conditions. Consequently, this study provides beneficial insights for practitioners in terms of the safe and efficient use of wood as an engineering material in applications related to the strength of the bond between wood and adhesive.