Optimal Modified Starch Content in UF Resin for Glulam Based on Bonding Strength Using Artificial Neural Network

The purpose of this study was to present an application the artificial neural network (ANN) that predicts bonding strength glulam manufactured from plane tree (Platanus orientalis L.) wood layers adhered with a combination modified starch adhesive and UF resin. Bonding measured at different weight ratios containing values nano-zinc oxide as additive under conditions press temperature time. As part research, experimental design determined. According that, specimens were fabricated, measured, results statistically analyzed. Then, model developed predict using technique. To describe results, FTIR TGA tests also conducted. show maximum obtained when WR middle level (50%), content (4%), time fixed 200 °C 22 min, respectively. ANN agreed well results. It became clear prediction errors in acceptable range. indicate could error.