Application of the Artificial Neural Network to Predict the Bending Strength of the Engineered Laminated Wood Produced Using the Hydrolyzed Soy Protein-Melamine Urea Formaldehyde Copolymer Adhesive

The artificial neural network (ANN) was used to predict the modulus of rupture (MOR) laminated wood products adhered by melamine/urea formaldehyde (MUF) resin with different molar ratios combined weight protein adhesive resulting from alkaline treatment (NaOH) soybean oil meal MUF pressed at temperatures according central composite design (CCD). After making boards and performing mechanical test measure MOR, based on experimental data, statistics such as determination coefficient (R2), root mean square error (RMSE), absolute (MAE) sum squares (SSE) were determined, then suitable algorithm selected determine estimated values. comparing values values, direct interactive effects independent variables MOR determined. results indicated that using algorithms train ANN well, a very good estimate bending strength can be offered least error. In addition, measured strengths FTIR TGA diagnostic analyses, it found replacement bio-based when low F M/U ratios, is maximized if high range temperature during press.