Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network

In this study, some physical and mechanical properties of yellow pine wood (Pinus sylvestris), which is used extensively in furniture industry, were tested after heat treatment. The findings obtained modelled by artificial neural network (ANN) interval values related to temperature time variations tried be estimated. This makes it easier reach intermediate values, aims save the relevant researchers from trial load all heating parameters during design/production stages. study scotch samples heat-treated at 150, 160, 170, 180, 190 200 °C for 2, 4 6 hours, under normal atmosphere conditions. Color changes, weight losses compression strength parallel grain determined. After experimental modelling procedure was performed ANN using two different learning algorithm- Levenberg-Marquardt (LM) Scaled Conjugate Gradient (SCG) 15 hidden neurons. best model 2-7-6 structure LM algorithm. Mean absolute percentage error (MAPE) found below 8.0% estimated color parameters. loss 5.79% 1.50%, respectively. It concluded that can successfully predict studied samples.