Identification and determination of the effect of factory control variables on the physical and mechanical properties of medium density fiberboard with artificial neural network system

The properties of wood composite products are due to the control variables of factory machines. Identifying these sensitive places is of particular importance, because it allows the operator to be able to adjust the production line and product quality in a completely engineered way. Also, it allows operator to have a more detailed study of material and process behavior. Factory available data are including variables of moisture content of chips, chips density, density Mat, material temperature The amount of glue used in percent, the amount of glue used in kilograms, fiber moisture and press speed, and also properties of density, flexural modulus, modulus of elasticity, internal bonding, board moisture and thickness swelling. The effect of input variables on each of the properties of fiberboard was determined by artificial neural network method. The results show that all of the input variables have affected on the output properties of fiberboard and the order in which the influential variables are depends on the type of properties. The effect of variables such as density Mat is almost greater than other variables. Some input variables, such as the, the amount of glue used in kilograms, have less effect on the properties of fiberboard with medium density, and this variable is considered constant in the production line of some factories. The high correlation between the prediction value and the actual value of the output and its low mean absolute percent error indicates the high validity of the prediction that have a high value of 0.9 and less than 9%, respectively.