Prediction model and application of biological foaming materials based on BP neural network

Using the mass ratio of ethylene-vinyl acetate to starch, glycerol content and NaHCO₃ content as the input parameters, the tensile strength and resilience as the output parameters, a 3-layer BP (back propagation) neural network were established. The extrusion foaming orthogonal experiment result of the starch were taken as sample to forecast the properties of starch foaming materials. The results show that the BP neural network could accurately predict the properties. Meanwhile, the resilience of foaming material increases with the increase of glycerol content, while the tensile strength decreases with the glycerol content's increasing. When the mass fraction of NaHCO₃ is 3%, the tensile strength reaches its minimum. The results provide information for improving the properties and expanding the application scope of the biomass foaming material.