The work aims to study the nonlinear relationship between the heat sealing parameters in the heat sealing process of plastic film, and establish a mathematical model which can be used in the heat sealing process of automatic packaging machine. The BP neural network was trained by the additional momentum method under the sample data collected from experimental data to establish the nonlinear mathematical model between the heat sealing parameters. Finally, the neural network was used to predict the heat sealing time, and the interpolation algorithm was used to establish the polynomial mathematical model between the heat sealing temperature and the heat sealing time under the targeted heat sealing strength. Through the combination of interpolation algorithm and neural network, the mathematical relationship between heat sealing temperature and heat sealing time was described accurately; at the same time, the interpolation function realized the simplification of the neural network model, and the error of the both was small. The nonlinear relationship between the heat sealing parameters of packaging materials can be determined in the proposed method, and it can be applied to the heat sealing packaging equipment, which can improve the intelligence level of the equipment.