Research and analysis of pipe extrusion process prediction model based on SAA-BPNN

Abstract

Substituting plastic for steel in automotive piping is an important indicator for achieving lightweight vehicle. Research on high-precision and high-quality plastic piping has become a hot spot now. In the production process of plastic pipes, the extrusion production process is the most complicated, with the most influencing factors, and the most difficult to establish an accurate mathematical model. Therefore, establishing an accurate prediction model of the extrusion system is the key to improving its control accuracy. Based on this, this paper studies a back-propagation neural network (SSA-BP) optimized based on the Sparrow search algorithm, which takes the melt temperature, melt pressure, screw speed and traction speed of the production line as input variables, and pipe wall thickness as output variables. The prediction result uses the average absolute error, the mean square error and the average absolute percentage error as evaluation indicators. By comparing the prediction results of the SSA-BP algorithm and the BP algorithm, it is finally concluded that the SSA-BP algorithm has a higher prediction accuracy.