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

Hui Li; Hao Wang; Hailiang Xu; Jianan Li

doi:10.1117/12.2652466

10 November 2022 Research and analysis of pipe extrusion process prediction model based on SAA-BPNN

Hui Li, Hao Wang, Hailiang Xu, Jianan Li

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123310J (2022) https://doi.org/10.1117/12.2652466
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

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.

Citation Download Citation

Hui Li, Hao Wang, Hailiang Xu, and Jianan Li "Research and analysis of pipe extrusion process prediction model based on SAA-BPNN", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123310J (10 November 2022); https://doi.org/10.1117/12.2652466

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available