Decision-making for structural parameters of injection mold gating system based on agent model and intelligent algorithm

For the flat plastic parts with the size range of 200 to 1300 mm, the structural parameters decision model of injection mold gating system is established in this paper. Firstly, the relationship between the warpage and the structural parameters of gating system is fitted by Kriging model, and the mi...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of advanced manufacturing technology Vol. 119; no. 11-12; pp. 7599 - 7614
Main Authors Chu, Hongyan, Liu, Zhijian, Zhang, Caixia, Liu, Zhifeng, Zhao, Yongsheng, Yang, Congbin
Format Journal Article
LanguageEnglish
Published London Springer London 01.04.2022
Springer Nature B.V
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:For the flat plastic parts with the size range of 200 to 1300 mm, the structural parameters decision model of injection mold gating system is established in this paper. Firstly, the relationship between the warpage and the structural parameters of gating system is fitted by Kriging model, and the minimum warpage is optimized by genetic algorithm (GA) to obtain the best structural parameters. Secondly, the best structural parameters of gating system corresponding to 16 groups of plastic parts are taken as samples, and the relationship between the structural parameters of gating system and the size parameters of plastic parts is established by Kriging model. In addition, K-means is used to reduce the number of the structural parameters of gating system from 5 to 2, in order to improve the accuracy of decision model. Finally, the size parameters of plastic parts are input to the decision model to obtain the structural parameters of gating system. Through the verification of mold flow analysis experiment, the structural parameters of gating system obtained by this method meet the design requirements and can effectively shorten the structural design cycle of injection mold.
ISSN:0268-3768
1433-3015
DOI:10.1007/s00170-022-08756-6