Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

A Study on Optimal Solution of Short Shot Using Fuzzy Logic Based Neural Network(FNN)

퍼지-신경망을 이용한 미성형 사출제품의 최적해결에 관한 연구

  • Kang, Seong-Nam (Dept. of Mechanical Eng., Korea University of Technology and Education) ;
  • Huh, Yong-Jeong (School of Mechatronics Eng., Korea University of Technology and Education) ;
  • Cho, Hyun-Chan (School of Information Technology, Korea University of Technology and Education)
  • Published : 2001.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

In injection molding, short shot is one of the frequent and fatal defects. Experts of injection molding usually adjust process conditions such as injection time, mold temperature, and melt temperature because it is the most economic way in time and cost. However it is a difficult task to find appropriate process conditions for troubleshooting of short shot as injection molding process is a highly nonlinear system and process conditions are coupled. In this paper, a fuzzy neural network(FNN) has been applied to injection molding process to shorten troubleshooting time of short shot. Based on melt temperature and fill time, a reasonable initial mold temperature is recommended by the FNN, and then the mold temperature is inputted to injection molding process. Depending on injection molding result, specifically the insufficient quantity of an injection molded part, an appropriate mold temperature is recommend repeatedly through the FNN.

Keywords