Journal of the Korean Society for Precision Engineering (한국정밀공학회지)
- Volume 16 Issue 11
- /
- Pages.224-233
- /
- 1999
- /
- 1225-9071(pISSN)
- /
- 2287-8769(eISSN)
A Study on Volumetric Shrinkage of Injection Molded Part by Neural Network
신경회로망을 이용한 사출성형품의 체적수축률에 관한 연구
Abstract
The quality of injection molded parts is affected by the variables such as materials, design variables of part and mold, molding machine, and processing conditions. It is difficult to consider all the variables at the same time to predict the quality. In this paper neural network was applied to analyze the relationship between processing conditions and volumetric shrinkage of part. Engineering plastic gear was used for the study, and the learning data was extracted by the simulation software like Moldflow. Results of neural network was good agreement with simulation results. Nonlinear regression model was formulated using the test data of 3,125 obtained from neural network, Optimal processing conditions were calculated to minimize the volumetric shrinkage of molded part by the application of RQP(Recursive Quadratic Programming) algorithm.
Keywords