Design & Manufacturing

Korean Society of Die & Mold Engineering (한국금형공학회)
권호 표지

A study on the prediction of optimized injection molding conditions and the feature selection using the Artificial Neural Network(ANN)

인공신경망을 통한 사출 성형조건의 최적화 예측 및 특성 선택에 관한 연구

  • 양동철 (심테크) ;
  • 김종선 (한국생산기술연구원 금형성형연구부문)
  • Published : 2022.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The qualities of the products produced by injection molding are strongly influenced by the process variables of the injection molding machine set by the engineer. It is very difficult to predict the qualities of the injection molded product considering the stochastic nature of the manufacturing process, since the processing conditions have a complex impact on the quality of the injection molded product. It is recognized that the artificial neural network(ANN) is capable of mapping the intricate relationship between the input and output variables very accurately, therefore, many studies are being conducted to predict the relationship between the results of the product and the process variables using ANN. However in the condition of a small number of data sets, the predicting performance and robustness of the ANN model could be reduced due to too many input variables. In the present study, the ANN model that predicts the length of the injection molded product for multiple combinations of process variables was developed. And the accuracy of each ANN model was compared for 8 process variables and 4 important process inputs that were determined by the feature selection. Based on the comparison, it was verified that the performance of the ANN model increased when only 4 important variables were applied.

Keywords

Acknowledgement

본 연구는 산업통상자원부의 글로벌 시장진출을 위한 프레스사출 복합공정을 이용한 자동차용 커넥터 금형성형기술 개발(Project No. KM220118, 20011822)의 지원으로 진행되었습니다.

References

  1. Xuehong, L. and Khin, L.S., "A statistical experimental study of the injection molding of optical lenses", J. Mater. Proces. Technol., Vol. 113, No. 1-3, pp. 185 195, 2001.
  2. Joseph, B.D., "Injection molds and molding: a practical manual", Springer Science & Business Media, Berlin, 1987.
  3. Yarlagadda, P.K. and Khong C.A.T., “Development of Hybrid Neural Network System for Prediction of Process Parameters in Injection Moulding”, J. Mater. Process. Technol., Vol. 118, No. 1, pp. 109-115, 2001.
  4. Kenig, S., Ben-David, A., Omer, M. and Sadeh, A., “Control of Properties in Injection Molding by Neural Networks”, Eng. Appl. Artif. Intell., Vol. 14, No. 6, pp. 819-823, 2001.
  5. Lau, H.C.W., Ning, A., Pun, K.F. and Chin, K.S., “Neural Networks for the Dimensional Control of Molded Parts based on Reverse Process Model”, J. Mater. Process. Technol., Vol. 117, No. 1, pp. 89-96, 2001.
  6. Shen, C., Wang, L. and Li, Q., “Optimization of Injection Molding Proces Parameters Using Combination of Artifcial Neural Network and Genetic Algorithm Method”, J. Mater. Proces. Technol., Vol. 183, No. 2-3, pp. 412-418, 2007.
  7. Yang, J.B., Shen, K.Q., Ong, C.J. and Li, X.P., "Feature Selection for MLP Neural Network: The Use of Random Permutation of Probailistic Outputs", IEEE Trans. Neural Networks, Vol. 20, No. 12, pp. 1911-1922, 2009. https://doi.org/10.1109/TNN.2009.2032543
  8. Solvason, C.C., Chemmangatuvalapil, N.G., Eljack, F.T. and Eden, M.R., “Efficient Visual Mixture Design of Experiments Using Property Clustering Techniques”, Ind. Eng. Chem. Res., Vol. 48, No. 4, pp. 245-256, 2009.
  9. Leaman, R., Doan, R.T. and Lu, Z., “Disease Name Normalization with Pairwise Learning to Rank”, Bioinf., Vol. 29, No. 22, pp. 2909-2917, 2013.
  10. Goldberg, Y., “Neural Network Methods for Natural Language Processing”, Synth. Lect. Hum. Lang. Technol., Vol. 10, No. 1, pp. 1-309, 2017.
  11. Svozil, D., Kvasnieka, V. and Pospichal. J., "Introduction to multi-layer feed forward neural networks", Chemom. Intell. Lab. Syst., Vol. 39, No. 1, pp. 43 62, 1997.
  12. Prechelt. L., "Automatic early stopping using cross validation: quantifying the criteria", Neural Netw., Vol. 11, No. 4, pp. 761 767, 1998. https://doi.org/10.1016/S0893-6080(98)00010-0