DOI QR코드

DOI QR Code

A Study on the Improvement of Injection Molding Process Using CAE and Decision-tree

CAE와 Decision-tree를 이용한 사출성형 공정개선에 관한 연구

  • Hwang, Soonhwan (Department of Smart Convergence Consulting, Hansung University) ;
  • Han, Seong-Ryeol (Department of Metalmold Design Engineering, Kongju National University) ;
  • Lee, Hoojin (Department of Smart Convergence Consulting, Hansung University)
  • 황순환 (한성대학교 스마트융합컨설팅학과) ;
  • 한성렬 (공주대학교 금형설계공학과) ;
  • 이후진 (한성대학교 스마트융합컨설팅학과)
  • Received : 2021.01.06
  • Accepted : 2021.04.02
  • Published : 2021.04.30

Abstract

The CAT methodology is a numerical analysis technique using CAE. Recently, a methodology of applying artificial intelligence techniques to a simulation has been studied. A previous study compared the deformation results according to the injection molding process using a machine learning technique. Although MLP has excellent prediction performance, it lacks an explanation of the decision process and is like a black box. In this study, data was generated using Autodesk Moldflow 2018, an injection molding analysis software. Several Machine Learning Algorithms models were developed using RapidMiner version 9.5, a machine learning platform software, and the root mean square error was compared. The decision-tree showed better prediction performance than other machine learning techniques with the RMSE values. The classification criterion can be increased according to the Maximal Depth that determines the size of the Decision-tree, but the complexity also increases. The simulation showed that by selecting an intermediate value that satisfies the constraint based on the changed position, there was 7.7% improvement compared to the previous simulation.

현재 사출성형분야의 Computer Aided Testing(CAT) 방법론으로 CAE(Computer Aided Engineering)를 이용한 수치 해석 기법이 주를 이루고 있다. 그러나 최근 시뮬레이션에 추가로 인공지능 기법을 응용하는 방법론이 연구되고 있다. 우리는 지난 연구에서 다양한 Machine Learning 기법을 활용하여 사출 성형 공정에 따른 변형 결과를 비교하였으며, 최종적으로 MLP(Multi-Layer Perceptron) 예측모델을 생성하였고, HMA(Hybrid Metaheuristic Algorithm)를 이용하여 최적화 결과를 얻어냈다. 그러나 MLP는 예측 성능이 우수한 반면 블랙박스와 같이 결정 과정에 대한 설명이 부족하다. 본 연구에서는 Radiator Tank 부품에 대하여 사출 성형 해석 소프트웨어인 Autodesk Moldflow 2018을 이용하여 수치 해석 기법으로 데이터를 생성하고, Machine Learning 소프트웨어인 RapidMiner Studio version 9.5를 활용하여 여러 Machine Learning Algorithms 모델을 생성하여 평균 제곱근 오차를 비교하였다. Decision-tree는 Root Mean Square Error(RMSE) 값이 다른 Machine Learning 기법에 비해 양호한 예측 성능을 갖추고 있었다. Decision-tree의 크기를 결정하는 Maximal Depth에 따라 분류 기준을 높일 수 있지만 복잡성도 함께 증가시켰다. Decision-tree를 이용하여 구속 조건을 만족하는 중간 값을 선정하여 시뮬레이션을 진행한 결과 기존의 시뮬레이션만 진행한 것보다 7.7%의 개선 효과가 있었다.

Keywords

References

  1. S. H. Hwang, J. S. Kim, "Injection mold design of reverse engineering using injection molding analysis and machine learning", Journal of Mechanical Science and Technology, Vol.8, pp.3803-3812, 2019. DOI: https://doi.org/10.1007/s12206-019-0723-1
  2. D. Kozjeka, R. Vrabica, D. Kraljb, P. Butalaa, N. Lavracc, "Data mining for fault diagnostics: A case for plastic injection molding", Procedia CIRP, Vol.81, pp.809-814, 2019 DOI: https://doi.org/10.1016/j.procir.2019.03.204
  3. K. C. Ke, M. S. Huang, "Quality prediction for injection molding by using a multilayer perceptron neural network", Polymers, Vol.12, pp.1812, August, 2020 DOI: https://doi.org/10.3390/polym12081812
  4. A. K. Kim, K. H Oh, J. Y Jung, B. H Kim, "Imbalanced classification of manufacturing quality conditions using cost-sensitive Decision-tree ensembles", International Journal of Computer Integrated Manufacturing, pp.701-717, Dec, 2017 DOI: https://doi.org/10.1080/0951192X.2017.1407447
  5. O. Ogorodnyk, O. V. Lyngstad, M. Larsen, K. Wang, K. Martinsen, "Application of machine learning methods for prediction of parts quality in thermoplastics injection molding", International Workshop of Advanced Manufacturing and Automation, pp.237-244, Dec, 2018 DOI: https://doi.org/10.1080/0951192X.2017.1407447
  6. S. H. Hwang, S. H. Park, S. J. Hwang, J. H. Lee, Moldflow Basic Course, Chung-Dam Books, Korea, pp.378-383, 2018
  7. Training and Test Sets: Splitting Data, Machine Learning Crash Course[Internet], Available From: https://developers.google.com/machine-learning/crash-course/training-and-test-sets/splitting-data?hl=ko (accessed Dec. 20, 2020)
  8. Descending into ML: Training and Loss, Machine Learning Crash Course[Internet], Available From: https://developers.google.com/machine-learning/crash-course/descending-into-ml/training-and-loss (accessed Dec. 20, 2020)