DOI QR코드

DOI QR Code

사출성형공정에서 데이터의 불균형 해소를 위한 담금질모사

Simulated Annealing for Overcoming Data Imbalance in Mold Injection Process

  • 이동주 (공주대학교 산업시스템공학과)
  • Dongju, Lee (Department of Industrial & Systems Engineering, Kongju National University)
  • 투고 : 2022.12.03
  • 심사 : 2022.12.20
  • 발행 : 2022.12.31

초록

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

키워드

참고문헌

  1. Chawla, N.V., Bowyer, K.W., Hall, L.O., and Kegelmeyer, W.P., SMOTE: Synthetic Minority Over-sampling Technique, Journal of Artificial Intelligence Research, 2002, Vol. 16, pp. 321-357.  https://doi.org/10.1613/jair.953
  2. Chen, Z., Yan, Q., Han, H., Wang, S., Peng, L., Wang, L., and Yang, B., Machine learning based mobile malware detection using highly imbalanced network traffic, Information Science, 2018, Vol. 433, pp. 346-364.  https://doi.org/10.1016/j.ins.2017.04.044
  3. Cheong, Y.-G., Park, K., Kim, H., Kim, J., and Huun, S., Machine Learning Based Intrusion Detection Systems for Class Imbalanced Datasets, Journal of The Korea Institute of Information Security & Cryptology, 2017, Vol. 27, No. 6, pp. 1385-1395.  https://doi.org/10.13089/JKIISC.2017.27.6.1385
  4. Han, H., Wang, W.-Y., and Mao B.-H., Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning, Proceedings of ICIC 2005: Advances in Intelligent Computing, 2005, pp. 878-887. 
  5. Jang, Y.S., Kim, J.W., and Hur, J., Combined Application of Data Imbalance Reduction Technique Using Genetic Algorithm, Journal of Intelligence and Information Systems, 2008, Vol. 14, No. 3, pp. 133-154. 
  6. Jung, H.N., Lee, J.-H., and Jun, C.-H., A Data Mining Procedure for Unbalanced Binary Classification, Journal of the Korean Institute of Industrial Engineers, 2010, Vol. 36, No. 1, pp. 13-21. 
  7. Kim, H.S. and Lee, H.S., Generative Adversarial Networks based Data Generation Framework for Overcoming Imbalanced Manufacturing Process Data, J. of Korean Ins. of Intell. Syst., 2019, Vol. 29, No. 1, pp. 1-8.  https://doi.org/10.5391/jkiis.2019.29.1.1
  8. Kirkpatrick, S., Gelatt, C.D., and Vecchi, M.P., Optimization by Simulated Annealing, Science, 1983, Vol. 220, No. 4598, pp. 671-680.  https://doi.org/10.1126/science.220.4598.671
  9. Lee, J.S. and Kwon, J.G., A Hybrid SVM Classifier for Imbalanced Data Sets, J. Intell. Inform. Syst., 2013, Vol. 19, No. 2, pp. 125-140.  https://doi.org/10.13088/JIIS.2013.19.2.125
  10. Lee, K.N., Lim, J., Bok, K., and Yoo, J., Handling Method of Imbalance Data for Machine Learning : Focused on Sampling, The Journal of the Korea Contents Association, 2019, Vol. 19, No. 11, pp. 567-577.  https://doi.org/10.5392/JKCA.2019.19.11.567
  11. Ministry of SMEs and Startups, Korea AI Manufacturing Platform(KAMP), CNC Machine AI Dataset, KAIST(UNIST, EPM Solutions), 2020.12.14., https://kamp-ai.kr. 
  12. Shin, S.S., Cho, H.Y., and Kim, Y.H., Optimal Ratio of Data Oversampling Based on a Genetic Algorithm for Overcoming Data Imbalance, J. of the Korea Convergence Society, 2021, Vol. 12, No. 1, pp. 49-55.  https://doi.org/10.15207/JKCS.2021.12.1.049
  13. Son, M.J., Jung, S.W., and Hwang, E.J., A Deep Learning Based Over-Sampling Scheme for Imbalanced Data Classification, KIPS Trans. Softw. And Data Eng., 2019, Vol. 8, No. 7, pp. 311-316. https://doi.org/10.3745/KTSDE.2019.8.7.311