DOI QR코드

DOI QR Code

금형의 절삭가공에서 이론 모형 기반 표면거칠기 예측 결과의 실험적 모형 전환을 위한 인공신경망 구축에 대한 연구

A Study on the Construction of an Artificial Neural Network for the Experimental Model Transition of Surface Roughness Prediction Results based on Theoretical Models in Mold Machining

  • 김지우 (국립한국교통대학교 기계공학과) ;
  • 이동원 (인하대학교 기계공학과) ;
  • 김종선 (한국생산기술연구원 금형성형연구부문) ;
  • 김종수 (한국생산기술연구원 금형성형연구부문)
  • Ji-Woo Kim (Dept. of Mechanical Eng., Korea Nat'l Univ. of Transportation) ;
  • Dong-Won Lee (Dept. of Mechanical Eng., Inha Univ.) ;
  • Jong-Sun Kim (Korea Inst. of Industrial Technology) ;
  • Jong-Su Kim (Korea Inst. of Industrial Technology)
  • 투고 : 2023.12.14
  • 심사 : 2023.12.31
  • 발행 : 2023.12.31

초록

In the fabrication of curved multi-display glass for automotive use, the surface roughness of the mold is a critical quality factor. However, the difficulty in detecting micro-cutting signals in a micro-machining environment and the absence of a standardized model for predicting micro-cutting forces make it challenging to intuitively infer the correlation between cutting variables and actual surface roughness under machining conditions. Consequently, current practices heavily rely on machining condition optimization through the utilization of cutting models and experimental research for force prediction. To overcome these limitations, this study employs a surface roughness prediction formula instead of a cutting force prediction model and converts the surface roughness prediction formula into experimental data. Additionally, to account for changes in surface roughness during machining runtime, the theory of position variables has been introduced. By leveraging artificial neural network technology, the accuracy of the surface roughness prediction formula model has improved by 98%. Through the application of artificial neural network technology, the surface roughness prediction formula model, with enhanced accuracy, is anticipated to reliably perform the derivation of optimal machining conditions and the prediction of surface roughness in various machining environments at the analytical stage.

키워드

과제정보

본 연구는 2023년도 산업통상자원부의 '기계산업핵심기술개발 (No. 20023669, KM230303)' 사업의 지원을 받아 연구되었습니다.

참고문헌

  1. Lee, D. W., Lee, H. H., Kim, J. S., Kim, J. S., A Study on the Surface Roughness Analysis by Cutting Condition in Machining of STAVAX mold for Vehicle Light Guide, Korean Society of Mechanical Technology, Vol. 24:6, 1106-1112, 2022.
  2. Lee, D. W., Lee, H. H., Kim, J. S., Kim, J. S., A study on surface roughness depending on cutting direction and cutting fluid type during micro-milling on STAVAX steel, Design & Manufacturing, Vol. 17:2, 22-26, 2023. https://doi.org/10.22847/KSDME.17.2.202306.004
  3. Kim, J. S., A study on the surface roughness of STD11 material according to the helix angle of ball endmill, Design & Manufacturing, vol. 17:1, 33-39, 2023.
  4. Hossain, M. S. J., Ahmad, N. Artificial intelligence based surface roughness prediction modeling for three dimensional end milling. Int. J. Adv. Sci. Technol., Vol. 45:8, 1-18. 2012.
  5. Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., Talwalkar, A., Hyperband: A novel bandit-based approach to hyper-parameter optimization. J. Mach. Learn. Res. Vol. 18, 6765-6816. 2017.
  6. Lee, J. H., Kim, J. S., A study on the construction of the quality prediction model by artificial neural intelligence through integrated learning of CAE-based data and experimental data in the injection molding process, Design & Manufacturing, Vol. 15:4, 24-31, 2021.
  7. Lee, J. H., Kim, J. S., A study on the accuracy of multi-task learning structure artificial neural network applicable to multi-quality prediction in injection molding process, Design & Manufacturing, Vol. 16:3, 1-8, 2022.
  8. Kingma, D. P., Ba, J., Adam: A method for stochastic optimization., arXiv, 2014.