Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction Model of CNC Processing Defects Using Machine Learning

머신러닝을 이용한 CNC 가공 불량 발생 예측 모델

  • Han, Yong Hee (Department of Entrepreneurship and Small Business, Soongsil University)
  • 한용희 (숭실대학교 벤처중소기업학과)
  • Received : 2021.11.26
  • Accepted : 2022.02.20
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study proposed an analysis framework for real-time prediction of CNC processing defects using machine learning-based models that are recently attracting attention as processing defect prediction methods, and applied it to CNC machines. Analysis shows that the XGBoost, CatBoost, and LightGBM models have the same best accuracy, precision, recall, F1 score, and AUC, of which the LightGBM model took the shortest execution time. This short run time has practical advantages such as reducing actual system deployment costs, reducing the probability of CNC machine damage due to rapid prediction of defects, and increasing overall CNC machine utilization, confirming that the LightGBM model is the most effective machine learning model for CNC machines with only basic sensors installed. In addition, it was confirmed that classification performance was maximized when an ensemble model consisting of LightGBM, ExtraTrees, k-Nearest Neighbors, and logistic regression models was applied in situations where there are no restrictions on execution time and computing power.

본 연구는 최근 가공 불량 예측 방법으로 주목받고 있는 머신러닝 기반의 모델을 이용하여 CNC 가공 불량 발생의 실시간 예측을 위한 분석 프레임워크를 제안하고, 해당 프레임워크에 기반하여 XGBoost, CatBoost, LightGBM, 랜덤 포레스트, Extra Trees, SVM, k-최근접 이웃, 로지스틱 회귀 모델을 CNC 설비에 기본 내장된 센서들로부터 추출된 데이터에 적용 및 분석하였다. 분석 결과 XGBoost, CatBoost, LightGBM 모델이 동일하게 가장 우수한 정확도, 정밀도, 재현율, F1 점수, AUC 값을 보였으며, 이 중 LightGBM 모델이 소요 실행 시간이 가장 짧은 것으로 나타났다. 이러한 짧은 소요 실행 시간은 실 시스템 구축 비용 절감, 빠른 불량 예측에 따른 CNC 장비 파손 확률 감소, 전체적인 CNC 활용률 증가 등의 실무적 장점을 가지므로 LightGBM 모델이 기본 센서들만 설치된 CNC 설비에 적용 시 가공 불량 예측에 가장 효과적으로 판단된다. 또한 소요 실행 시간 및 컴퓨팅 파워의 제약이 없는 상황에서는 LightGBM, Extra Trees, k-최근접 이웃, 로지스틱 회귀 모형으로 구성된 앙상블 모델을 적용할 경우 분류 성능이 최대화됨을 확인하였다.

Keywords

References

  1. S. H. Kang & S. B. Kim. (2016). Multivariate Monitoring of the Metal Frame Process in Mobile Device Manufacturing, Journal of Korean Institute of Industrial Engineers, 42(6), 395-403. DOI : 10.7232/JKIIE.2016.42.6.395
  2. J. S. Kong. (2018), Optimization of the Tool Life Prediction Using Genetic Algorithm, Journal of the Korea Academia-Industrial cooperation Society, 19(11), 338-343. DOI : 10.5762/KAIS.2018.19.11.338
  3. D. J. Oh, B. S. Sim, & W. Lee. (2021). Tool Wear Monitoring during Milling Using an Autoassociative Neural Network, Transactions of the Korean Society of Mechanical Engineers - A, 45(4), 285-291. DOI : 10.3795/KSME-A.2021.45.4.285
  4. R. Teti, K. Jemielniak, G. O'Donnell, & D. Dornfeld. (2010). Advanced Monitoring of Machining Operations, CIRP Annals, 59(2), 717-739. DOI : 10.1016/j.cirp.2010.05.010
  5. Y. C. Liu, X. F. Hu, & S. X. Sun. (2019, July). Remaining Useful Life Prediction of Cutting Tools Based on Support Vector Regression, IOP Conference Series: Materials Science and Engineering, 576, 1-8. DOI : 10.1088/1757-899X/576/1/012021
  6. P. Stavropoulos, A. Papacharalampopoulos, E. Vasiliadis, & G. Chryssolouris. (2016). Tool Wear Predictability Estimation in Milling Based on Multi-sensorial Data, The International Journal of Advanced Manufacturing Technology, 82(1-4), 509-521. DOI : 10.1007/s00170-015-7317-6
  7. X. Li, A. Djordjevich & P. K. Venuvinod. (2000). Current-sensor-based Feed Cutting Force Intelligent Estimation and Tool Wear Condition Monitoring, IEEE Transactions on Industrial Electronics, 47(3), 697-702. DOI : 10.1109/41.847910
  8. K. Lee, S. Park, S. Sung, & D. Park. (2019). A Study on the Prediction of CNC Tool Wear Using Machine Learning Technique, Journal of the Korea Convergence Society, 10(11), 15-21. DOI : 10.15207/JKCS.2019.10.11.015
  9. J. V. Abellan-Nebot & F. R. Subiron. (2010). A Review of Machining Monitoring Systems Based on Artificial Intelligence Process Models, The International Journal of Advanced Manufacturing Technology, 47(1), 237-257. DOI : 10.1007/s00170-009-2191-8
  10. C. Drouillet, J. Karandikar, C. Nath, A. C. Journeaux, M. El Mansori, & T. Kurfess. (2016). Tool Life Predictions in Milling Using Spindle Power with the Neural Network Technique, Journal of Manufacturing Processes, 22, 161-168. DOI : 10.1016/j.jmapro.2016.03.010
  11. da Silva, R. H. L., M. B. da Silva, & A. Hassui. (2016). A Probabilistic Neural Network Applied in Monitoring Tool Wear in the End Milling Operation via Acoustic Emission and Cutting Power Signals, Machining Science and Technology, 20(3), 386-405. DOI : 10.1080/10910344.2016.1191026
  12. J. A. Duro, J. A. Padget, C. R. Bowen, H. A. Kim, & A. Nassehi. (2016). Multi-sensor Data Fusion Framework for CNC Machining Monitoring, Mechanical Systems and Signal Processing, 66, 505-520. DOI : 10.1016/j.ymssp.2015.04.019
  13. A. J. Torabi, M. J. Er, X. Li, B. S. Lim, L. Zhai, R. J. Oentaryo, & J. M. Zurada. (2013). A Survey on Artificial Intelligence-based Modeling Techniques for High Speed Milling Processes, IEEE Systems Journal, 9(3), 1069-1080. DOI : 10.1109/JSYST.2013.2282479
  14. S. T. Jung, S. H. Kim, H. J. Kim, & S. Y. Baek. (2018). Prediction and Experiments of Cutting Forces in Down Milling of Hardened Mold Steel, Journal of the Korean Society of Manufacturing Technology Engineers, 27(4), 346-350. DOI : 10.7735/ksmte.2018.27.4.346
  15. Ministry of SMEs and Startups of Korea. (2020). CNC Machine AI Dataset. Korea AI Manufacturing Platform (KAMP). https://https://kamp-ai.kr
  16. A. Geron. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O'Reilly Media.