머신러닝 알고리즘 기반 반도체 자동화를 위한 이송로봇 고장진단에 대한 연구

A Study on the Failure Diagnosis of Transfer Robot for Semiconductor Automation Based on Machine Learning Algorithm

  • 김미진 (한국공학대학교 IT반도체융합공학부) ;
  • 고광인 (차세대 융합기술원) ;
  • 구교문 (한국공학대학교 메카트로닉스공학부) ;
  • 심재홍 (한국공학대학교 메카트로닉스공학부) ;
  • 김기현 (한국공학대학교 메카트로닉스공학부)
  • Kim, Mi Jin (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Ko, Kwang In (Advanced Institute of Convergence Technology) ;
  • Ku, Kyo Mun (Department of Mechatronics Engineering, Tech University of Korea) ;
  • Shim, Jae Hong (Department of Mechatronics Engineering, Tech University of Korea) ;
  • Kim, Kihyun (Department of Mechatronics Engineering, Tech University of Korea)
  • 투고 : 2022.11.11
  • 심사 : 2022.12.13
  • 발행 : 2022.12.31

초록

In manufacturing and semiconductor industries, transfer robots increase productivity through accurate and continuous work. Due to the nature of the semiconductor process, there are environments where humans cannot intervene to maintain internal temperature and humidity in a clean room. So, transport robots take responsibility over humans. In such an environment where the manpower of the process is cutting down, the lack of maintenance and management technology of the machine may adversely affect the production, and that's why it is necessary to develop a technology for the machine failure diagnosis system. Therefore, this paper tries to identify various causes of failure of transport robots that are widely used in semiconductor automation, and the Prognostics and Health Management (PHM) method is considered for determining and predicting the process of failures. The robot mainly fails in the driving unit due to long-term repetitive motion, and the core components of the driving unit are motors and gear reducer. A simulation drive unit was manufactured and tested around this component and then applied to 6-axis vertical multi-joint robots used in actual industrial sites. Vibration data was collected for each cause of failure of the robot, and then the collected data was processed through signal processing and frequency analysis. The processed data can determine the fault of the robot by utilizing machine learning algorithms such as SVM (Support Vector Machine) and KNN (K-Nearest Neighbor). As a result, the PHM environment was built based on machine learning algorithms using SVM and KNN, confirming that failure prediction was partially possible.

키워드

과제정보

이 논문은 경기도의 경기도협력연구센터(GRRC)사업[(GRRC TU Korea2020-B02), 이종소재 접합 제조공정 자동화를 위한 로봇 응용기술 개발]과 2022년도 정부(산업통상자원부)와 한국산업기술진흥원의 '한/체코 국제공동기술개발사업(No. P0019623)으로 수행된 연구 결과입니다.

참고문헌

  1. D.J.Choi, J.H.Han., "Comparison of Characteristics of Noise and Vibration Data for Diagnosis of Deep Learning Motor Fault", J. of The Korean Electrical Society. Vol. 39. pp. 46-47, 2019
  2. S.H.Choi, J.K.Park, B.R.Jo, "A Fundamental Study on the Fault Diagnosis Method for Integrated Drive Module of Collaborative Robot based on Artificial Neural Network", ICROS. pp.599~600, 2021
  3. H.Jung, J.W.Kim, "A Machine Learning Approach for Mechanical Motor Fault Diagnosis", J of Korean Society of Industrial and Systems Engineering. Vol.40. pp. 57~64, 2017 https://doi.org/10.11627/jkise.2017.40.1.057
  4. S.Y.Lim, U.H.Jeong, H.W.Lim, "Study on Failure Prediction Method of BLDC Motor Driver", J of Advanced Engineering and Technology. Vol.9. pp.105~109, 2016
  5. Y.H.Lee, K.J.Kim, S.I.Lee, "Seq2Seq model-based prognostics and Health Management of Robot Arm", KIIECT. Vol.12, 2019
  6. S.M.Chun, S.Y.Suk, "Development and Implementation of Smart Manufactruing Big-Data Platform Using Opensource for Failure Prognostics and Diagnosis Technology of Industrial Robot", IEMEK, Vol.14. pp.184~195, 2019
  7. D.S.Kim, T.G.Kim, W.S.Seo, "Development of Collaborative Robot Actuator Reliability Test System for Real Time Monitoring and Fault Detection", The Institute of Electronics and Information Engineers. pp.597~598, 2019
  8. D.H.Ko, W.H.Choi, S.D.Choi, " Failure Prognostics of Start Motor Based on Machine Learning", J of Korean Society of Manufacturing Process Engineers. Vol.20. pp.85~91, 2021
  9. J.S.Choi, "Predictive Maintenance of the Robot Trouble Using The Machine Learning Method", J of the semiconductor & display technology, Vol.19 no.1. pp.1~5, 2020
  10. H.J.Shin, "A Fault Diagnosis Methodology for Module P rocess of TFT-LCD Manufacture Using Support Vector Machines", J of the semiconductor & display technology, Vol.9 no.4, pp.93~97, 2010
  11. S.U.Park, J.H.Han, J.Y.Kim, "Study on Compatibility of Learning Model by Verification of External Motor Failure Noise and Vibration Data", KIEE. Vol.52. pp.1797~1798, 2021
  12. N.J.Kim, Y.C.Bae, "Status Diagnosis of Pump and Motor Applying K-Nearest Neighbors", KIECS. vol.13. pp.1249~1256, 2018
  13. S.I.Kim, Y.J.Noh, "Fault Classification Model Based on Time Domain Feature Extraction of Vibration Data", J of Computational Structural Engineering Institute. Vol.34. pp.25~33, 2021 https://doi.org/10.7734/COSEIK.2021.34.1.25