Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Study on the Failure Diagnosis of Robot Joints Using Machine Learning

기계학습을 이용한 로봇 관절부 고장진단에 대한 연구

  • Mi Jin Kim (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Kyo Mun Ku (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Jae Hong Shim (Department of Mechanical Engineering, Tech University of Korea) ;
  • Hyo Young Kim (Department of Mechanical Engineering, Tech University of Korea) ;
  • Kihyun Kim (Department of Mechanical Engineering, Tech University of Korea)
  • 김미진 (한국공학대학교 IT반도체융합공학부) ;
  • 구교문 (한국공학대학교 IT반도체융합공학부) ;
  • 심재홍 (한국공학대학교 메카트로닉스공학부) ;
  • 김효영 (한국공학대학교 메카트로닉스공학부) ;
  • 김기현 (한국공학대학교 메카트로닉스공학부)
  • Received : 2023.11.29
  • Accepted : 2023.12.18
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Maintenance of semiconductor equipment processes is crucial for the continuous growth of the semiconductor market. The process must always be upheld in optimal condition to ensure a smooth supply of numerous parts. Additionally, it is imperative to monitor the status of the robots that play a central role in the process. Just as many senses of organs judge a person's body condition, robots also have numerous sensors that play a role, and like human joints, they can detect the condition first in the joints, which are the driving parts of the robot. Therefore, a normal state test bed and an abnormal state test bed using an aging reducer were constructed by simulating the joint, which is the driving part of the robot. Various sensors such as vibration, torque, encoder, and temperature were attached to accurately diagnose the robot's failure, and the test bed was built with an integrated system to collect and control data simultaneously in real-time. After configuring the user screen and building a database based on the collected data, the characteristic values of normal and abnormal data were analyzed, and machine learning was performed using the KNN (K-Nearest Neighbors) machine learning algorithm. This approach yielded an impressive 94% accuracy in failure diagnosis, underscoring the reliability of both the test bed and the data it produced.

Keywords

Acknowledgement

이 논문은 2022년도 정부(산업통상자원부)와 한국산업기술진흥원의 '한/체코 국제공동기술개발사업(P0019623), 경기도의 경기도지역협력연구센터(GRRC) 사업[GRRC한국공대2023-B02], 중소벤처기업부에서 지원하는 2022년 산학연 플랫폼 협력기술개발사업(S3311002), 그리고 한국공학대학교 연구년 지원을 받아 수행하였음.

References

  1. J.H.Ahn., Y.Oh., "A Study on the Implementation of Intelligent Diagnosis System for Motor Pump" J of Korean Society of Semiconductor & Display Technology, pp. 87-91, 2019.
  2. Y.J.Lee., H.J.Youn., H.U.Park., "SCADA System for Semiconductor Equipment Condition Monitoring" J of Korean Society of Semiconductor & Display Technology, pp. 92-95, 2019.
  3. Koen Classens., Maurice Heemels., Tom Oomen., "From Fault Diagnosis and Predictive Maintenance to Control Reconfiguration", DSPE MIKRONIEK, pp. 5-6, 2023.
  4. M.J.Kim., K.I.Ko., K.M.Ku., K.H.Kim., "A study on the Failure Diagnosis of Transfer Robot for Semiconductor Automation Based on Machine Learning Algorithm", J of Korean Society of Semiconductor & Display Technology, Vol.21, pp.65-70, 2022.
  5. 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 Institute of Electrical Engineers, pp. 46-47, 2019.
  6. N.J.Kim., Y.C.Bae., "Status Diagnosis of Pump and Motor Applying K-Nearest Neighbors" J. of Korean Institute of Electronic Communication Science, Vol. 13, pp. 1249-1255, 2018.
  7. Y.K. Lee., S.C. Hong., J.K. Hong., "LSTM-based Drone's Anomal Motor Vibration Detection System" J. of Information Technology and Architecture, Vol. 17, pp. 315-321, 2020.
  8. Izaz Raouf., H.Y.Lee., H.S.Kim., "Mechanical fault detection based on machine learning for robotic RV reducer using electrical current signature analysis: a data-driven approach" J. of Computational Design and Engineering, Vol. 9, pp. 417-433, 2022. https://doi.org/10.1093/jcde/qwac015
  9. B.D. Youn., Y.H. Kim., J.H. Park., "Experimental Assessment of Fault Detection Method for and Industrial Robot under Various Operation Conditions" J. of Korean Society for Noise and Vibration Engineering, Vol. 10, pp. 243, 2017.
  10. Kaije Lu., Chong Chen., Tao Wang., "Fault diagnosis of industrial robot based on dual-module attention convolutional neural network" J of Autonomous Intelligent System, Vol. 2, pp. 2-12, 2022. https://doi.org/10.1007/s43684-022-00031-5
  11. Jae Hyun Park., Cheol Hong Kim., "Analysis of Accuracy and Computation Complexity of Bearing Fault Diagnosis Methods using CNN-based Deep Learning," J of Institute of Next Generation Computing, Vol. 18, pp. 7-18, 2022.
  12. J.H.Jung., M.Y.Kim., J.U.Ko., "Deep Learning Based Diagnosis using Enhanced Vibration Image for Journal Bearing Roter Systems: Efficiency and Accuracy Study" J of The Korean Society of Mechanical Engineers, Vol. 9, pp. 1132-1134, 2017.
  13. J.H.Park., M.J.Song., S.E.Ahn., "Developing the Fault Diagniostics and Prognostics Model of a Rotating Machinery" J of The Korean Operations Research and Management Science Society, Vol. 45, pp. 25-38, 2020. https://doi.org/10.7737/JKORMS.2020.45.1.025
  14. J.H.Jo., S.B.Yoo., S.W.Ban., " Deep learning-based failure diagnosis" J of Korean Institute of Information Scientists and Engineering, Vol. 15, pp. 509-511, 2021.
  15. S.H.Kim., J.H.Jang., B.S.Chu., "Development of Diagnosis Algorithm for Cam Wear of Paper Container Using Machine Learning", Vol. 36, pp. 953-959, 2019. https://doi.org/10.7736/KSPE.2019.36.10.953
  16. S.H.Park., J.S.Do., S.D.Choi., J.W.Hur., "Fault Diagnosis of Drome Using Machine Learning", Vol. 20, pp. 28-34, 2021. https://doi.org/10.14775/ksmpe.2021.20.09.028