반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

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

CNN과 진동데이터를 활용한 산업용 로봇의 고장 진단

Fault Diagnosis of Industrial Robots using CNN and Vibration Data

  • 김미진 (한국공학대학교 IT반도체융합공학부) ;
  • 구교문 (한국공학대학교 IT반도체융합공학부) ;
  • 사이풀 (한국공학대학교 IT반도체융합공학부) ;
  • 정명진 (한국공학대학교 메카트로닉스공학부) ;
  • 김효영 (한국공학대학교 메카트로닉스공학부) ;
  • 김기현 (한국공학대학교 메카트로닉스공학부)
  • Mi Jin Kim (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Kyo Mun Ku (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Saiful Islam (Department of IT Semiconductor Engineering, Tech University of Korea) ;
  • Myung-Jin Chung (Department of Mechatronics Engineering, Tech University of Korea) ;
  • Hyo Young Kim (Department of Mechatronics Engineering, Tech University of Korea) ;
  • Kihyun Kim (Department of Mechatronics Engineering, Tech University of Korea)
  • 투고 : 2024.09.16
  • 심사 : 2024.09.14
  • 발행 : 2024.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Products were typically produced using specialized equipment such as CNC machines, milling machines, and lathes in traditional manufacturing. However, modern manufacturing is increasingly attempting with technological advancements to leverage large industrial robots for machining, offering greater flexibility, efficiency, and a high degree of freedom throughout the entire production process. Additionally, the demand for industrial robots continues to rise as industries adopt smart factories. These robots are becoming larger, more precise, and faster, as they take over tasks previously requiring specialized equipment or skilled human operators. Where numerous robots are in operation in factories, ensuring a stable supply chain and maintaining operational uptime is crucial. Therefore, preparing for potential mechanical failures in each robot is necessary, and there is a growing need for technologies that enable real-time fault diagnosis and predictive maintenance. A large industrial robot used for machining was employed as a testbed for fault diagnosis in this study. The Vibration data was collected from various robot axes under both normal operating conditions and abnormal conditions, such as end-effector overloads and drive malfunctions. The collected vibration data was then preprocessed, and key features were analyzed and extracted. The extracted features were used to build a learning model, and in this study, the CNN (Convolutional Neural Network) algorithm was applied instead of k-NN (k-Nearest Neighbors) to diagnose defects occurring in the discontinuous movements of the robot, thereby improving accuracy.

키워드

과제정보

본 연구는 산업통상자원부의 국제공동기술개발사업의 일환으로 수행하였습니다. [P159100011, 과제명: 스마트 워크피스 홀더와 스마트 그리퍼 적용 밀링/라우팅/트리밍 가공용 로봇 가공 시스템 개발]

참고문헌

  1. Benjamin Y. Choo, Peter A. Beling, Amy E. LaViers, Jeremy A. Marvel, and Brian A., "Adaptive Multi-scale PHM for Robotic Assembly Processes" J. of National Institute of Standards and Technology, Gaithersburg, Maryland, 20899, USA, 2015.
  2. Guixiu Qiao and Brian A., " Advancing Measurement Science to Assess Monitoring, Diagnostics, and Prognostics for Manufacturing Robotics" J. of National Institute of Standards and Technology, Gaithersburg, MD, 20899, USA, 2016.
  3. Kwok L. Tsui,1 Nan Chen,2 Qiang Zhou,1 Yizhen Hai,1 and Wenbin Wang3,4., "Prognostics and Health Management: A Review on Data Driven Approaches" J. of Mathematical Problems in Engineering, Vol.20, PP.17, 2015.
  4. Fabio Immovilli, Claudio Bianchini, Marco Cocconcelli, Alberto Bellini, Riccardo Rubini., " Bearing Fault Model for Induction Motor With Externally Induced Vibration" J. of Transactions on Industrial Electronics, Vol.60, No.8, pp.3408-3418, 2013.
  5. MD Saiful Islam, Mi-Jin Kim, Kyo-Mun Ku, HyoYoung Kim, and Kihyun Kim., "Study on Fault Diagnosis and Data Processing Techniques for Substrate Transfer Robots Using Vibration Sensor Data" J of The Korean Microelectronics and Packaging Society, Vol.31, No.2, pp.45-53, 2024.
  6. Jae Hyun Park, Cheol Hong Kim., "Analysis of Accuracy and Computation Complexity of Bearing Fault Diagnosis Methods using CNN-based Deep Learning" J. of Korean Institute of Next Generation Computing, Vol.18, No.1, pp.7-18, 2022.
  7. Mingzhi Chen, Haidong Shao , Haoxuan Dou, Wei Li , and Bin Liu., "Data Augmentation and Intelligent Fault Diagnosis of Planetary Gearbox Using ILoFGAN Under Extremely Limited Samples" J. of IEEE Transactions on Reliability, Vol.72. No.3, pp.1029-1037, 2023.
  8. Ilias P. Georgakopoulos, Epaminondas D. Mitronikas, Athanasios N.Safacas., "Detection of Induction Motor Faults in Inverter Drives Using Inverter Input Current Analysis" J. of IEEE Transactions on Industrial Electronics, Vol.58. No.9, pp.4365-4373, 2011.
  9. Ye Won Song, Hong Seong Lee, HoonSeok Park, Young Jin Kim, Jae Yoon Jung., "A signal Processing Technique for Predictive Fault Detection based on Vibration Data", J of Society for e-Business Studies, Vol.23, No.2, pp.111-121,2018.
  10. Yuan Yao, Bin Xie, Yu Hao, Bing Li, Binquan Li, Yesong Li., "A signal-End Data Augmentation Method for Mechanical Fault Diagnosis Based on Self-Sensing Motor Driver" J. of International Conference on Electrical Machines and Systems, 2023.
  11. Kyusung Jung, Joo-Ho Choi., "A study on model based fault diagnosis of electric motors using motor current signature analysis", J of the Korean Society of Mechanical Engineers, 2017.
  12. Min su Kim, Jong Pil Yun, Minseon Gwak, PooGyeon Park., "A Fault Diagnosis Model using a Vibration Signal and Visualizing Decision Criteria of the Model", J of The Korean Institute of Electrical Engineers, 2021.
  13. Kaijie Lu, Chong Chen, Tao Wang, Lianglun Cheng, Jial Qin., "Fault diagnosis of industrial robot based on dual-module attention convolutional neural network", J of Autonomous Intelligent Systems, Vol.2, No,12, 2022.
  14. Mi Jin Kim, Kwang In Ko, Kyo Mun Ku, Jae Hong Shim, Kihyun Kim., "A Study on the Failure Diagnosis of Transfer Robot for Semiconductor Automation Based on Machine Learning Algorithm", J of the Semiconductor & Display Technology, Vol.21, No.4, pp.65-70, 2022.
  15. Xin Pan, Xiancheng Zhang, Zhinong Jiang, Guangfu Bin., "Real-Time Intelligent Diagnosis of Co-frequency Vibration Faults in Rotating Machinery Based on Lightweight-Convolutional Neural Networks", Chinese J of Mechanical Engineering, Vol.37, No.41, pp.2-19, 2024.
  16. Mi Jin Kim, Kyo Mun Ku, Jae Hong Shim, Hyo Young Kim, Kihyun Kim., "Study on the Failure Diagnosis of Robot Joints Using Machine Learning", J of the Semiconductor & Display Technology, Vol.22, No.4, pp.113-118, 2023.