산업경영시스템학회지 (Journal of Korean Society of Industrial and Systems Engineering)

  • 제47권2호
  • /
  • Pages.10-20
  • /
  • 2024
  • /
  • 2005-0461(pISSN)
  • /
  • 2287-7975(eISSN)
한국산업경영시스템학회 (Society of Korea Industrial and System Engineering)
권호 표지
DOI QR코드

DOI QR Code

센서 데이터의 시계열 특성을 고려한 딥러닝 모델 기반의 공압 실린더 고장 감지 시스템 구현

Real-time Fault Detection System of a Pneumatic Cylinder Via Deep-learning Model Considering Time-variant Characteristic of Sensor Data

  • 김병수 (국립한밭대학교 산업경영공학과) ;
  • 송근명 (국립한밭대학교 산업경영공학과) ;
  • 이민정 (국립한밭대학교 산업경영공학과) ;
  • 백수정 (국립한밭대학교 산업경영공학과)
  • Byeong Su Kim (Department of Industrial & Management Engineering, Hanbat National University) ;
  • Geun Myeong Song (Department of Industrial & Management Engineering, Hanbat National University) ;
  • Min Jeong Lee (Department of Industrial & Management Engineering, Hanbat National University) ;
  • Sujeong Baek (Department of Industrial & Management Engineering, Hanbat National University)
  • 투고 : 2024.05.23
  • 심사 : 2024.06.17
  • 발행 : 2024.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder's status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2022R1F1A1069296). This work was also supported by Korea Institute for Advancement of Technology (KIAT) grant funded by the Korea Government (MOTIE) (P0012744, HRD program for industrial innovation).

참고문헌

  1. Ali, P.J.M. and Faraj, R.H., Data normalization and standardization: A technical report, Mach Learn Tech Rep, 2014, Vol. 1, No. 1, pp. 1-6.
  2. Baek, S., Fault pattern extraction via adjustable time segmentation considering inflection points of sensor signals for aircraft engine monitoring, J. Soc. Korea Ind. Syst. Eng., 2020, Vol. 44, No. 3, pp. 86-97. https://doi.org/10.11627/jkise.2021.44.3.086
  3. Gupta, A.K. and Arora, S.K., Industrial automation and robotics. Laxmi Publications, 2011.
  4. Hadi, H.H. and Sallom, M.Y., Pneumatic control system of automatic production line using SCADA implement PLC, 4th Scientific International Conference Najaf (SICN), 2019, pp. 37-42.
  5. Jeong, J.H., Jang, J.S., and Ji, S. W., Analysis of the control performance of 6 DoF simulator with pneumatic cylinder, Proceeding of the Korean Society of Power System Engineering, 2006, pp. 278-281.
  6. Jimenez, M., Kurmyshev, E., and Castaneda, C.E., Experimental study of double-acting pneumatic cylinder, Experimental Techniques, 2020, Vol. 44, pp. 355-367. https://doi.org/10.1007/s40799-020-00359-8
  7. Kalsoom, T., Ramzan, N., Zhmed, S., and Ur-Rehman, M., Advances in sensor technologies in the era of smart factory and industry 4.0, Sensors, 2020, Vol. 20, pp. 6783:1-22. https://doi.org/10.1109/JSEN.2019.2959158
  8. Kang, B.S., Lee, C.S., and Chang, M.S., Life Prediction of Cylinder Head Bolt using Accelerated Life Testing, Proceeding of 2012 Spring Conference of the Korean Society of Mechanical Engineers, 2012, pp. 510-513.
  9. Kim, D.H., Lee, I.S., and Cha, C.N., Development of cyber-physical production system based manufacturing control system for aircraft parts plant, J. Soc. Korea Ind. Syst. Eng., 2020, Vol. 43, No. 1, pp. 143-150. https://doi.org/10.11627/jkise.2020.43.1.143
  10. Kim, N.G., Kim, C.H., and Whang, G.N., Hydraulic cylinder abnormal detection by facility data analysis, Proceeding of 2019 Autumn Conference of Korean Institute of Industrial Engineers, 2019, pp. 3428-3432.
  11. Kim, S.H., Jin, L., and Ryu, G.H., Incremental regression based on a sliding window for stream data prediction, Journal of KIISS:Databases, 2007, Vol. 34, No. 6, pp. 483-492.
  12. Kim, S., Seo, W., Kwak, K., and Hong, D., Modified block diagonalization precoding with greedy approach, The Journal of Korean Information and Communication Society, 2008, Vol. 33, No. 1, pp. 79-85.
  13. Kim, Y. and Hwang, J., Greedy-based neighbor generation methods of local search for the traveling salesman problem, Journal of the Korea Society of Computer and Information, 2022, Vol, 27, No. 9, pp. 69-76. https://doi.org/10.9708/JKSCI.2022.27.09.069
  14. Kwon, D.-H. and Oh, C.-H., Predictive maintenance technology for smart factory, Proceeding of 2021 Spring Conference of Korea Institute of information and Communication Engineering, 2021, pp. 172-174.
  15. Lee, H.J., Park E.M., Shin, D.C., Choe, J.S., and Kim, T.W., Development of raising device for greenhouse column using a pneumatic cylinder, Protected Horticulture and Plant Factory, 2018, Vol. 27, No. 3, pp. 206-212. https://doi.org/10.12791/KSBEC.2018.27.3.206
  16. Lee, H.R. and Park, C., Comparative study of recommender systems based on deep learning algorithms, Journal of the Korean Data & Information Science Society, 2024, Vol. 35, No. 1, pp. 1-13. https://doi.org/10.7465/jkdi.2024.35.1.1
  17. Lee, J. and Kang, S., Analyzing extreme diurnal temperature range in spring on the South Korea using a sliding window approach, Journal of the Korean Data & Information Sciences Society, 2024, No. 35, No. 1, pp. 75-97. https://doi.org/10.7465/jkdi.2024.35.1.75
  18. Lee, K.J., Lee, H.J., and Oh, K.J., Using fuzzy-neural network to predict hedge fund survival, Journal of the Korean Data & Information Science Society, 2015, Vol. 26, No. 6, pp. 1189-1198. https://doi.org/10.7465/jkdi.2015.26.6.1189
  19. Lee, Y.-B., Lee, G.C., Lee, J.J., and Lim, S.Y., A study on the accelerated life test of yaw gearbox for wind turbine, Journal of Drive and Control, 2024, Vol. 21, No. 1, pp. 16-21. https://doi.org/10.7839/KSFC.2024.21.1.016
  20. Na, K., Kim, M., and Lee, J., Real-time batch size determination in the production line, J. Soc. Korea Ind. Syst. Eng., 2019, Vol. 42, No. 1, pp. 55-63. https://doi.org/10.11627/jkise.2019.42.1.055
  21. Ramasamy, S., Kalaiarasan, A., Ajithvishva, M.S., Hemsri, M., Oorppan, G.M., Yasodharan, R., IoT visualization of smart factory for additive manufacturing System (ISFAMS) with visual inspection and material handling processes, IOP Conference Series: Materials Science and Engineering, 2020, Vol. 995. pp. 012027: 1-12.
  22. Sherstinsky, A., Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network, Physica D: Nonlinear Phenomena, 2020, Vol. 404, pp. 132306:1-28. https://doi.org/10.1016/j.physd.2019.132306
  23. Song, Y.-U. and Baek, S., Real-time fault detection in discrete manufacturing systems in via LSTM model based on PLC digital control signals, J. Soc. Korea Ind. Syst. Eng., 2021, Vol. 44, No. 2, pp. 115-123. https://doi.org/10.11627/jkise.2021.44.2.115
  24. Yoo, G.H., Yang, H.C., and Whang, G.N., Abnormal detection of the mold cylinder temperature cycle using 1D CNN, Proceeding of 2021 Spring Conference of Korean Institute of Industrial Engineers, 2021, pp. 5873-5878.
  25. Yoon, Y.A., Jung, J.H., Lim, J.H., Chang, T.-W. and Kim, Y.S., A study on data preprocessing for developing remaining useful life predictions based on stochastic degradation models using air craft engine data, J. Soc. Korea Ind. Syst. Eng., 2020, Vol. 43, No. 2, pp. 48-55. https://doi.org/10.11627/jkise.2020.43.2.048
  26. Yu, Y., Si, X., Hu, C., and Zhang, J., A review of recurrent neural networks: LSTM cells and network architectures, Neural Computation, 2019, Vol. 31, No. 7, pp. 1235-1270. https://doi.org/10.1162/neco_a_01199