DOI QR코드

DOI QR Code

Elevator Fault Classification Using Deep Learning Model

딥러닝 모델을 활용한 승강기 결함 분류

  • Young-Jin, Jung (Department of Industrial Engineering, Inha University) ;
  • Chan-Young, Jang (Department of Industrial Engineering, Inha University) ;
  • Sung-Woo, Kang (Department of Industrial Engineering, Inha University)
  • 정영진 (인하대학교 산업경영공학과) ;
  • 장찬영 (인하대학교 산업경영공학과) ;
  • 강성우 (인하대학교 산업경영공학과)
  • Received : 2022.10.01
  • Accepted : 2022.12.21
  • Published : 2022.12.31

Abstract

Elevators are the main means of transport in buildings. A malfunction of an elevator in operation may cause in convenience to users. Furthermore, fatal accidents, such as injuries and death, may occur to the passengers also. Therefore, it is important to prevent failure before accidents happen. In related studies, preventive measures are proposed through analyzing failures, and the lifespan of elevator components. However, these methods are limited to existing an elevator model and its surroundings, including operating conditions and installed environments. Vibration occurs when the elevator is operated. Experts have classified types of faults, which are symptoms for malfunctions (failures), via analyzing vibration. This study proposes an artificial intelligent model for classifying faults automatically with deep learning algorithms through elevator vibration data, hereby preventing failures before they occur. In this study, the vibration data of six elevators are collected. The proposed methodology in this paper removes "the measurement error data" with incorrect measurements and extracts operating sections from the input datasets for proceeding deep learning models. As a result of comparing the performance of training five deep learning models, the maximum performance indicates Accuracy 97% and F1 Score 97%, respectively. This paper presents an artificial intelligent model for detecting elevator fault automatically. The users' safety and convenience may increase by detecting fault prior to the fatal malfunctions. In addition, it is possible to reduce manpower and time by assisting experts who have previously classified faults.

Keywords

Acknowledgement

이 연구는 2022년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2022H1D8A3037396) 이 연구는 2022년도 산업통산자원부 및 산업기술평가원(KEIT) 연구비 지원에 의한 연구임(20011249)

References

  1. H. H. Jeon, et al.(2020), "Elevator industry technology trend and industry prospect." KEIT PD Issue Report, 20(5):69-85.
  2. B. G. Gu(2020), "Design and implementation of data logger for elevator remote monitoring." Journal of Platform Technology, 8(4):3-10. https://doi.org/10.23023/JPT.2020.8.4.003
  3. Korea Elevator Information Center(2022a), Elevator inspection status.
  4. Korea Elevator Information Center(2022b), Elevator failure status.
  5. Korea Elevator Information Center(2022c), Elevator accident status.
  6. B. S. Kim, P. Park(2020), "Derivation of safety management implications through analysis of major elevator failures." J. Korea Saf. Manag. Sci., 22(3):23-29. https://doi.org/10.12812/KSMS.2020.22.3.023
  7. S. W. Jang, Y. J. Kim(2022), "A study on safety management measures for accident prevention through user error analysis among elevator accident cases." Journal of the Korea Academia-Industrial Cooperation Society, 23(3):549-558.
  8. O. N. Jeong, et al.(2016), "Accident prevention for the elevator and escalator by the accident type analysis." J. Korean Soc. Saf., 31(4):15-21. https://doi.org/10.14346/JKOSOS.2016.31.4.15
  9. J. M. Kim, et al.(2016), "Public service design to prevent negligent accident: Focused on escalator in subway station." J. Industrial Design, 10(1):51-60.
  10. H. J. Kim, et al.(2017), "A study on the estimation of the optimum lifetime of elevator components for elevator accident prevention." KIEE, 66(8):1278-1284.
  11. S. J. Yoo, et al.(2020), "Design of test bed for the fault diagnosis of traction machines for elevators." Proceedings of the Korean Society of Mechanical Engineers, 2020:113-114.
  12. T. B. Song, K. H. Choi(2010), "Predictive maintenance using vibration analysis of elevator's parts fault." Proceedings of the Spring Conference of the Korean Society for Precision Engineering, 2010:239-240.
  13. K. Y. Kim, K. M. Kwak(2008), "Dynamic modeling and controller design for active vibration control of elevator." Proceedings of the Spring Conference of the Korean Society for Noise and Vibration Engineering, 2008:71-76.
  14. S. Karen, A. Zisserman(2014), Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  15. H. Kaiming, et al.(2016), "Deep residual learning for image recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
  16. S. Christian, et al.(2016), "Rethinking the inception architecture for computer vision." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:2818-2826.
  17. A. G. Howardm et al.(2017), Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
  18. M. Tan, Q. Le(2019), "Efficientnet: Rethinking model scaling for convolutional neural networks." International Conference on Machine Learning, PMLR, 2019:6105-6114.