The Next Failure Time Prediction of Escalators via Deep Neural Network with Dynamic Time Warping Preprocessing
Source abstract
Abstract
The escalator is one of the most popular travel methods in public places, and the safe working of the escalator is significant. Accurately predicting the escalator failure time can provide scientific guidance for maintenance to avoid accidents. However, failure data have features of short length, non-uniform sampling, and random interference, which makes the data modeling difficult. Therefore, a strategy that combines data quality enhancement with deep neural networks is proposed for escalator failure time prediction in this paper. First, a comprehensive selection indicator (CSI) that can describe the stationarity and complexity of time series is established to select inherently excellent failure sequences. According to the CSI, failure sequences with high stationarity and low complexity are selected as the referenced sequences to enhance the quality of other failure sequences by using dynamic time warping preprocessing. Secondly, a deep neural network combining the advantages of a convolutional neural network and long short-term memory is built to train and predict quality-enhanced failure sequences. Finally, the failure-recall record of six escalators used for 6 years is analyzed by using the proposed method as a case study, and the results show that the proposed method can reduce the average prediction error of failure time to less than one month.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Elevator Systems and Control · Anomaly Detection Techniques and Applications · Traffic control and management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory for Manufacturing and Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China
School of Traffic and Transportation Engineering, Central South University, Changsha 410075, China
Funding
National Key Research and Development Program of China · National Natural Science Foundation of China
References (28)
Show source-provided references
1. Riding the Escalator: How Dangerous is it Really?10.5811/westjem.2012.12.13346 ↗
2. An analysis of escalator-related injuries in metro stations in China, 2013–201510.1016/j.aap.2017.10.007 ↗
3. In-depth investigation of escalator riding accidents in heavy capacity MRT stations10.1016/j.aap.2005.12.010 ↗
4. Modeling, simulation and analysis of group trampling risks during escalator transfers10.1016/j.physa.2015.10.091 ↗
5. Notice of Retraction Risk management based on the escalator overturned accident10.1109/QR2MSE.2013.6625527 ↗
6. System safety principles: A multidisciplinary engineering perspective10.1016/j.jlp.2014.04.001 ↗
7. Optimizing preventive maintenance policy: A data-driven application for a light rail braking system
8. Prediction of occupational risk in the shipbuilding industry using multivariable linear regression and genetic algorithm analysis10.1016/j.ssci.2015.11.010 ↗
9. Safety performance evaluation in a steel industry: A short-term time series approach10.1016/j.ssci.2018.08.028 ↗
10. Jiang, H., Li, X., Shao, H., and Zhao, K. (2018). Intelligent failure diagnosis of rolling bearings using an improved deep recurrent neural network. Meas. Sci. Technol., 29.10.1088/1361-6501/aab945 ↗
11. Zhang, C.-Y., Wei, J., Jing, H., Fei, C.-W., and Tang, W. (2019). Reliability-Based Low Fatigue Life Analysis of Turbine Blisk with Generalized Regression Extreme Neural Network Method. Materials, 12.10.3390/ma12091545 ↗
12. Liu, X., Liu, Z., Liang, Z., Zhu, S.-P., Correia, J.A.F.O., and De Jesus, A.M.P. (2019). PSO-BP Neural Network-Based Strain Prediction of Wind Turbine Blades. Materials, 12.10.3390/ma12121889 ↗
13. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
14. Graves, A. (2012). Supervised Sequence Labelling. Supervised Sequence Labelling with Recurrent Neural Networks, Springer.10.1007/978-3-642-24797-2 ↗
15. Traffic flow prediction using LSTM with feature enhancement10.1016/j.neucom.2018.12.016 ↗
16. A recurrent neural network based health indicator for remaining useful life prediction of bearings10.1016/j.neucom.2017.02.045 ↗
17. Accident Diagnosis and Autonomous Control of Safety Functions During the Startup Operation of Nuclear Power Plants Using LSTM10.1007/978-3-319-94229-2_47 ↗
18. Real-time safety monitoring in the induction motor using deep hierarchic long short-term memory10.1007/s00170-018-2607-4 ↗
19. Sainath, T.N., Vinyals, O., Senior, A., and Sak, H. (2015, January 19–24). Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, QLD, Australia.10.1109/ICASSP.2015.7178838 ↗
20. Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats10.1016/j.compbiomed.2018.06.002 ↗
21. Tian, C., Ma, J., Zhang, C., and Zhan, P. (2018). A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network. Energies, 11.10.3390/en11123493 ↗
22. New parallel implementations for DTW algorithms10.1109/29.52710 ↗
23. Seokgoo, K., Nam, H.K., and Joo, H.C. (2020). Prediction of remaining useful life by data augmentation technique based on dynamic time warping. Mech. Syst. Signal Process., 136.10.1016/j.ymssp.2019.106486 ↗
24. Sharma, S.K., Phan, H., and Lee, J. (2020). An Application Study on Road Surface Monitoring Using DTW Based Image Processing and Ultrasonic Sensors. Appl. Sci., 10.10.3390/app10134490 ↗
25. Quantitative trend fault diagnosis of a rolling bearing based on Sparsogram and Lempel-Ziv10.1016/j.measurement.2018.06.051 ↗
26. Toward accurate dynamic time warping in linear time and space10.3233/IDA-2007-11508 ↗
27. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
28. Bodén, M. (2001). A Guide to Recurrent Neural Networks and Back Propagation. [Ph.D. Thesis, Halmstad University].