An Implementation of Artificial Neural Network based on IMU sensor for Train Detection
Abstract
The purpose of train detection systems is to check the clearness-relation in track section of vehicles before a train passes through a route. A train detection system has an important role in ensuring the safety of train traffic. There are mainly 2 commercially used train detection systems. They consist of an axle counter and a track circuit. The problem with both systems is the high-cost installations and related equipment management. Several solutions have already been presented either on previous research with various methods, such as using Infrared and computer vision/image processing. Most of them want to make the system more effective and less cost maintenance than commercial use. To solve the issues, we propose a new method for train detection based on the usage of an Inertia Measurement Unit (IMU) with embedded artificial neural network module mounted on the sleeper's train in the following section. We utilize the method of train detection by involving an appropriate data acquisition method and a convolution operator as a time series processing algorithm. This idea equips the system to recognize the difference between train and gangway at the speed of 30 km/h. Several experiments conducted on actual rails demonstrate the method's dependability, suggesting its adoption in an automatic track warning system. So, in this proposed train detection system, we propose the train detection system using IMU with Artificial Neural Network Algorithm.
Full Text:
PDFReferences
W. A. Fikri, F. P. Fhazrel, and R. A. Fahmi, “ANALISIS KEPUASAN PELANGGAN PT. KERETA API INDONESIA (PERSERO),” no. 4, 2018.
J. W. Palmer, “THE NEED FOR TRAIN DETECTION”.
A. Zamani and A. Mirabadi, “Analysis of sensor orientation in Railway axle counters, using Response Surface Methodology,” 2011.
A. Suharjono, E. D. Wardihani, and Y. F. K. Hardani, “Analysis of the vibration signal detection for rail train arrival,” in 2017 IEEE International Conference on Communication, Networks and Satellite
(Comnetsat), Semarang, Indonesia: IEEE, Oct. 2017, pp. 85–87.
doi: 10.1109/COMNETSAT.2017.8263578.
R. V. Pise, P. D. Nikhar, and A. H. Shelar, “REVIEW ON RAILWAY TRACK CRACK DETECTION USING IR TRANSMITTER AND RECEIVER,” vol. 04, no. 01.
S. Faghih-Roohi, S. Hajizadeh, A. Nunez, R. Babuska, and B. De Schutter, “Deep convolutional neural networks for detection of rail surface defects,” in 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada: IEEE, Jul. 2016, pp. 2584–2589. doi: 10.1109/IJCNN.2016.7727522.
V. V. Krylov, “Spectra of Low-Frequency Ground Vibrations Generated by High-Speed Trains on Layered Ground,” Journal of Low Frequency Noise, Vibration and Active Control, vol. 16, no. 4, pp. 257–270, Dec. 1997, doi: 10.1177/026309239701600404.
L. Hall, “Simulations and analyses of train-induced ground vibrations in finite element models,” Soil Dynamics and Earthquake Engineering, vol. 23, no. 5, pp. 403–413, Jul. 2003, doi: 10.1016/S02677261(02)00209-9.
M. V. Nikolic, B. D. Kosic, M. D. Milanovic, N. M. Antonic, Z. M. Stojkovic, and I. Z. Kokic, “Railway axle counter prototype,” in 2014 22nd Telecommunications Forum Telfor (TELFOR), Belgrade, Serbia:
IEEE, Nov. 2014, pp. 694–697. doi: 10.1109/TELFOR.2014.7034503.
“10 railway axle counter remote supervision system.pdf.”
J. A. Velazquez, T. Petit, and A. Lavoie, “An evaluation of the Canadian global meteorological ensemble prediction system for short-term hydrological forecasting,” Hydrol. Earth Syst. Sci., 2009.
P. Purnawansyah, H. Haviluddin, R. Alfred, and A. F. O. Gaffar, “Network Traffic Time Series Performance Analysis Using Statistical Methods,” Kno. Eng. Da. Sc., vol. 1, no. 1, p. 1, Dec. 2017, doi:
17977/um018v1i12018p1-7.
J. Singh and P. Tripathi, “Time Series Forecasting Using Back Propagation Neural Network with ADE Algorithm,” vol. 7, no. 5, 2017.
P. J. Brockwell and R. A. Davis, Introduction to time series and forecasting, 2nd ed. in Springer texts in statistics. New York: Springer, 2002.
G. Sermpinis, C. Dunis, J. Laws, and C. Stasinakis, “Forecasting and trading the EUR/USD exchange rate with stochastic Neural Network combination and time-varying leverage,” Decision Support Systems, vol. 54, no. 1, pp. 316–329, Dec. 2012, doi: 10.1016/j.dss.2012.05.039.
A. S. Lundervold and A. Lundervold, “An overview of deep learning in medical imaging focusing on MRI,” Zeitschrift für Medizinische Physik, vol. 29, no. 2, pp. 102–127, May 2019, doi: 10.1016/j.zemedi.2018.11.002.
R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi,
Convolutional neural networks: an overview and application in radiology,” Insights Imaging, vol. 9, no. 4, pp. 611–629, Aug. 2018, doi: 10.1007/s13244018-0639-9.
“18 Time‑ series analysis with smoothed CNN.pdf.”
M. Binkowski, G. Marti, and P. Donnat, “Autoregressive Convolutional Neural Networks for Asynchronous Time Series”.
S. Smyl, “A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting,” International Journal of Forecasting, vol. 36, no. 1, pp. 75–85, Jan. 2020, doi:
1016/j.ijforecast.2019.03.017.
C. Yang, Y. Sun, C. Ladubec, and Y. Liu, “Developing Machine Learning-Based Models for Railway Inspection,” Applied Sciences, vol. 11, no. 1, p. 13, Dec. 2020, doi: 10.3390/app11010013.
M. Hamadache, S. Dutta, O. Olaby, R. Ambur, E. Stewart, and R. Dixon, “On the Fault Detection and Diagnosis of Railway Switch and Crossing Systems: An Overview,” Applied Sciences, vol. 9, no. 23, p.
, Nov. 2019, doi: 10.3390/app9235129.
H. Ismail Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Muller, “Deep learning for time series classification: a review,” Data Min Knowl Disc, vol. 33, no. 4, pp. 917–963, Jul. 2019, doi:
1007/s10618-019-00619-1.
P. Cichosz, Data mining algorithms: explained using R. Chichester, West Sussex ; Malden, MA: John
Wiley & Sons Inc, 2015.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.