Railway Signal Electronic Control System Based on BP Neural Network
Main Article Content
Abstract
Railway signal system is the core system of railway command train operation. After the installation of the system equipment is completed, a comprehensive test shall be carried out through joint debugging and joint testing, and the applicability of the system to the design requirements shall be generally evaluated according to the test results. This paper focuses on the research of railway signal electronic control system. Based on BP neural network, fault information can be quickly and accurately identified in a relatively short time, and accurate electronic signal control can be realized in a complex system environment. The final result of the study shows that the difference in delay error of railway signal transmission under BP neural network technology is small, there are some subtle differences in 5 different modes, but the impact is small, in mode 1, the target time value is 0.236s, The actual reflection time is 0.322s, it can be seen that the error is controlled within 0.2s, which is feasible. Through the analysis of delay error of railway signal electronic control system, BP neural network has certain advantages in railway signal transmission.
Article Details
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
References
Gorobetz M, Alps I, Beinarovica A, et al. Algorithm of Signal Recognition for Railway Embedded Control Devices[C]// 2018 IEEE 59th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON). IEEE, 2018,40(2):2397-2407.
Thendral R, Ranjeeth A. Computer Vision System for Railway Track Crack Detection using Deep Learning Neural Network[C]// 2021 3rd International Conference on Signal Processing and Communication (ICPSC). 2021, 5(82):45-53.
Milne D, Masoudi A, Ferro E, et al. An analysis of railway track behaviour based on distributed optical fibre acoustic sensing. Mechanical Systems and Signal Processing, 2020, (142):106769-10689.
Fortino G F, Zamora J C, Tamayose L E, et al. Digital Signal Analysis based on Convolutional Neural Networks for Active Target Time Projection Chambers. 2022,2(3):1-22.
Thanachayanont A. Design procedure for noise and power optimisation of CMOS folded-cascode operational transconductance amplifier based on the inversion coefficient. Analog Integrated Circuits and Signal Processing, 2022, 111(2):201-214.
Zi-Kui Y I, Tan J P, Yan T. Analysis of an Online Evaluation System of Motor Noises based on BP Neural Network. Noise and Vibration Control, 2017, 233(3):32-39.
Verezhinskaia E A, Gorbachev A A, Maruev I A, et al. The model of the optical-electronic control system of vehicles location at level crossing[C]// SPIE Photonics Europe. 2019, 62(1):313-320.
Ankalaki S, Gupta S C, Prasath B P, et al. Design and Implementation of Neural Network Based Non Linear Control System (LQR) for Target Tracking Mobile Robots[C]// 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2018, 70:1-12.
Yang Z, Zheng H G, Jian M Y. 2475. Vibration signal analysis and fault diagnosis of bogies of the high-speed train based on deep neural networks. Journal of Vibroengineering, 2017, 19(4):2456-2474.
Ma F, Wang X, Deng L, et al. Multi-Port Railway Power Conditioner and Its Management Control Strategy with Renewable Energy Access. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2019,5(5):1-1.
Gholamian M, Yazdi M, Joursaraei A, et al. An ECG classification based on modified local binary patterns: a novel approach. Research on Biomedical Engineering, 2021, 37(4):617-630.
X Zhang, Amp H S, Division T. Analysis of Health Management of High Speed Railway Speed-up Switch. Railway Signalling & Communication Engineering, 2019, 1952(2):11-78.