Prediction of railway switch point failures by artificial intelligence methods

Arslan, Burak; Tiryaki, Hasan

doi:10.3906/elk-1906-66

Cited by 14 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main embodiment of intelligence in high-speed railway was the integration of advanced technology methods represented by machine learning [13], [14] and high-speed railway networks. Intelligent failure diagnosis and prediction [5], [15], [16], condition monitoring and health management [17] were studied, such as failure intelligent diagnosis of rolling bearings [18], [19] or bogies [20], [21] of high-speed trains, switch failure prediction [22], [23], vehicle-body vibration prediction [24], as well as online condition monitoring of the pantograph slide plate [25]. It can be seen that machine learning methods have achieved remarkable results compared with the traditional methods.…”

Section: Related Workmentioning

confidence: 99%

“…Considering that train operation and maintenance were mutually exclusive, Liden et al [32], [33] presented a mixed integer programming model for Swedish Northern Main Line to solve the problems of integrated railway traffic and maintenance planning. The above research results showed that intelligent maintenance could reduce malfunction process time, save resources [22], and optimize the route planning of high-speed trains [34].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Failure Features of High-Speed Automatic Train Protection System

Kang

Wang

Chen³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

An automatic train protection (ATP) system is the core to ensure operation safety of high-speed railway. However, at present, failure rate change rules of the system are not well understood and the maintenance strategy is not refined. In order to improve the protection capability and maintenance level of high-speed trains, this paper proposes a decision tree machine learning model for failure feature extraction of ATP systems. First, system type, mean operation mileage, mean service time, etc. are selected as ATP failure feature parameters, and cumulative failure rate as a model output label. Second, support vector machine, AdaBoost, artificial neural networks and decision tree model are adopted to train and test practical failure data. Performance analysis shows that decision tree learning model has better generalization ability. Its accuracy of 0.9761 is significantly greater than the other machine learning models, so it is most suitable for failure features analysis. Third, interpretability analysis reveals the quantitative relationship between system failure and features. Finally, an intelligent maintenance system for ATP systems is built, which realize the refined maintenance throughout life cycle.INDEX TERMS Automatic train protection system, intelligent maintenance, failure feature, machine learning, model interpretability, high-speed train.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Analysis of Failure Features of High-Speed Automatic Train Protection System

Kang

Wang

Chen³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Along with the improvement of existing electric switches by replacing unreliable elements and electric motors, global companies are working to create new types [12]. Increasingly, turnouts are equipped with a modified drive system with microcontroller control.…”

Section: Introduction One Of the Main Directions Of Implementation Of The National Transport Strategy Ofmentioning

confidence: 99%

“…The ball-screw pair «screw-nut» converts the rotational movement of the screw ( 9) into the translational motion of the nuts (10). The screw is mounted on the support bearings (11) and connected to the motor shaft via a coupling (12). Nuts through vertical rods (13), hinges (14) and longitudinal rod (15) transmit forces to the sharpeners (7), which carry out their movement between the frame rail (8) [18].…”

Section: Introduction One Of the Main Directions Of Implementation Of The National Transport Strategy Ofmentioning

confidence: 99%

Mathematical modelling of transients in the electric drive of the turnout of the mono-sleeper type with switched-inductor motor

Buriakovskyi¹,

Maslii²,

Asmolova³

et al. 2021

Electrical Engineering & Electromechanics

View full text Add to dashboard Cite

Introduction. The study is devoted to the development of the functionality of a railway track switch by introducing a switched-inductor electric drive. This solution justifies simplifying the mechanical part of the switches by changing the gearbox to a ball-screw and locating the all kinematic line of the switches on the mono-sleeper type. Goal. A study of the mono-sleeper turnout type behaviour to meet modern traffic safety requirements and improve operational reliability factors. Methodology. Based on electric drive theory, a kinematic line of a mono-switch turnout type with nonlinear friction characteristic is presented. Using differential equation theory and Laplace transformation, a mathematic description of a four-phase switched-inductor motor with ball-screw in a mechanical line of a single-mass electromechanical system has been made. A simulation mathematical model of the electric drive of mono-sleeper turnout type as the control system with a switched-inductor motor and nonlinear friction characteristic was built in MATLAB. Results. Simulation modelling of a mathematical model of a mono-sleeper turnout type with a switched-inductor motor and ball-screw gear has been developed and implemented. Studies of dynamics of turnout point movement have shown that, in contrast to the motors used today, the switched-inductor motor makes it possible to simplify the mechanical part of the drive, which leads to reduced time spent on laying and maintenance of turnout points, and therefore makes the design more reliable. The application of PID controller and fuzzy speed controller has shown improved dynamics of turnout point, while the fuzzy PID controller provides better performance of the set values and turnout point movements. Originality. First developed a mathematical model of the electric drive of the mono-sleeper turnout type, taking into account nonlinear friction characteristic, as an object of speed control of turnout point movement, is developed. Practical value. The developed mathematical model of a railway track turnout of the mono-sleeper type with a switched-inductor motor and ball-screw gear enables more efficient use of a microprocessor control system, creation of promising electric motor protection means and control of a turnout point.

show abstract

“…The test set samples are presented to the network once all weights have been determined. The network is considered to have been effectively trained if it responds correctly to the test set samples [9].…”

mentioning

confidence: 99%

Prediction of Radio Signal Failures of Communication Based Train Operating Systems by Machine Learning Methods

Arslan,

Tiryaki

2024

Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi

Self Cite

View full text Add to dashboard Cite

The use of rail systems in urban public transportation has become a necessity for reasons such as time saving, travel comfort and operating costs, especially in cities with high population and road traffic. Communication based train operating systems (CBTC) are used for the safe use of urban rail systems and the maximum capacity of the railway line. In this study, in line with the data collected from the trains on a railway line operated with CBTC, the status of the radio signals that enable the wireless communication of the trains with the trackside signaling equipment was evaluated by machine learning methods, and the situations that may have negative effects on the train operations of the problems at the signal level were evaluate. The problems on the antennas which receives signals from trackside above trains, the poor connection related with fiber optical and LAN cables, the trackside transmitter antenna orientation problems causes decrease on signal levels. It is aimed that to take actions about the problematic signal levels without any negative impact on the passenger comfort and the operation yet. The radio signal losses cause unexpected trains stops and delays. A decision support model has been developed that will offer early solution suggestions to system maintainers in order to intervene first. In conclusion, since it is the first study related with failure prediction by using radio signal levels data on railway signaling system, this study presents an important innovation in terms of literature.

show abstract

Prediction of railway switch point failures by artificial intelligence methods

Cited by 14 publications

References 14 publications

Analysis of Failure Features of High-Speed Automatic Train Protection System

Analysis of Failure Features of High-Speed Automatic Train Protection System

Mathematical modelling of transients in the electric drive of the turnout of the mono-sleeper type with switched-inductor motor

Prediction of Radio Signal Failures of Communication Based Train Operating Systems by Machine Learning Methods

Contact Info

Product

Resources

About