Train Braking Research Articles

Research on train braking model by improved Polach model considering wheel‐rail adhesion characteristics

AbstractTo study the braking process of the train under different adhesion conditions, this paper takes the braking system of a single rail vehicle as the research object. The author establishes a corresponding co‐simulation platform based on MATLAB/Simulink and AMESim, including the sub‐models of braking control, vehicle brake longitudinal dynamics and air brake unit. Considering the cleaning effect caused by large sliding, the author builds a suitable adhesion model for different adhesion conditions based on the improved Polach model, which is the input of the vehicle braking longitudinal dynamics sub‐model. Based on the finite state machine, the anti‐skid control algorithm of the train is constructed as the core of the brake control sub‐model, which can judge the motion state of the wheelset, and control the stage release and hold of the brake cylinder pressure. According to the International Standard EN15595 and the actual operating parameters of a certain type of train, the braking process of the train under dry and wet rail conditions is simulated on the platform. The validity of the model is verified, which provides a reliable method for future research on the braking process.

Train/track coupled dynamics model of long heavy haul train based on substructure and parallel computing

To consider the coupled effect on the running safety between elastic track and longitudinal impulse of Long Heavy Haul Train(LHHT), a train/track coupled dynamics model is established by using connection substructure theory. The ballasted track is divided into several segments called sub-tracks: a sub-track includes rail, sleepers and ballast. In the sub-track model, the sleepers and ballast are modelled as lumped mass. The rail is divided into the contact and connection rail. The contact rail is modelled as an Euler beam to reflect the wheel/rail interaction and the flexible vibration of the rail. The connection rail is modelled as a super element to reflect the interaction between adjacent contact rail. To increase the simulation speed, a new parallel computing method is proposed: a train/track coupled dynamics model is divided into different submodule, a submodule includes a sub-track and a vehicle on the sub-track. A submodule is calculated by a single computer core. The submodule is connected by connection rail, couplers and ballast. The advantage of this parallel method is that the load of each computer core is almost uniform. The simulation speed depends on the number of parallel computing cores instead of one core with a particularly large load. Finally, taking the 10,000-ton train as an example, the distribution of coupler force, the derailment coefficient and wheel unloading rate are given during the train braking on a curve, which shows the application and necessity of the train/track coupled dynamics model based on substructure and parallel computing.

The design of electronically controlled pneumatic brake signal propagation mode for electronic control braking of a 30,000-ton heavy-haul train

This paper takes 30,000-ton heavy-haul trains as the research object, and studies the propagation characteristics, train braking ability and longitudinal impulse level of three ECP electronic control signal Propagation modes of segmented electro-pneumatic braking under different lag times. The difference between the train’s use of segmented electro-pneumatic braking and air braking in the long ramp operation method is compared. The results show that the best way is when the leading control locomotive sends the ECP signal backward and the slave control locomotive sends the ECP signal both forward and backward. Compared with the worst mode that only the leading control locomotive propagates the ECP signal backward, the coupler force can be reduced by 46.5%, the time difference between the slowest and fastest action vehicles can be reduced by 60.5%, and the emergency braking distance can be reduced by 1.2%. With the increase in the lag time of the slave control locomotive, the differences in the braking capacity and longitudinal impulse level of the three ECP electronic control signal propagation modes decrease. The effectiveness of the slave control locomotive’s ability to send ECP signals is closely related to the lag time of the leading and slave control locomotives. Compared with pure air braking, segmented electro-pneumatic braking can delay the braking times of the last two brakes by 32.6 s and 83.7 s,respectively, during the three-cycle braking, and the starting time of relief can be delayed by 12.7 s, 89.8 s and 16.9 s respectively, and the maximum coupler force can be reduced by 30.1%. The research work of this paper can provide reference for the formulation of electro-pneumatic braking scheme of 30,000-tons heavy-haul train.

Train Brake System Pipe Leakage Detection and Early Warning Method Based on Bayesian Networks

This paper proposes a method for detecting and warning about leaks in train braking system pipelines based on Bayesian networks. Firstly, a detection model for pipeline leaks is established through the learning and inference of Bayesian networks. In the anomaly detection phase, the Bayesian network model is trained using historical data to monitor brake pressure abnormalities in real-time. Secondly, in the parameter regression calibration phase, the location and severity of the pipeline leaks are estimated based on the current brake pressure and relevant parameters. Finally, in the fault inference phase, the Bayesian network model is used to infer the possible causes of the leaks. The effectiveness and reliability of this method are verified through simulation design and actual data analysis. Compared to existing methods, this method can provide accurate leak detection and warning, thereby contributing to the safety of train operation. This research provides an effective method for detecting and warning about leaks in brake system pipelines and has practical application value.

Time Series Multi-Step Forecasting Based on Memory Network for the Prognostics and Health Management in Freight Train Braking System

In rail trains, the prognostics and health management system will make use of data from sensors deployed in key components. These data are typically non-stationary multi-variable time series with abrupt variations. The challenges of multivariate time series forecasting include how to identify the interactions between various variables, and how to assess the influence of historical data on present data. This paper presents the nature of the air brake system and its physical models. By analyzing the observed data obtained from the freight train air brake system, a Memory network-based Time series Multi-step fault Forecasting model (MTMF) is proposed. MTMF consists of a dual-encoder and a memory network module for feature extraction. The two encoders are used to extract features of short-term and long-term historical data respectively. The memory network is used to further mine the different weights of the long-term historical data. MTMF also designs a joint multi-step forecasting loss function, which is composed of shape, time and mean square error losses between the forecasting series and the real series. The improved loss function is no longer restricted to the differences in evaluation points. MTMF is evaluated on the real freight train braking system time series dataset. The results show that MTMF outperforms other forecasting methods on multivariate time series. The forecasting accuracy is increased by 5%-45%, demonstrating that the model is effective for non-stationary series and can better mine the dependence patterns for the train braking system.

The Arrangement and Cross-sectional Shape of Cooling Fins on Train Brake Discs

Taking into account physical factors such as the wind effect of the brake disc pump, heat dissipation power, and temperature rise, the optimal cross-sectional shape and layout of the brake disc cooling fins are studied. The flow field distribution and pump-wind heat dissipation power ratio of four different cross-sectional shapes, namely circular, elliptical, square, and rhombic, are compared and analyzed. The flow characteristics, wind effect, and heat dissipation power of the cooling fins under two different layouts, namely crosswise and parallel layouts, are also analyzed. The research results show that the circular cooling fins have the optimal pump-wind loss and heat dissipation power, and the crosswise layout of cooling fins shows the best comprehensive performance. The performance analysis method of cooling fins obtained in this paper provides a reference for the optimization design of brake disc structures.

Timetable optimization for maximization of regenerative braking energy utilization in traction network of urban rail transit

Timetable optimization is one of the effective solution methods for urban rail transit to achieve energy-saving. Previous studies on timetable optimization only focused on the transfer and utilization of mechanical energy, which did not consider the exchange of energy and line losses in the traction network. Therefore, this paper constructs a cross-substation energy transmission and utilization model taking into account the characteristics of the actual traction power supply systems. An overlap current method is presented to increase the utilization of regenerative braking energy (RBE) of trains and reduce the energy supply of the traction substation by considering the line loss, which is achieved by compensating the current generated by accelerating and braking trains in the substation. The compensation current can be maximized by adjusting the dwell time to achieve energy-saving. The traction power supply systems with highly nonlinear dynamic characteristics are linearized to construct a mixed-integer linear programming (MILP) model, which utilizes the utilization of RBE as the objection and dwell time as the variable. The method of maximum compensation current is verified by numerical examples based on Beijing Batong Line. The results show that the energy-efficient of the method is greatly improved compared with the method of maximizing the overlap time between the accelerating train and the braking train.

Efficient visual fault detection for freight train braking system via heterogeneous self distillation in the wild

Efficient visual fault detection of freight trains is a critical part of ensuring the safe operation of railways under the restricted hardware environment. Although deep learning-based approaches have excelled in object detection, the efficiency of freight train fault detection is still insufficient to apply in real-world engineering. This paper proposes a heterogeneous self-distillation framework to ensure detection accuracy and speed while satisfying low resource requirements. The privileged information in the output feature knowledge can be transferred from the teacher to the student model through distillation to boost performance. We first adopt a lightweight backbone to extract features and generate a new heterogeneous knowledge neck. Such neck models positional information and long-range dependencies among channels through parallel encoding to optimize feature extraction capabilities. Then, we utilize the general distribution to obtain more credible and accurate bounding box estimates. Finally, we employ a novel loss function that makes the network easily concentrate on values near the label to improve learning efficiency. Experiments on four fault datasets reveal that our framework can achieve over 37 frames per second and maintain the highest accuracy of 98.88% in comparison with traditional distillation approaches. Moreover, compared to state-of-the-art methods, our framework demonstrates more competitive performance with lower memory usage and the smallest model size.

Failure Propagation Prediction of Complex Electromechanical Systems Based on Interdependence

Interdependence is an inherent feature of the cyber-physical system. Small damage to one component in the system may affect several other components, leading to a series of failures, thus collapsing the entire system. Therefore, the system failure is often caused by the failure of one or more components. In order to solve this problem, this paper focuses on a failure propagation probability prediction method for complex electromechanical systems, considering component states and dependencies between components. Firstly, the key component set in the system is determined based on the reliability measure. Considering the three coupling mechanisms of mechanical, electrical, and information, a topology network model of the system is constructed. Secondly, based on the topology network model and fault data, the calculation method of influence degree between components is proposed. Three state parameters are used to express the risk point state of each component in the system through mathematical representation, and the correlation coefficient between the risk point state parameters is calculated and measured based on the uncertainty evaluation. Then, the influence matrix between the system risk points is constructed, and the fault sequence is predicted by using the prediction function of an Artificial Neural Network (ANN) to obtain the fault propagation probability. Finally, the method is applied to the rail train braking system, which verifies that the proposed method is feasible and effective.

Power Allocation Strategy for Urban Rail HESS Based on Deep Reinforcement Learning Sequential Decision Optimization

A hybrid energy storage system (HESS) is adopted to tackle the traction network voltage fluctuation problem caused by high power and large energy demand during the starting and braking of urban rail trains. The system is composed of on-board ultracapacitors and ground lithium batteries, aiming to smooth out the power fluctuation to realize “peak-shaving and valley-filling”. Based on deep reinforcement learning (DRL) online sequence decision, a dynamic power allocation strategy is proposed to improve the energy-saving and voltage stabilization of DC traction networks as well as HESS life protection. Furthermore, to enhance the DRL’s efficiency under time-varying operating conditions, an annealing bias - priority experience replay twin delayed deep deterministic policy gradient algorithm (A-TD3) is proposed to train the replay buffer in DRL. The online learning and optimization strategy is implemented via the mechanism of “trial and error” and “feedback” of the agent. RT-LAB semi-physical real-time simulation systems are adopted to verify the effectiveness of the proposed strategy. Compared with the traditional filtering algorithms and DRL algorithms, the results show that the proposed method converges faster and is more energy saving and stable while effectively protecting the energy storage components.

Optimal Control Strategies for Metro Trains to Use the Regenerative Braking Energy: A Speed Profile Adjustment Approach

The Regenerative Braking Energy (RBE) of metro trains plays an important role in metro energy saving. If the regenerative energy can be directly absorbed by the adjacent trains, the investment in other RBE usage equipments like super capacitors will be reduced. To increase the RBE usage, the overlaps of traction and braking processes of adjacent trains can be increased by timetable optimization or real-time train regulation. But if the overlaps cannot be realized, the RBE cannot be efficiently absorbed by the other trains. To solve this problem, this paper proposes an optimal train control method to absorb the RBE of the braking train by adjusting the speed profile of an adjacent train that runs at non-braking stage. A speed profile adjustment algorithm for the adjacent train is given considering the speed limits and gradients, in which a traction process is incorporated in the adjusted speed profile. Connected and unconnected DC power supply networks are both considered. In the connected DC power supply network, the RBE of the braking train can be absorbed by the adjacent adjusted train, which runs in the different power supply section. To test the robustness of the proposed algorithm, random train delays are considered in the simulations. The interstation running time will be regulated to reduce the train delay by a linear programming model, based on which, the speed profile of the cooperative train will be adjusted. Simulations are conducted based on a whole day data of Beijing Metro Line 4. The simulation results show that the proposed method improves the energy efficiency over 13% by improving RBE usage, and the proposed method also shows strong robustness in the train delay simulations, which makes it a promising method to be applied in real metro system.

Numerical investigation on wheel-rail adhesion under water-lubricated condition during braking

PurposeThe purpose of this study is to develop a 3D wheel-rail adhesion model under wet condition, which considers the generated surface roughness topography and the traditional braking procedure for high-speed trains.Design/methodology/approachWheel-rail adhesion has an important effect on the braking ability of railway vehicle. Based on the deterministic mixed lubrication approach, the model was solved to get the adhesion characteristics of the train during braking. The elastic deformation was calculated with the discrete convolution and fast Fourier transform method. The simulation results of adhesion coefficient were compared with the experimental values. The wheel-rail adhesion characteristics of train braking at several different initial speeds were investigated. The effects of the time-step length and roughness orientation on the contact load ratio were also discussed.FindingsThe results show that the adhesion coefficient of the numerical model is in good agreement with the experimental results. At the instant of braking, the adhesion coefficient drops to a lower adhesion level, the value of adhesion coefficient is lower than 0.06, especially at a higher speed (200, 300 and 400 km/h).Originality/valueIt can provide a better understanding of the low adhesion phenomenon of train braking under wet condition.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-02-2023-0040/

Safety analysis of train-track-bridge coupled braking system under earthquake

Bridges represent a significant proportion of high-speed railway (HSR) lines in China, and high-speed trains operate on these structures for prolonged periods. Consequently, the occurrence of an earthquake during a train crossing is a probable event. With the support of the existing communication technology, the train will receive a warning in advance and brake urgently when the earthquake hits the train. However, research on the response of high-speed trains traversing bridges during an earthquake is scarce. To address this research gap, a three-dimensional train-track-bridge coupled braking system (TTBCBS) is developed using the finite element method and multibody dynamics, and the system’s motion equation is derived. Furthermore, the system is then programmed using mathematical software, and dynamic analysis is performed using different parameters such as friction coefficient and pier height under train braking and earthquake. Finally, the calculated train and bridge responses are evaluated based on safety indices, which provide evaluation standards for train running safety (TRS). However, it is found that the response of both the train and the bridge is smaller when the train is braking under earthquake, which is advantageous for the response of the TBCBCS system.

DEVELOPMENT OF A MATHEMATICAL MODEL AND AN AUTOMATED ALGORITHM FOR CALCULATING THROUGHPUT

Background. The problem of this work is to develop a methodology for calculating cash throughput, which is based on the well-known formulas for calculating cash throughput, the main innovation of which is to take into account the time spent by trains on acceleration and deceleration en route. Currently, in the process of calculating the available capacity, a formal approach is used to determine the removal coefficients, and the site speed is also taken into account, calculated taking into account acceleration and deceleration, but representing only the ratio of the length of a certain section of the railway polygon to the time of the train following it.
 Materials and/or methods: simulation modeling, economic and mathematical modeling, AnyLogic software package, methods of general systems theory, logistics.
 Results. An analytical formula is proposed that allows calculating the available throughput with higher accuracy. The results of the study can be used in the dispatch centers of transportation management of JSC “Russian Railways” in order to more fully analyze the operation of the landfill of the road, railway lines or individual sections in order to more fully analyze the work performed on transportation.
 Conclusion. The article develops a methodology for calculating the available capacity on a railway line with full consideration of the effect of acceleration and braking of trains on their way to the resulting available capacity.

Friction mechanisms of brake pads made of cast iron and composite material on the surface of railway wheels

The friction mechanisms of brake pads made of cast iron and composite material (rubber-asbestos or rubber-free mixtures, including those with cast-iron inserts) on the surface of wheels of railway rolling stock were analysed. Values of the friction coefficient are given. The main role in the mechanism of friction of cast iron pads on the surface of railway wheels belongs to the microstructure of cast iron, namely, the amount, shape, distribution in volume of graphite inclusions, dispersion of pearlite and cementite inclusions, and the construction of phosphide eutectics. The friction mechanism of pads made of composite material on the wheel surface is determined by the content and properties of the components from which the composite rubber mixture is formed, their chemical and granulometric composition, as well as the degree of burnout of the composite rubber mixture during the operation of the brake pads. It is shown that due to the lack of regulation in the standards and technical conditions for composite blocks of the percentage content of ingredients and their chemical composition in the composite material, its properties and the value of the coefficient of friction are uncontrolled. Cyclic temperature changes on the contact surface of the brake pads with the wheels during train braking and high peak temperatures (up to 800 °C) in individual periods of braking lead to changes in the structure and properties of the surface layer of the metal of the wheels and the material of the brake pads. This is reflected in the frictional characteristics of the friction process of brake pads with wheels. The disadvantage of brake pads made of composite material is their low thermal conductivity compared to cast iron pads. As a result, the temperature in the contact zone of composite pads with wheels increases more than when using pads made of cast iron. The hydrodynamic effects of moisture (water) in the contact zone of brake pads with the surface of vehicle wheels are considered from the standpoint of classical tribology approaches. The microrelief of the working surface of the brake pads was studied. The influence of various factors on the coefficient of friction of the brake pads on the surface of the wheels is shown. Recommendations are provided for improving standards and technical conditions for brake pads made of cast iron and other materials. Keywords: brake pads, wheels of railway transport, friction, cast iron, composite materials, surface microrelief.

A trailer car dynamics model considering brake rigging of a high-speed train and its application

AbstractBrake systems are essential for the speed regulation or braking of a high-speed train. The vehicle dynamic performance under braking condition is complex and directly affects the reliability and running safety. To reveal the vehicle dynamic behaviour in braking process, a comprehensive trailer car dynamics model (TCDM) considering brake systems is established in this paper. The dynamic interactions between the brake system and the other connected components are achieved using the brake disc–pad frictions, brake suspension systems, and wheel–rail interactions. The force and motion transmission from the brake system to the wheel–rail interface is performed by the proposed TCDM excited by track irregularity. In addition, the validity of TCDM is verified by experimental test results. On this basis, the dynamic behaviour of the coupled system is simulated and discussed. The findings indicate that the braking force significantly affects vehicle dynamic behaviour including the wheel–rail forces, suspension forces, wheelset torsional vibration, etc. The dynamic interactions within the brake system are also significantly affected by the vehicle vibration due to track irregularity. Besides, the developed TCDM can be further employed to the dynamic assessment of such a coupled mechanical system under different braking conditions.

Causal Graph Attention Network with Disentangled Representations for Complex Systems Fault Detection

Considering the importance of complex systems fault detection, much efforts have been dedicated to fault feature extraction with monitoring data. The graph-based approach has become a trending topic, which exploits the non-Euclidean structure and generates representation based on spatial information. However, most graph-based models are built based on correlation assumption, and disregards the causality which are intrinsic in system and its failure process. In this paper, a causal graph attention network with disentangled representations (Causal-GAT) is proposed for fault detection. High-dimensional variables are first characterized into directed acyclic graphs using data-driven causal discovery combining expertise. The causal graph, which represents variables’ cause-effect relations, is fed into the Causal-GAT. Disentangled Causal Attention (DC-Attention) is proposed to adaptively aggregate cause variables for embedding the effect variables. To improve feature extraction efficiency in the multi-head attention, the DC-Attention enforces disentangled node representation by regularizing it with a specified causal condition. To verify the effectiveness of the proposed method, a real case study concerning the high-speed train braking systems is considered. Experimental results with the benchmark methods demonstrate the advantages of the proposed method. Validities of causal graph construction, representation disentanglement, as well as interpretability of the model are also discussed in this work.

Modelling and stability analysis of a high-speed train braking system

The stability of a braking system is crucial for the steady and safe operation of trains. To investigate the dynamic behaviors and stability of a train braking system as influenced by key parameters, a numerical model integrating mode-coupling, negative friction–velocity slope (NFVS), and stick–slip theories was established. Additionally, the wheelset connected with the braking system was contained in the model considering that mode-coupling and stick–slip characteristics were affected by system structures. Based on this model, the influence and mechanism of stiffness, damping, and NFVS characteristics on mode-coupling of the braking system were revealed. The results showed that when the tangential and normal contact stiffness values of the pad were close, the system experienced mode-coupling instability and vibrations in these two directions were coupled. When the tangential and normal damping values of the pad were unequal, the energy dissipation in the two directions became different and the system instability was enhanced. Additionally, the system complex eigenvalues always had positive real parts and the dynamic behaviors were more complicated by considering NFVS at relatively low speeds. This is because NFVS characteristics can be equivalent to negative damping values, which cause the difference in tangential and normal damping values and continuously input energy into the braking system, then weakening the system stability.

Parallel co-simulation of heavy-haul train braking dynamics with strong nonlinearities

A new wave of research interests on train braking dynamics has been raised which requires more accurate and faster train braking dynamics simulations. Simulations with fully nonlinear fluid dynamic air brake models and nonlinear friction draft gear models are more accurate, however these are not yet available. This paper developed a model that has combined both of these aspects. Simulations were achieved by using a parallel co-simulation method which requires minimum working loads to merge legacy codes. A case study was carried out to simulate a heavy haul train braking commencing with a minimum service brake and then followed by a full-service brake before the minimum service brake was fully executed. Such transient simulations were not able to be accurately conducted by using empirical air brake models, but only by using fluid dynamic air brake models. Influences of co-simulation synchronization frequencies on computing time and results of the simulations were also investigated. Simulation results have recommended a synchronization frequency of 100 Hz. The corresponding simulation was 43% faster than real-time for a 152-vehicle train.

Numerical simulation and optimization on opening angles of aerodynamic braking plates sets for a maglev train

The aerodynamic braking has become an attractive option with the continuous improvement of train speeds. The study aims to obtain the optimal opening angles of multiple sets of braking plates for the maglev train. Therefore, a multi-objective optimization method is adopted to decrease the series interference effect between multiple sets of plates. And the computational fluid dynamics method, based on the 3-D, RANS method and SST k-ω turbulence model, is employed to get the initial and iterative data. Firstly, the aerodynamic drag and lift are analysed, as well as the pressure and velocity distribution of the flow field with the braking plates open at 75°. Then, the aerodynamic forces of each braking plate pre and post optimization are compared. Finally, the correlation between each set of braking plates and the optimized objective is analysed. It is found from the results that the aerodynamic drag and lift of the train have significant differences with or without multiple sets of braking plates. Additionally, the design variable corresponding to the number of iterations of 89 is taken as the relative optimal solution, and its opening angles of braking plates (B2-B5) are 87.41°, 87.85°, 87.41°, and 89.88°, respectively. The results are expected to provide a reference for the opening angles design scheme for the future engineering application of high-speed maglev train braking technology.