Train Wheelset Research Articles

Analysis of temperature characteristics of high‐speed train wheelset system under complex operating conditions

AbstractWith the rapid advancements in high‐speed train technology, the importance of ensuring the safety of train operations has become paramount. Bearings, being a critical component of train bogies, have garnered significant attention for their role in maintaining safety standards. Monitoring the temperature of bearings to evaluate their motion state is a common practice in high‐speed trains, emphasizing the need for further research into temperature fluctuations. In this study, a dynamic model is developed for the bearing rotor system of high‐speed trains. By considering the contact points between raceways and rolling elements, the power loss in the bearing is obtained and a transient temperature‐field model of the system is established. The relationship between node temperature and factors such as ambient temperature, train running speed, and load is illustrated, with a detailed presentation of the influence of bearing fault type and size on node temperature. The analysis results reveal that the node temperature increases with higher values corresponding to those quantifiable factors and is most affected by rolling element fault. Additionally, it is observed that the temperature rises rapidly in the initial stage and gradually flattens out over time. The comparative analysis of temperature under different fault conditions shows that the node temperature is most affected by the rolling element fault. Experiments and actual line temperature data are used to verify the validity of the model. The comparison results show that the simulation aligns well with experimental and line data. The transient temperature‐field model of the bearing rotor system in high‐speed trains can effectively simulate and predict the temperature change process of each node of the system. The simulation results hold certain theoretical guiding significance for further research and practical applications in ensuring train operation safety.

A Multiline Structured Light Sensor-Based System for Measuring the Geometries of Train Wheelsets

A Multiline Structured Light Sensor-Based System for Measuring the Geometries of Train Wheelsets

Detection of Train Wheelset Tread Defects with Small Samples Based on Local Inference Constraint Network

Due to the long-term service through wheel-rail rolling contact, the train wheelset tread will inevitably suffer from different types of defects, such as wear, cracks, and scratches. The effective detection of wheelset tread defects can provide critical support for the operation and maintenance of trains. In this paper, a new method based on a local inference constraint network is proposed to detect wheelset tread defects, and the main purpose is to address the issue of insufficient feature spaces caused by small samples. First, a generative adversarial network is applied to generate diverse samples with semantic consistency. An attention mechanism module is introduced into the feature extraction network to increase the importance of defect features. Then, the residual spine network for local input decisions is constructed to establish an association between sample features and defect types. Furthermore, the network’s activation function is improved to obtain higher learning speed and accuracy with fewer parameters. Finally, the validity and feasibility of the proposed method are verified using experimental data.

Rapid measurement method for key dimensions of train wheelset based on improved image processing algorithm

The key dimensions of train wheelsets change with the increase of running time. To ensure the safe operation of the train, the key dimensions should meet the relevant technical requirements. Maintenance of wheelsets and measurement of key dimensions are important part of the daily maintenance work. A rapid measurement method based on image processing algorithms for key dimensions of hand-held wheelsets integrating multiple parameter measurements is studied. The general framework of the system is examined and the roles of the modules are described. The optical center for the initial position of the continuous line spot is searched. The continuous line spot center extraction algorithm during tread measurement is optimized. A three-dimensional model is reconstructed using point cloud data, then key dimensions are measured and calculated from the model. In order to verify the feasibility of the method, traditional measurement methods are used for comparison tests. The results show that the method is effective in the daily maintenance of trains.

A comprehensive laser image dataset for real-time measurement of wheelset geometric parameters

Railway transportation has experienced significant growth worldwide, offering numerous benefits to society. Most railway accidents are caused by wheelset faults so it’s significant to monitor wheelset conditions. Therefore, we need to collect wheelset images, repaint them, extract laser stripe centerlines, construct 3D contour, and measure their geometric parameters to judge the wheelset’s conditions. Deep learning can fulfill the tasks satisfyingly because it’s adaptable, robust, and generalize compared with traditional methods. To train the deep learning models effectively, we need rich and high-quality wheelset datasets. So far, there are no applicable public train wheelset datasets available, which greatly hinders the research on train wheelsets. Thus we construct a publicly available Wheelset Laser Image Dataset (WLI-Set). WLI-Set consists of four sub-datasets, Original, Inpainting, Segmentation, and Centerline. The dataset contains abundant annotated multiline laser stripe images that can facilitate the research on train wheelsets effectively.

Optimal allocation method of electric/air braking force of high-speed train considering axle load transfer

Reasonable distribution of braking force is a factor for a smooth, safe, and comfortable braking of trains. A dynamic optimal allocation strategy of electric-air braking force is proposed in this paper to solve the problem of the lack of consideration of adhesion difference of train wheelsets in the existing high-speed train electric-air braking force optimal allocation strategies. In this method, the braking strategy gives priority to the use of electric braking force. The force model of a single train in the braking process is analyzed to calculate the change of adhesion between the wheel and rail of each wheelset after axle load transfer, and then the adhesion of the train is estimated in real time. Next, with the goal of maximizing the total adhesion utilization ratio of trailer/motor vehicles, a linear programming distribution function is constructed. The proportional coefficient of adhesion utilization ratio of each train and the application upper limit of braking force in the function is updated according to the change time point of wheelset adhesion. Finally, the braking force is dynamically allocated. The simulation results of Matlab/Simulink show that the proposed algorithm not only uses the different adhesion limits of each trailer to reduce the total amount of braking force undertaken by the motor vehicle, but also considers the adhesion difference of each wheelset. The strategy can effectively reduce the risk and time of motor vehicles during the braking process and improve the stability of the train braking.

Dynamic-Projection-Integrated Particle-Filtering-Based Identification of Friction Characteristic Curve for Train Wheelset on Slipping Fault Condition

This paper proposes a dynamic-projection-integrated particle-filtering-based identification strategy for the friction characteristic curve of a train wheelset under the slipping fault condition. This strategy aims to achieve the identification of the fault friction characteristic curve (FFCC) in the early slipping fault stage. First, a multi-dimensional integrated particle-filtering (MDIPF)-based parameters correction method is proposed. The MDIPF constructs an error particle state transition model encompassing multi-dimensional parameters, which integrates inter-particle correlation to facilitate error fusion during the state transition process. Then, a dynamic projection domain (DPD)-based particle refinement method is proposed. The DPD constructed the contraction factors to dynamically fine-tune the particle projection domain. Finally, a multi-level evaluation-based identification method for the FFCC is proposed. And the dynamic-projection-integrated particle-filtering-based identification strategy is validated, which can actualize the rapid and accurate identification of the FFCC.

Multirotational Speed Data Augmentation and Data Repair of High-Speed Train Wheelset Bearings Using Graph Speed Classifier GAN

Multirotational Speed Data Augmentation and Data Repair of High-Speed Train Wheelset Bearings Using Graph Speed Classifier GAN

Early faint fault diagnosis of wheelset axlebox bearings in urban rail trains based on ICiSSA-MOMEDA

Circulant Singular Spectrum Analysis (CiSSA) performs well in the decomposition and extraction of the periodic components of nonstationary signals. However, the decomposition of signals in complex environments suffers from spectral aliasing and difficulties in extracting feature information. Therefore, based on CiSSA, an improved CiSSA and multipoint optimal minimum entropy deconvolution adjustment (ICiSSA-MOMEDA) is proposed and applied to the early faint fault diagnosis of axlebox bearings of urban rail train wheelsets. First, the optimal embedding dimension was computed adaptively and accurately using an improved Cao’s method. Then, the initial components obtained from the decomposition were reorganized using the K-ARs method. ICiSSA effectively solves the problems of spectrum confusion and fault-information dispersion. Finally, ICiSSA was combined with MOMEDA to improve its ability to detect weak fault information. The superiority of ICiSSA-MOMEDA was verified based on the analysis of the actual bearing data and comparison with other methods.

Dynamic hybrid observer-based early slipping fault detection for high-speed train wheelsets

Early slipping fault detection of High-speed Train (HST) wheelsets on ramped railway lines has been a challenging problem due to the difficulty of achieving accurate detection in a limited time-frame. A dynamic hybrid observer-based early slipping fault detection strategy is proposed. Firstly, a hybrid observer-based adhesion coefficient estimation method is proposed. The hybrid observer is constructed in an interconnected configuration, which integrates the estimated ramped line angle into the adhesion coefficient estimation. Then, a multivariate evaluation function (MEF)-based parameter dynamic adjustment method is proposed. The MEF is constructed to reconcile the trade-off of the speediness and smoothness of the hybrid observer. Finally, a dynamic adhesion coefficient-based early slipping fault detection method for HST wheelsets is proposed. And the proposed strategy is verified on the hardware-in-the-loop(HIL)-based platform. The test results show that the proposed strategy can actualize millisecond-level early slipping fault detection and reduce the false detection rate on ramped railway lines.

Prediction of Key Parameters of Wheelset Based on LSTM Neural Network

As a key component of rail vehicle operation, the running condition of the wheelset significantly affects the operational safety of track vehicles. The wheel diameter, flange thickness, and flange height are key dimensional parameters of the wheelset, which directly influence the correct position of wheelsets on the track, and the train needs to be continuously monitored during the passenger operation. A prediction model for the key parameters of the wheelset is established based on LSTM (long short-term memory) neural network, and real measured data of wheelsets from the Shanghai Metro vehicles are selected. The predicted results of the model are compared and analyzed, and the results show that the LSTM-based prediction model for key parameters of wheelsets performs well, with the mean absolute percentage errors (MAPEs) for wheel diameter, flange thickness, and flange height being 0.08%, 0.42%, and 0.44%, respectively, for the left wheel and 0.07%, 0.35%, and 0.44%, respectively, for the right wheel. The prediction model for the train wheelset parameters established in this paper has a good prediction accuracy. By predicting the key parameters of the wheelset, the faults and causes of the wheelset can be found and determined, which is helpful for engineers to overhaul the wheelset faults, make maintenance plans, and perform preventive maintenance.

Investigation on smoothed finite element methods using linear tetrahedral elements for high-speed train hollow axle strength analysis

PurposeThis paper aims to investigate the performance of two novel numerical methods, the face-based smoothed finite element method (FS-FEM) and the edge-based smoothed finite element method (ES-FEM), which employ linear tetrahedral elements, for the purpose of strength assessment of a high-speed train hollow axle.Design/methodology/approachThe calculation of stress for the wheelset, comprising an axle and two wheels, is facilitated through the application of the European axle strength design standard. This standard assists in the implementation of loading and boundary conditions and is exemplified by the typical CRH2 high-speed train wheelset. To evaluate the performance of these two methods, a hollow cylinder cantilever beam is first used as a benchmark to compare the present methods with other existing methods. Then, the strength analysis of a real wheelset model with a hollow axle is performed using different numerical methods.FindingsThe results of deflection and stress show that FS-FEM and ES-FEM offer higher accuracy and better convergence than FEM using linear tetrahedral elements. ES-FEM exhibits a superior performance to that of FS-FEM using linear tetrahedral elements, showing accuracy and convergence close to FEM using hexahedral elements.Originality/valueThis study channels the novel methods (FS-FEM and ES-FEM) in the static stress analysis of a railway wheelset. Based on the careful testing of FS-FEM and ES-FEM, both methods hold promise as more efficient tools for the strength analysis of complex railway structures.

Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network

Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network

Fault Diagnosis of Train Wheelset Bearing Roadside Acoustics Considering Sparse Operation with GA-RBF

Trackside acoustic signals are useful for non-contact measurements as well as early warnings in the diagnosis of train wheelset bearing faults. However, there are two important problems when using roadside acoustic signals to diagnose wheel-to-wheel bearing faults; one is the presence of strong interference from strong noise and high harmonics in the signal, and the other is the low efficiency of bearing fault identification caused by it. Therefore, from the viewpoint of solving the two problems, a sparse operation method is proposed for denoising and detuning the modulation of the roadside acoustic signal, and a machine learning classifier with a Genetic Algorithm (GA)-optimized Radial Basis Neural Network (RBFNN) is proposed to improve the rate at which the features of roadside acoustic signal faults are recognized. Firstly, the background noise is filtered out from the Doppler-corrected acoustic signal using the Sparse Representation method, and the inverse wavelet transform is reconstructed into a noiseless signal. Secondly, the interference high-harmonic signal in the signal is filtered out using the Resonant Sparse Signal Decomposition (RSSD) method. Then, the GA is selected to optimize the parameters of the RBF neural network and build a fault diagnosis model. Finally, the extracted acoustic signal feature set is trained on the network model, and the trained model is used for testing. In summary, the sparse operation on the roadside acoustic signal processing and the GA-RBFNN diagnosis model were verified as being very effective in the diagnosis of roadside acoustic train wheel pair faults through the simulation experiment.

URS: A Light-Weight Segmentation Model for Train Wheelset Monitoring

To detect the wheelset deformation and wear, an intuitive method is to first collect wheelset multi-line laser stripe images by monitors, and then extract the centerlines to construct 3D contours that are transferred to the cloud data center by 6G communication. The images, however, contain flairs and fractures due to the influence of environmental interference and reflected light on the smooth surfaces. The image defects affect the accurate extraction of stripe centerlines. To segment the defects and inpaint them, we propose a new lightweight U-shaped segmentation model URS. A target-shaped receptive field is designed to efficiently extract the details of the local, the ring-shaped, and the cross-shaped context around the local, which facilitates segmenting various defects. A scale-select sub-module is designed to adjust the weights of features from different receptive fields. To train the model, a multi-line laser image defect segmentation dataset MLIDSD is constructed. Experiments demonstrate that the performance of our model surpasses twelve SOTA models explicitly and can achieve a balance between the accuracy and the lightweight requirement.

Causes and evolution of asymmetric polygonal wear of metro train wheelsets

Wheel acoustic roughness of one metro line in China shows that the wheel polygonal wear (WPW) on both sides of the wheelset is asymmetrical. The dominant harmonics of the left and right wheels are 12–13, but with large differences in acoustic roughness levels. To analyse the causes of the asymmetrical WPW (AWPW), an investigation of the acoustic roughness of the wheels and rails and a modal analysis of the wheelset–track system are carried out. In addition, a long-term wear model considering the flexibility of the wheelset and track is established to provide insight into the initiation and evolution of the AWPW. The results of the experiments and simulations show that the natural asymmetric vibration mode in the wheelset–track system with a frequency of 83 Hz is the main cause of WPW, which can be excited on sharp curves. The difference between the lengths of the left and right curved tracks with small radius is the cause of AWPW. The residual WPW after reprofiling and rail corrugation with a wavelength of about 200 mm are the main sources of excitation for the asymmetric natural vibration.

Deformable residual attention network for defect detection of train wheelset tread

Deformable residual attention network for defect detection of train wheelset tread

A recursive multi-head graph attention residual network for high-speed train wheelset bearing fault diagnosis

Wheelset bearings are a core component of high-speed trains, and their fault diagnosis is the key to smooth operation. Deep learning is widely used in fault diagnosis due to its powerful classification ability. To explicitly fit the features of vibration signals and further explore the relationship between the signals, the graph attention network (GAT) is becoming a focus of research. Unlike traditional graph neural networks, GATs can focus on edges with stronger correlations with vertices, making the model more powerful when fitting graph samples in non-Euclidean space. However, existing GATs have two limitations. Firstly, most graph construction methods do not consider the characteristics of vibration signals, so the graph interpretation is not good. Secondly, the existing methods of graph attention coefficient cannot effectively reflect the importance of edges. To address these issues, a recursive multi-head graph attention residual network (RMHGARN) is proposed. In RMHGARN, vibration signals are transformed into recurrence graphs due to the recursive nature of nonlinear time series. A multi-kernel Gaussian symmetric graph attention mechanism is proposed to obtain the Hilbert spatial distribution between neighboring vertices. In addition, a graph encoding module is proposed to improve the feature representation of input samples. The effectiveness and superiority of RMHGARN under strong noise samples are verified using three wheelset bearing datasets.

A Multichannel MN-GCN for Wheelset-Bearing System Fault Diagnosis

The working condition of high-speed train wheelset bearings is complex and bad, which makes its vibration signal contain strong noise. To obtain more information of samples, signals are constructed into graphs and fit by graph convolution network (GCN). The existing GCN-based models still have some problems, such as insufficient theoretical basis of graph and the unstable and overfitting during training of models, which significantly limits the diagnosis accuracy. To address these issues, first, a weighted <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\varepsilon $ </tex-math></inline-formula> -recurrence network is proposed to construct the recurrence graph (RG). The recurrence relationship between samples is analyzed by the recursive nature of vibration signals. Maximum mean discrepancy (MMD) is used to obtain the regenerated Hilbert spatial distribution distance between two samples to reduce the weight gap between different recursive pairs. Also, the proposed method has better ex ante interpretability. Second, a vertex mean normalization (MN) layer is proposed to normalize individual vertex features to introduce some spatial perturbations and reduce the variance of vertex features, which can improve training stability and reduce overfitting. In addition, multichannel MN-GCN is proposed to fit multiscale graph features. Analyze recurrence nature of samples at different scales through RGs with varying densities of connection to improve the antinoise ability. Experimental results show that the proposed model can obtain spatial topology information accurately and improve the wheelset-bearing system fault diagnosis performance.

Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision

Whether the wheelset of a high-speed train has defects such as cracks is very important to the safety of high-speed trains. Hence, the wheelset must be regularly inspected for flaws. For flaw detection of a wheelset, it is necessary to record the axle end information of the wheelset to correlate with the flaw detection results. To quickly and accurately identify the axle end mark of the wheelset, an automatic identification method based on machine vision is proposed. Our method identifies seven types of marks on the axle end, including the smelting number, steel grade number, unit number, sequence number, year and month, axle type mark, and the azimuth mark. Using the established automatic identification method of axle end marks, based on Retinex theory, an improved dual-core Laplacian combined with Gaussian filtering operation is proposed to solve the problem of the low contrast of the wheelset axle end image. An improved image tilt correction algorithm based on the combination of Hough circle detection and bilinear interpolation is proposed, which solves the angle tilt problem of the target character area of the axis end image. To handle the various types of axis end markers and the small amount of data, a retraining method to improve recognition accuracy is proposed. This method first uses Chi_Sim as the basic font for training and then retrains based on the trained font. Finally, Tesseract-OCR is used to improve the accuracy of the recognition results. Experiments are carried out by developing an automatic recognition program for axle end marks. The results show that the proposed method can effectively identify and classify seven-character types, and the recognition accuracy reaches 96.88% while the recognition time of each image is 5.88 s.