High-speed Train Bogie Research Articles

Multiple Convolutional Recurrent Neural Networks for Fault Identification and Performance Degradation Evaluation of High-Speed Train Bogie.

As an important part of high-speed train (HST), the mechanical performance of bogies imposes a direct impact on the safety and reliability of HST. It is a fact that, regardless of the potential mechanical performance degradation status, most existing fault diagnosis methods focus only on the identification of bogie fault types. However, for application scenarios such as auxiliary maintenance, identifying the performance degradation of bogie is critical in determining a particular maintenance strategy. In this article, by considering the intrinsic link between fault type and performance degradation of bogie, a novel multiple convolutional recurrent neural network (M-CRNN) that consists of two CRNN frameworks is proposed for simultaneous diagnosis of fault type and performance degradation state. Specifically, the CRNN framework 1 is designed to detect the fault types of the bogie. Meanwhile, CRNN framework 2, which is formed by CRNN Framework 1 and an RNN module, is adopted to further extract the features of fault performance degradation. It is worth highlighting that M-CRNN extends the structure of traditional neural networks and makes full use of the temporal correlation of performance degradation and model fault types. The effectiveness of the proposed M-CRNN algorithm is tested via the HST model CRH380A at different running speeds, including 160, 200, and 220 km/h. The overall accuracy of M-CRNN, i.e., the product of the accuracies for identifying the fault types and evaluating the fault performance degradation, is beyond 94.6% in all cases. This clearly demonstrates the potential applicability of the proposed method for multiple fault diagnosis tasks of HST bogie system.

Prognostics and Health Management for Maintenance Practitioners - Review, Implementation and Tools Evaluation

In literature, prognostics and health management (PHM) systems have been studied by many researchers from many different engineering fields to increase system reliability, availability, safety and to reduce the maintenance cost of engineering assets. Many works conducted in PHM research concentrate on designing robust and accurate models to assess the health state of components for particular applications to support decision making. Models which involve mathematical interpretations, assumptions and approximations make PHM hard to understand and implement in real world applications, especially by maintenance practitioners in industry. Prior knowledge to implement PHM in complex systems is crucial to building highly reliable systems. To fill this gap and motivate industry practitioners, this paper attempts to provide a comprehensive review on PHM domain and discusses important issues on uncertainty quantification, implementation aspects next to prognostics feature and tool evaluation. In this paper, PHM implementation steps consists of; (1) critical component analysis, (2) appropriate sensor selection for condition monitoring (CM), (3) prognostics feature evaluation under data analysis and (4) prognostics methodology and tool evaluation matrices derived from PHM literature. Besides PHM implementation aspects, this paper also reviews previous and on-going research in high-speed train bogies to highlight problems faced in train industry and emphasize the significance of PHM for further investigations.

Realistic fatigue damage assessment of a high-speed train bogie frame by damage consistency load spectra based on measured field load

This work focused on the realistic fatigue damage assessment of a high-speed train bogie frame under actual service conditions. The bogie frame and its attached components were strain gauged and statically calibrated to measure field load histories. The stress histories and load–strain response matrix at the fatigue key points (FKPs) were obtained for calculation of the actual and load spectra damage, respectively. According to the damage consistency criterion, the damage consistency load spectra (DCLS) were established based on the measured field load by a novel calibration method. This method was based on that the damage percentage of each load series at the FKPs can produce a more reasonable set of calibration coefficients, and the DCLS established by this method has a higher fatigue assessment accuracy. The damage ratios indicated that the DCLS yielded a more realistic fatigue damage assessment than the fatigue test spectrum specified in the relevant standards.

SCC behavior and susceptibility prediction mode of SMA490BW weathering steel under cathodic potential

SMA490BW weathering steel has been used to manufacture high speed train bogie structures. However, its stress corrosion cracking (SCC) behavior was not very clearly, let alone the prediction mode. In this work, combined with fracture surface analysis by SEM, electrochemical impedance spectroscopy (EIS) and potentiodynamic polarization analysis, the SCC behavior of SMA490BW steel in 3.5 wt.% NaCl solution under cathodic potentials from open circuit potential (OCP) to −1200 mVSCE (SCE = saturated calomel electrode) was studied using slow strain rate tensile (SSRT) method at 25 °C. The results indicated that the SCC susceptibility index (ISSRT) decreased with the applied potential negative shift from OCP (ISSRT = 0.31) to −800 mVSCE (ISSRT = 0.11) by anodic dissolution (AD) mechanism, and then sharply increased with the potential negatively increasing (ISSRT = 0.41 at −1200 mVSCE) by hydrogen embrittlement (HE) mechanism. The SCC susceptibility could be preliminarily predicted using the mode founded as a function of charge transfer resistance (Rt): This study will be helpful for the service assessment of high speed train bogie structure and other structures manufactured by SMA490BW steel.

Fault diagnosis of high-speed train bogie based on LSTM neural network

Fault diagnosis of high-speed train bogie based on LSTM neural network

Fault Diagnosis of High-Speed Train Bogie Based on Capsule Network

Intelligent fault diagnosis of bogie is fundamental for the reliability, stability, and security of a high-speed train (HST). However, thorny issues, including complicated structure of bogie and complex motion states of HST, aggravate the difficulty of research, where traditional approaches for fault diagnosis might fail. In this article, CapsNet, a contemporary novel neural network architecture, in which a single unit called capsule known for its uniqueness of multidimension and abundant spatial information, is adopted to accomplish the recognition and classification of seven working conditions of a HST bogie, comprising both single and compound faults. The experimental accuracy achieved is 96.65%, which proves the efficiency and potency of CapsNet in this regard. The ability of CapsNet to diagnose faults of a bogie in this article exceeds that of a convolutional neural network (CNN), especially for compound ones. Moreover, the method employed is capable of extracting features from raw data automatically and is independent of expert experience or knowledge about signal processing.

Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model

High-speed rail (HSR) is being developed in Asian and European countries to satisfy the rapidly growing demand for intercity services and to shore up economic growth. The rapid growth of HSR, however, has posed great challenges regarding operation safety, reliability and ride comfort. Irregular wheel defects can induce high-magnitude impact forces hindering safety and ride comfort of HSR and may also cause damage to rail tracks and vehicles. The focus of this study is to develop a real-time defect detection methodology based on Bayesian dynamic linear model (DLM) enabling to detect potentially defective wheels in real time. The proposed methodology embraces logics for (i) prognosis, (ii) potential outlier detection, (iii) identification of change occurrence (change-point detection), and (iv) quantification of damage extent and uncertainty. Relying on the strain monitoring data acquired from high-speed train bogies, the Bayesian DLM for characterizing the actual stress ranges is established, by which one-step forecast distribution is elicited before proceeding to the next observation. The detection of change-point is executed by comparing the routine model (forecast distribution generated by the Bayesian DLM) and an alternative model (the mean value is shifted by a prescribed offset) to determine which better fits the actual observation. If the comparison results are in favor of the alternative model, it is claimed that a potential change has occurred. Whether such an observation is an outlier or the beginning of a genuine change (change-point), three metrics (i.e., Bayes factor, maximum cumulative Bayes factor and run length) are performed for further identification. Once a change-point is confirmed, Bayesian hypothesis testing is conducted for the purpose of damage extent assessment and uncertainty quantification. A severe change, if identified, implies that the quality of train wheels has suffered from a significant alteration due to defects. In the case study, two cases making use of strain monitoring data acquired by fiber Bragg grating (FBG) sensors affixed on bogies are illustrated to verify the performance of the proposed methodology for real-time wheel defect detection of in-service high-speed trains.

Acoustic emission source localization method for high-speed train bogie

Bogie is one of the most critical parts of high-speed train and is directly related to the operation quality and safety of the train. However, currently no dynamic non-destructive testing method exists for real-time monitoring. Therefore, this paper proposes a new damage localization method for high-speed train bogie dynamic testing. The acoustic emission testing technology is applied to test the vulnerable welding parts of the bogie with time reversal localization method. Firstly, the bogie welding parts structure model based on finite element software is established. Then an acoustic emission damage signal is sent from the model and the acoustic emission source signal is received by the preset acoustic emission sensor. And the accurate localization of damage is achieved by dealing with the received signal according to the time reversal focusing principle and imaging the acoustic emission source. The simulation experiments show that the proposed method can accurately find the damaged localization. And finally, the method has been verified through experiment, and the results show it can effectively improve signal energy of the damage source, and the position of the damage source can be shown accurately through signal reconstruction and localization in the detection area.

Effect of Snow Parameters on Snow Accumulation in High-speed Train Bogies

Effect of Snow Parameters on Snow Accumulation in High-speed Train Bogies

Fault Diagnosis of High-Speed Train Bogie by Residual-Squeeze Net

Fault diagnosis of high-speed train (HST) bogie is essential in guaranteeing the normal daily operation of an HST. In prior works, feature extraction from multisensor vibration signals mainly relies on signal processing methods, which is independent of the classification process. Based on convolutional neural networks (CNNs), this paper presents a novel fault diagnosis system using the residual-squeeze net (RSNet), which is directly applicable to raw data (time sequences) and does not require any signal transformation or postprocessing. In this network, information fusion is achieved by using the convolutional layer. More specifically, via the squeeze operation, an optimal combination of channels is learnt by training the network. Experimental results obtained by using SIMPACK simulation data demonstrate the effectiveness of the proposed approach in both complete failure case and single failure case, with diagnosis accuracy near 100%. The proposed approach also shows good performance in identifying the locations of faulty components. Comparisons between RSNet and competitive methods shows the advantages of RSNet for fault classification.

Suspension parameters optimum of high-speed train bogie for hunting stability robustness

ABSTRACT Hunting stability of high-speed train is an important objective for the optimization of bogie suspension parameters. An adequate hunting stability margin is required for the high-speed train. Besides, a remarkable ability to resist the influence caused by the disturbance of bogie suspension parameters and wheel-rail contact parameters on hunting stability is also required. In this paper, the concept of robustness of hunting stability is proposed, and the indexes for vehicle speed robustness, suspension parameter robustness, and wheel-rail contact equivalent conicity robustness are defined and chosen as the optimization objectives for the bogie suspension parameters. The multi-objective optimization method is used, which can optimize the key suspension parameters simultaneously to balance the multiple complicated and conflicting performance indexes, and six groups of typical suspension parameters are obtained by cluster analysis of Pareto frontier. The correlation between suspension parameters and each index is analysed by multivariate statistical analysis, and the optimization and matching rules for key suspension parameters of the high-speed train bogie based on hunting stability robustness are obtained. With the application of this method during the design process of suspension parameters, the hunting stability of high-speed trains in service can be greatly improved.

A multi-perspective architecture for high-speed train fault diagnosis based on variational mode decomposition and enhanced multi-scale structure

The performance degradation and failure of high-speed train bogie would directly threaten the safe long-term operation of the vehicle. The fault diagnosis based on vibration signals is encountering difficulties as nonlinearity, high complexity, strong coupling, and high uncertainty. To address these challenges, this paper proposes a multi-perspective architecture for fault diagnosis, based on variational mode decomposition and enhanced multi-scale convolutional neural network. The proposed method provides multiple perspectives for the multi-channel and multi-component signal analysis, including perspectives from channel, component and time scale, with low input dimension and reduced model complexity. Signal features under different perspectives can be adaptively extracted. The effectiveness of the proposed method is validated on high-speed train fault data and rolling element bearings dataset. The experimental results show that the proposed scheme not only improves the accuracy of fault diagnosis but also has superior noise robustness which could be valuable for practical applications of complex systems, especially in dynamic environments.

Microstructure and properties of laser-arc hybrid welding thick bainitic steel joints with different arc position

The realization of 12mm thick laser-arc hybrid welding technology is the prerequisite for efficient production of new high-speed train bogies. In this work, for the laser-leading hybrid welding, the problem of hump defects in the root of the weld is easy to occur. The arc-leading mode is chosen to obtain the welded joint of high-strength bainitic steel with no hump, no unfilled and no porosity defects. Then the microstructure distribution of the welds of the high-strength bainitic steel is analyzed, which the weld metal is mainly composed of acicular ferrite and lath bainite and the heat affected zone mainly concludes coarse-grained bainite and granular bainite. Then, under the optimal process, the hardness distribution, arc action area size and weld impact performance of the laser-leading and arc-leading welds were compared. It was found that the arc-leading weld hardness distribution was more uniform and stable, and the hardness peaks both appear in the HAZ (coarse lath bainite), and the valleys both appear in partial phase-change zones (Bulk ferrite). Meanwhile, the arc-leading weld impact performance is 21.49% higher than that of laser-leading.

Fatigue life reliability evaluation in a high-speed train bogie frame using accelerated life and numerical test

Durability fatigue tests for full-scale structures are essential to ensure the fatigue reliability and operational safety of high-speed trains. An accelerated life test (ALT) method is first used to predict the fatigue life of a full-scale bogie frame. Three step-up acceleration load spectrum is compiled for an ALT on the basis of the failure mechanism consistency principle. The ALT of a full-scale bogie frame is conducted. Then, the acceleration coefficient and cycle times from the accelerated load level to the working load level are calculated. Based on the equal damage principle, combined with the finite element calculation, the fatigue life of the bogie frame under acceleration load spectrum is extrapolated. The ALT method is used to compile the acceleration load spectrum and to perform fatigue tests to analyze the acceleration coefficients and predict the fatigue life for a full-scale bogie frame, which provides a reference for the reliability evaluation of large structures.

Condition recognition of high-speed train bogie based on multi-view kernel FCM

Monitoring the operating status of a High-Speed Train (HST) at any moment is necessary to ensure its security. Multi-channel vibration signals are collected by sensors installed on bogies and beneficial information are extracted to determine the running condition. Based on multi-view clustering and considering different views of complementary information, this study proposes a Multi-view Kernel Fuzzy C-Means (MvKFCM) model for condition recognition of the HST bogie. First, fast Fourier transform coefficients of HST vibration signals of all channels are extracted. Then, the fuzzy classification coefficient of every channel is calculated after clustering to select the appropriate channels. Finally, the selected channels are used to cluster by MvKFCM and the conditions of HST are determined. Experimental results show that the selection is effective to maintain rich feature information and remove redundancy. Furthermore, the condition recognition rate of MvKFCM is higher than that of single-view and four other multiple-view clustering algorithms.

Measurement of Aerodynamic Bogie Noise and Velocity Profile around the Bogie of High-speed Train

Measurement of Aerodynamic Bogie Noise and Velocity Profile around the Bogie of High-speed Train

Fault Diagnosis of High-speed Train Bogie Based on Deep Neural Network

As an important part of high-speed train (HST), the performance of bogie has a direct impact on the safety of train. Real-time monitoring and evaluation of the operating state of bogie are of great significance for the safe operation of the train. The traditional signal processing methods are difficult to analyze the complex vibration signals of bogie which are collected during train operation. Deep Neural Network (DNN) has been widely used in the field of fault diagnosis due to its good performance in feature extraction of complex data. In this paper, DNN is taken as the overall framework. Failure modes include four states: air springs completely fail, anti-yaw dampers completely fail, lateral dampers completely fail and normal operation. In these four states, HST is running at the speed of 200km/h. Using the data collected in one hour of simulation as the input signal of DNN, the diagnostic accuracy of the four working conditions reached 92.5%. Experimental result shows that DNN has a good performance in multi-class fault diagnosis of bogie.

Convolutional Recurrent Neural Network for Fault Diagnosis of High-Speed Train Bogie

Timely detection and efficient recognition of fault are challenging for the bogie of high-speed train (HST), owing to the fact that different types of fault signals have similar characteristics in the same frequency range. Notice that convolutional neural networks (CNNs) are powerful in extracting high-level local features and that recurrent neural networks (RNNs) are capable of learning long-term context dependencies in vibration signals. In this paper, by combining CNN and RNN, a so-called convolutional recurrent neural network (CRNN) is proposed to diagnose various faults of the HST bogie, where the capabilities of CNN and RNN are inherited simultaneously. Within the novel architecture, the proposed CRNN first filters out the features from the original data through convolutional layers. Then, four recurrent layers with simple recurrent cell are used to model the context information in the extracted features. By comparing the performance of the presented CRNN with CNN, RNN, and ensemble learning, experimental results show that CRNN achieves not only the best performance with accuracy of 97.8% but also the least time spent in training model.

Effect of bogie fairings on the snow reduction of a high-speed train bogie under crosswinds using a discrete phase method

This paper investigated the wind-snow flow around the bogie region of a high-speed train under crosswinds using a coupled numerical method of the unsteady Realizable k-e turbulence model and discrete phase model (DPM). The flow features around the bogie region were discussed and the influence of bogie fairing height on the snow accumulation on the bogie was also analyzed. Here the high-speed train was running at a speed of 200 km/h in a natural environment with the crosswind speed of 15 m/s. The mesh resolution and methodology for CFD analysis were validated against wind tunnel experiments. The results show that large negative pressure occurs locally on the bottom of wheels, electric motors, gear covers, while the positive pressure occurs locally on those windward surfaces. The airflow travels through the complex bogie and flows towards the rear bogie plate, causing a backflow in the upper space of the bogie region. The snow particles mainly accumulate on the wheels, electric motors, windward sides of gear covers, side fairings and back plate of the bogie. Longer side fairings increase the snow accumulation on the bogie, especially on the back plate, side fairings and brake clamps. However, the fairing height shows little impact on snow accumulation on the upper region of the bogie. Compared to short side fairings, a full length side fairing model contributes to more than two times of snow accumulation on the brake clamps, and more than 20% on the whole bogie.

Mechanical and chemical stability of super-hydrophobic coatings on SMA490BW substrate prepared by HVOF spraying

SMA490BW weathering steel is an important engineering material employed in the bogies of high-speed train. However, the bogies are also subject to ice accumulation, corrosion, sand abrasive, and heterogeneous wear or other hazard. In this paper, the superhydrophobic (SH) surface on SMA490BW steel is fabricated by using High Velocity Oxygen Fuel (HVOF) spraying technology and low surface energy modification. Self-cleaning effect, hydrophobic durability, wear resistance, the weather resistance, PH stability and electrochemical properties were discussed. The results showed that the as prepared coating possesses CA of 154.3 ± 3° and sliding angle of 4.1 ± 0.1°. The CA has no obvious fluctuations after immersing in water for different time and at PH in the range of 1 to 7. The CA is still above 150° after abrasion for 2400 mm. The SH coating possesses higher Ecorr and lower Icorr compared with SMA490BW substrate and HVOF WC-12Co coating. The SH coating has a long-term water repellency towards environmental conditions during weathering. The SH coating possesses excellent mechanical and chemical stability, which is benefit for applying this coating on the high-speed train bogies.