Vertical Track Irregularities Research Articles

Track vertical irregularity estimation for railway bridges using a novel and lightweight deep-learning architecture

A comprehensive methodology is presented for the estimation of track vertical irregularities of railway bridges from vehicle responses, based on a novel and lightweight multi-layer-perceptron (MLP) deep learning architecture. Firstly, a vehicle–track–bridge interaction (VTBI) model is established for the generation of the datasets of deep learning networks. Secondly, the lightweight deep learning architecture is meticulously designed to identify the track's vertical irregularities. Then, the effectiveness of the proposed technique is validated through examples of a single-span simple bridge and a three-span bridge. Further, the sensitivity of the present method against various factors is investigated, including different combinations of vehicle responses, measurement noise, vehicle speed and different classes of track irregularity. It is confirmed that the identified track irregularities of the railway bridges, regardless of irregularity class and noise level, are in excellent agreement with the ground-truth ones. The increase in vehicle speed to some extent reduces the estimation accuracy of the irregularity. The proposed method has higher identification accuracy and efficiency for longer irregularity sequences of multi-span railway bridges.

Quantitative Detection of Vertical Track Irregularities under Non-Stationary Conditions with Variable Vehicle Speed.

Track irregularities directly affect the quality and safety of railway vehicle operations. Quantitative detection and real-time monitoring of track irregularities are of great importance. However, due to the frequent variable vehicle speed, vehicle operation is a typical non-stationary process. The traditional signal analysis methods are unsuitable for non-stationary processes, making the quantitative detection of the wavelength and amplitude of track irregularities difficult. To solve the above problems, this paper proposes a quantitative detection method of track irregularities under non-stationary conditions with variable vehicle speed by order tracking analysis for the first time. Firstly, a simplified wheel-rail dynamic model is established to derive the quantitative relationship between the axle-box vertical vibration and the track vertical irregularities. Secondly, the Simpson double integration method is proposed to calculate the axle-box vertical displacement based on the axle-box vertical acceleration, and the process error is optimized. Thirdly, based on the order tracking analysis theory, the angular domain resampling is performed on the axle-box vertical displacement time-domain signal in combination with the wheel rotation speed signals, and the quantitative detection of the track irregularities is achieved. Finally, the proposed method is validated based on simulation and field test analysis cases. We provide theoretical support and method reference for the quantitative detection method of track irregularities.

Railway track vertical irregularities classification based on vehicle response using machine learning method

The common method of railway track irregularities assessment currently used, based on track geometry measurement data, is expensive to run, disrupts regular train services, and shows poor correlation with the actual vehicle response when running on a given track section. Vehicle response-based track irregularities assessment methods aim to overcome the shortcomings of geometry measurement-based methods. One of the possible methods is to establish the correlation between track geometry and vehicle response statistically using machine learning. Classification algorithms have been used in previous research for categorizing track sections into discrete classes. In this paper, in addition to discrete classification, the probability for which a track section is categorized as a certain class is presented. Testing results of the trained machine learning classification model showed high accuracy, precision, and recall. The results indicated that this method is suitable for classification of the vertical track irregularities. Further testing was performed with shifted classification threshold. The finding showed that the classification model’s precision and recall could be adjusted by shifting the classification threshold. The result of this study highlights the potential of machine learning classification usage for track irregularities assessment.

Dynamic Stress Response in a Novel Prestressed Subgrade under Heavy-Haul Train Loading: A Numerical Analysis

To explore the dynamic transient characteristics induced by passing heavy-haul trains in newly-developed prestressed subgrade, two three-dimensional finite element models were constructed in the time domain using ABAQUS software. These models are categorized as train-track-prestressed subgrade and train-track-unreinforced subgrade. The numerical models also incorporated the vertical track irregularity commonly found in heavy-haul railways. The investigation aims to discern the dynamic stress response differences in both types of subgrades under three distinct train axle loads. Model validation occurred through comparisons with field tests gathered from various heavy-haul railways in China, as well as analogous numerical simulation cases. The findings indicate that track irregularity results in an asymmetric distribution of dynamic stress on the subgrade surface beneath both left and right rails, aligned transversely with the subgrade centerline. Additionally, this asymmetry is notably pronounced. The peak dynamic stress on the subgrade surface beneath the rails for both subgrades increases with escalating train axle loads. However, the prestressed reinforcement structure (PRS) effectively modulates this phenomenon, with the controlling advantage intensifying as train axle load increases. The average dynamic stress level in the prestressed subgrade is marginally lower than in the unreinforced subgrade within the roadbed layer beneath rails. Furthermore, train axle loads amplify the variation level of dynamic stress in the subgrade. However, the variable coefficient of dynamic stress in the prestressed subgrade is less than in the unreinforced subgrade, suggesting that PRS contributes positively to maintaining subgrade dynamic stability. In terms of the longitudinal distribution of peak dynamic stress, both subgrades exhibit normal distribution at varying depths within the roadbed layer. Lastly, the additional dynamic stress in prestressed steel bars also rises with increasing train axle loads. Nonetheless, it remains substantially lower than the static target pre-tensile stress. Moreover, the dynamic responses of prestressed steel bars in different rows attenuate as depth increases away from the subgrade surface. In summary, the study establishes that PRS significantly enhances the dynamic stability of railway subgrade.

PEM-based random vibration analysis under service-braking conditions on an irregular track

PurposeAccording to relevant research, non-uniform speed has a significant impact on the vehicle-track systems. Up to now, research work on it is still very limited. In this paper, the PEM is adopted to further transform it into a deterministic process to solve the vehicle’s problem of running at a non-uniform speed.Design/methodology/approachThe multi-body vehicle model has 10 degrees of freedom and the track is regarded as a finite long beam supported by lumped sleepers and ballast blocks. They are connected via linear Hertz springs. The vertical track irregularity is a Gaussian stationary process in the space domain. It is transformed into a uniformly modulated nonstationary random process in the time domain with respect to the non-uniform vehicle speed. By solving the equation of motion of the coupled vehicle-track system with the pseudo-excitation method, the pseudo-response and consequently the power spectral density and the standard deviation of the structural response can be obtained.FindingsTwo kinds of vehicle braking programs are taken in the numerical example and some beneficial conclusions are drawn.Originality/valueThe pseudo-excitation method (PEM) was used to perform the random vibration analysis of a coupled non-uniform speed vehicle-track system. Transforming the track irregularity into a uniformly modulated nonstationary random process in time domain with respect to the non-uniform vehicle speed was undertaken. The pseudo-response of the coupled system is solved by applying the Newmark algorithm with constant space integral steps. The random vibration transfer mechanism of the coupled system is fully discussed.

Measuring vertical track irregularities from instrumented heavy haul railway vehicle data using machine learning

This paper proposes a data-driven approach to estimating geometric track irregularities from instrumented railway vehicle (IRV) data. Machine learning is used to find the nonlinear mapping between IRV data and track irregularities. A dynamic model of the BRA1 railway vehicle was used to generate an artificial dataset that contains variables that are measured by the real BRA1 IRV and other variables measured by IRVs found in the literature. An extensive data analysis step was done to verify if the current instrumentation of the BRA1 IRV is sufficient for obtaining both lateral and vertical track irregularities. Feature engineering based on wagon movements, signal integration and time domain statistical metrics were applied to extract features and then the best features were selected using a wrapper method. Eight different regression ML models were trained and optimized after the feature selection using Optuna. The results show that, with the current instrumentation of the BRA1 IRV, obtaining lateral track irregularities is unlikely due to low correlation, however, vertical irregularities can be obtained with a root mean squared error (RMSE) of 0.556 mm. With postprocessing, the RMSE was further reduced to 0.410 mm.

Real-Time Measurement of Track Irregularities Using an Instrumented Axle and Kalman Filtering Techniques

Abstract A model-based methodology for the estimation of both lateral and vertical track irregularities is presented. This methodology, based on Kalman filter techniques, was developed for an independent and compact measuring system comprising an instrumented axle equipped with a limited set of low-cost sensors: a 3D gyroscope, a linear variable differential transformer (LVDT) distance sensor, and an encoder. The instrumented axle can be used on any railway vehicle traveling at moderate forward speed to provide measurements in real-time. The proposed methodology, combined with the instrumented axle, enables precise and prompt measurement of track irregularities. An experimental campaign carried out on a 1:10 scale track facility at the University of Seville validated both the system and the methodology. In the testing, 80 m of scaled track was measured at an operational speed of V = 0.65 m/s in just 2 min. Simulation estimates for track irregularities compared against the measured data from the testing showed a good performance of the proposed methodology, with maximum errors of 0.45 mm in the short wavelength range D1, the range most influential to vehicle dynamic behavior.

Identification of track irregularities with the multi-sensor acceleration measurements of vehicle dynamic responses

Track irregularities induce potential risks to the safety and stability of railway track systems. This paper proposes a novel methodology to identify vertical and lateral track irregularities. The method involves measuring system-based attitude calculation and a model-based unknown input observer estimator, based on the dynamic responses of distributed multi-sensors on the vehicle and bogie. First, a mechanical model of wheel-rail contacts is built with dynamic methods. The model considers the different directions of motion for a railway vehicle and consists of two bogies and four wheelsets. Based on the multi-sensor acceleration measurement, the vertical and lateral acceleration signals of the vehicle and bogies are integrated into the displacement signal. Then a state-space description of the vehicle suspension model is established for inverse dynamical analysis to extract the input signals. A suitable unknown input observer is constructed to estimate the track irregularities by transforming the state space equations of the vehicle into an augmented system that can monitor the track irregularities in-service. This method provides an opportunity to reduce the costs of the monitoring infrastructure and provide quicker and more reliable information about the status of a track.

Inversion and identification of vertical track irregularities considering the differential subgrade settlement based on fully convolutional encoder-decoder network

Differential subgrade settlement plays a key role in the formation of track geometry and significantly affects the running performance of a moving vehicle. This work therefore contributes to the on-line inversion of the track irregularities and the differential subgrade settlement hidden in the track irregularities is further excavated. To achieve the above goal, a vertically vehicle-track-subgrade coupled dynamics model with high accuracy and efficiency is first established by introducing the Green’s function method. The track irregularities are then generated by a probabilistic model and the rail deflections caused by the settlement are also accounted for. The vertical accelerations of the vehicle excited by track irregularities and various vehicle speeds are subsequently derived. On this basis, a 1-D fully convolutional encoder-decoder network is constructed to predict the track irregularities by treating the acceleration data as the network inputs. A total of seven scenarios involving different input variables are investigated and the results show that when the wheelset, bogie and car body accelerations are simultaneously considered in network training, the prediction performance achieves the optimum. Meanwhile, the network robustness with respect to various vehicle speeds and degradation levels of track irregularities is also demonstrated. Finally, a time–frequency unification method is employed to identify the settlement locations and wavelengths from the predicted track irregularities. Two cases are conducted to further illustrate the effectiveness of the presented settlement identification method.

Influence mechanism of vertical dynamic track irregularity on train operation stability of long-span suspension bridge

The track needs to maintain sufficient foundation stiffness to ensure its smoothness and meet the operation stability requirements of high-speed trains. However, the train-induced deformation of flexible suspension railway bridge will inevitably induce the obvious vertical dynamic track irregularity and threaten train operation stability. Combined with a long-span suspension bridge with a main span of 1092 m, this paper provides a new analysis framework for evaluating the track smoothness on the long-span bridge from the perspective of train operation stability. The comprehensive train-track-bridge coupling vibration analysis is conducted to highlight the impact factors on train operation stability and identify the dynamic track irregularity. The simplified evaluation framework of dynamic track irregularity are then proposed to evaluate the track smoothness. The results show that the vertical dynamic track irregularity of long-span bridges is obviously affected by action of train, random track irregularity and overall temperature load. It is quite different from the static track irregularity in terms of alignment and spatial frequency. By separating the dynamic track irregularity according to the wavelength limit of 200 m, two alignment evaluation methods are proposed, namely the mid-chord measurement within 200 m wavelength and curvature method above 200 m wavelength, to reveal the different contributions of dynamic track irregularity component to the vertical car-body acceleration. The influence mechanism of dynamic track irregularity caused by different factors on the stability of train operation is finally identified from the perspectives of vibration acceleration and centrifugal acceleration.

Analysis of the Fluid–Structure Coupling Characteristics of a High-Speed Train Passing through a Tunnel

After increasing the train speed, the wheel-rail coupling effect is intensified, as is the coupling effect between the train and the surrounding air, which causes the severe vibration of the train. Considering this problem and taking the high-speed train as the object of this study, a method for the coupling of aerodynamics and vehicle dynamics is proposed. Its validity is then demonstrated by the results of field tests and moving model experiments. On this basis, the fluid–structure coupling characteristics of a high-speed train passing through a tunnel are studied, as well as the effects of different coupling methods and track irregularities. The obtained results demonstrate that the interaction between the tail car and the surrounding air is significant. In the tunnel and at its exit, the lift and the car body acceleration significantly change, especially when the coupling of aerodynamics and vehicle dynamics, as well as the vertical and lateral track irregularities, are simultaneously imposed. When the head car travels out of the tunnel, the lift of the middle and tail cars both dramatically will change. It is deduced that the fluid–structure interaction has a significant effect on the swing phenomenon of the tail car. This phenomenon is the result of the combined effects of aerodynamics and track irregularities. The different frequencies of the lateral displacement for each car body, except the frequencies of the car bodies themselves, are mainly determined by vertical track irregularities.

Dynamic modeling of a metro vehicle considering the motor–gearbox transmission system under traction conditions

Abstract. As a vital means of transportation to alleviate urban traffic congestion, the metro vehicle has been developing rapidly in China during recent years. For the violent vibration and shock under the frequent switches between traction and braking conditions, higher requirements are put forward in the drive system. The dynamic performance of the traction motor and gearbox, which are the key elements in the drive system of the metro vehicle, is worthy of attention. Based on the classical vehicle–track coupled dynamics and the gear dynamics theory, a vertical–longitudinal dynamics model for a metro vehicle with frame-hung motors and gearboxes is developed in this paper. This model enables the consideration of some complicated excitations, such as external excitations (the track vertical irregularity) and internal excitations (the mesh stiffness and the dynamic transmission error). The established dynamics model is then validated by comparing the simulated results with the field test results in both time domain and time–frequency domain under traction conditions. Consequently, the established dynamics model is demonstrated to be capable of revealing the dynamic performance of the metro vehicle effectively, especially for the traction and transmission system in the entire vehicle vibration environment of a metro. In turn, the results indicate that the gear transmission has a great and lasting effect on the force state of the traction motors and gearboxes compared to its effect on the axle load transfer.

An Efficient Numerical Model to Predict the Mechanical Response of a Railway Track in the Low-Frequency Range

With railway interoperability, new trains are allowed to move on the French railway network. These trains may present different designs from standard trains. This work aims to complete the current approach for vehicle admission on the railway network, which is defined in technical baselines. Historically, computation rules for traffic conditions are based on simplified analytical works, which are considerably qualitative. They have evolved through feedback and experimental campaigns to comply with the track structure evolution. An efficient methodology based on numerical simulation is needed to evaluate railway vehicle admission to answer this issue. A perspective to update these computation rules is to evaluate the structural fatigue in the rail. That is to say, fatigue is caused by bending and shear stresses. The complexity of the railway system has led to an investigation at first of the vertical response of the railway track and quantifying its contribution to the rail’s stress response. In that sense, this paper investigates the vertical track response to a moving railway vehicle at low frequencies. For this purpose, a lightweight numerical model for the track, a multi-body model for the vehicle, and a random vertical track irregularity are proposed. More explicitly, the track model consists of a two-layer discrete support model in which the rail is considered as a beam and sleepers are point masses. The rail pads and ballast layer are modelled as spring/damper couples. Numerical results show a negligible effect of track inertia forces due to high track stiffness and damping. Nevertheless, this assumption is valid for normal rail stresses but not for ballast loading, especially in the case of sleeper voids or unsupported sleepers. Hence, the prediction of the mechanical stress state in the rail for fatigue issues is achieved through a static track model where the equivalent loading is obtained from a dynamic study of a simplified vehicle model. A statistical analysis shows that the variability of the vertical track irregularity does not influence the output variabilities like the maximum in time and space of the normal and shear stress.

Intelligent identification for vertical track irregularity based on multi-level evidential reasoning rule model

Intelligent identification for vertical track irregularity based on multi-level evidential reasoning rule model

Track geometry estimation from vehicle–body acceleration for high-speed railway using deep learning technique

Track geometry monitoring is essential for track maintenance. Dedicated track inspection vehicles are scheduled to measure track geometry irregularities throughout the railway network, so cannot inspect each line frequently. It is desirable to inspect geometry much higher frequently using in-service trains. One possible way is estimating track geometry from vehicle–body accelerations because the accelerators can be easily installed in vehicle–body. However, inverting track geometry from vehicle–body acceleration is a pending issue. Up to now, most research has focused on vehicle dynamics modelling and simulation. In this paper, we solve the problem using deep learning method and realistic measurement data. The training and test data are the inspection data acquired by comprehensive inspection trains from three main high-speed railways in China. The proposed AM–CNN–GRU model combines an Attention Mechanism (AM), a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU). The model’s inputs are vertical and lateral accelerations, and vehicle speed. The outputs are two vertical track irregularities, with wavelengths of 3–42m and 3–120 m, respectively. We evaluated the model by comparing the estimated irregularities with the actual measurements. We discussed different models, high-speed lines, sub-rail infrastructures and speed to validate the model effectiveness.

Measuring Vertical Track Irregularities from Instrumented Heavy Haul Railway Vehicle Data Using Machine Learning

Measuring Vertical Track Irregularities from Instrumented Heavy Haul Railway Vehicle Data Using Machine Learning

Experimental measurement of track irregularities using a scaled track recording vehicle and Kalman filtering techniques

The actual trend of railway industry on track surveying is heading up the development of fast automated methods for continuous monitoring of track quality. This paper presents a model-based methodology for the estimation of lateral and vertical track irregularities from different sensors mounted on a Track Recording Vehicle (TRV): an Inertial Measurement Unit (IMU), a gauge sensor and a position encoder. The proposed methodology, based on the Kalman filtering technique, allows a fast and accurate measurement of track irregularities, without the use of a total station (which usually makes the measurement process very slow). The proposed method has been validated through an experimental campaign carried out on a 90 m long 1:10, scaled track facility and a scaled TRV at the University of Seville. The use of the scaled TRV allows the measurement of the 90 metres long scaled track at an operation velocity of V = 0.7 m/s in only two minutes. The results of the estimation of track irregularities have been compared with a previous measurement of the mentioned scaled track using manual means, showing a good agreement: with errors lower than 0.7 mm in the short wavelength range D1, which is the most influential in the dynamic behaviour of the vehicle. Additionally, the obtained results have been analysed and compared in the different wavelength ranges, according to standards.

Probability analysis of train-bridge coupled system considering track irregularities and parameter uncertainty

In the dynamic analysis of railway lines, both lateral and vertical track irregularities should be considered. In addition, uncertainties in the bridge structure and train load will have different effects on the train-bridge coupled system (TBCS). This paper presents a three-dimensional model of the TBCS to study the influence of various sources of randomness on the response of the TBCS. The Karhunen–Loéve expansion is combined with the point estimate method (KLE-PEM) to calculate the statistical moment of the system response with high accuracy and efficiency. Furthermore, applicability of KLE-PEM method is discussed and the influence of different combinations of sources of randomness on the train and bridge responses under different speeds is analyzed according to the maximum range of probability values. Random track irregularities are found to have a much greater influence on the train response than uncertain parameters, whereas uncertain parameters have the greatest influence on the displacement of the bridge.

Vibration prediction based on the coupling method of half-train model and 3D refined finite element ground model

In this study, a train model and a refined three-dimensional(3D) finite element (FE) model were combined to predict the environmental vibration induced by running trains in the surroundings. A half-train model and a 3D rail-track-soil FE model are established, in which the connection mode of rail and fastener has also been studied. The vibration of the train and refined 3D FE ground model are predicted simultaneously, and the solution process is realised by an interactive and iterative calculation method, considering also the vertical track irregularity. The computational time is basically the same as the method of simulating train loads with a set of moving concentrated forces. The results of the comparative studies carried out show that the predicted vibrations are in good agreement with the measured values, verifying the feasibility and correctness of the proposed method. Finally, the verification of the proposed method is carried out against experiment measurement.

Effects analysis of vertical track irregularities on bogie vibration - method based on bogie modelling and wheelsets accelerations measurement

The paper analyzes the effect of the vertical track irregularities upon the vibrations in a two-axle bogie. The method in use implies the bogie modelling and the measurement of the vibrations in wheelsets generated by the track vertical irregularities. The behaviour of vibrations in the bogie is evaluated via the results derived from applications of numerical simulation developed on the basis of the bogie model, where the inputs are the accelerations measured in the two wheelsets. The vibration features in the bogie are pointed out at according to the spectra of accelerations in the bogie frame, to the standard deviation values of accelerations and to the maximum values of the accelerations calculated against the two wheelsets.