Lateral Acceleration Of Car Body Research Articles

Time consideration in machine learning models for train comfort prediction using LSTM networks

Safety and passengers’ comfort affect directly the reliability and availability of trains. Therefore, appropriate monitoring of the variables influencing those two concepts is mandatory for good operation and maintenance costs reduction. Moreover, operators and rail manufacturers are evolving to a condition-based maintenance strategy (CBM). For this purpose, machine learning is being used to predict early main component’s failures, avoiding a loss of reliability or availability during commercial operation. From the passengers’ point of view, punctuality and comfortability are two of the most relevant factors when evaluating a railway transport service. Comfort is mainly based on the availability of all services in the train, but it is also related to the accelerations received through the car body to the passengers. More precisely, the lateral car body acceleration (Ayc variable in this paper) is a key variable related to comfort perception and it is therefore important to be monitored and controlled. Rolling, suspension, and damping elements must be kept in perfect conditions during operation to achieve a smooth train movement. In this paper, an optimized model based on Long Short Term Memory networks (LSTM) is designed and trained to predict lateral car body accelerations using only the train accelerometers and with no additional sensoring for this specific experiment. This model will be compared with artificial neural networks (ANN) models to evaluate the relevance of time dependency for this purpose. The optimal time frame to group data is a key characteristic of the neural network training process and is also determined in this paper. The model is trained with data corresponding to the correct dynamic behavior of the train. To test the reliability of this method, a real case of excessive train movement is tested. In these situations, an alert could be sent to the operator or the maintainer for a not-programmed maintenance inspection at the depot (predictive maintenance), avoiding future passenger complaints for the loss of comfort or, in extreme cases, speed limitations due to safety reasons for excessive accelerations. The main contributions of this work are the following:- A LSTM-based neural network, predicting lateral car body accelerations achieving better results than a plain ANN for this dataset: 0.0335 m/s2 MAE and a 12% gain on extreme axles.- An optimization of the time frame to group the measurements in this algorithm that is considering as an input the time variable: 5 s.- A real use case of the model in which monitoring the deviation would have helped to take an early maintenance adjustment on the suspension or damping elements to prevent the loss of comfort.- The p-value used to reduce the uncertainty of the results obtained in the real use case is reaching over 0.95 in the coaches with good dynamic behavior and less than 0.15 in the coaches where a dynamic problem related to comfort loss is detected.

Condition-Based Maintenance for Normal Behaviour Characterisation of Railway Car-Body Acceleration Applying Neural Networks

Recently, passenger comfort and user experience are becoming increasingly relevant for the railway operators and, therefore, for railway manufacturers as well. The main reason for this to happen is that comfort is a clear differential value considered by passengers as final customers. Passengers’ comfort is directly related to the accelerations received through the car-body of the train. For this reason, suspension and damping components must be maintained in perfect condition, assuring high levels of comfort quality. An early detection of any potential failure in these systems derives in a better maintenance inspections’ planification and in a more sustainable approach to the whole train maintenance strategy. In this paper, an optimized model based on neural networks is trained in order to predict lateral car-body accelerations. Comparing these predictions to the values measured on the train, a normal characterisation of the lateral dynamic behaviour can be determined. Any deviation from this normal characterisation will imply a comfort loss or a potential degradation of the suspension and damping components. This model has been trained with a dataset from a specific train unit, containing variables recorded every second during the year 2017, including lateral and vertical car-body accelerations, among others. A minimum average error of 0.034 m/s2 is obtained in the prediction of lateral car-body accelerations. This means that the average error is approximately 2.27% of the typical maximum estimated values for accelerations in vehicle body reflected in the EN14363 for the passenger coaches (1.5 m/s2). Thus, a successful model is achieved. In addition, the model is evaluated based on a real situation in which a passenger noticed a lack of comfort, achieving excellent results in the detection of atypical accelerations. Therefore, as it is possible to measure acceleration deviations from the standard behaviour causing lack of comfort in passengers, an alert can be sent to the operator or the maintainer for a non-programmed intervention at depot (predictive maintenance) or on board (prescriptive maintenance). As a result, a condition-based maintenance (CBM) methodology is proposed to avoid comfort degradation that could end in passenger complaints or speed limitation due to safety reasons for excessive acceleration. This methodology highlights a sustainable maintenance concept and an energy efficiency strategy.

Shaking analysis of high-speed train’s carbody when cross lines

The high-speed train will exhibit different vibration characteristics when running on different lines. When the equivalent conicity of the wheel rail profile is larger, the critical speed of the vehicle will decrease, which will lead to the lateral instability of bogie and cause the abnormal vibration problem of carbody. This paper firstly analyzes the causes of high-speed train’s body shaking when cross lines, through the test acceleration analysis and equivalent conicity analysis of measured wheel profile and rail profile, found that the main reason is equivalent conicity increases when the vehicle cross to another line and change of the wheel rail contact relationship. And establish the train model with the Simpack software, and the phenomenon of body shaking is reappeared by using the measured tread and rail profile, and the vibration of the carbody after crossing the line is obvious under the dominant frequency of 7.1 Hz. And proposes two optimization schemes: decreases the distance between backs of the wheel flanges and the optimization of suspension parameters. The simulation results show that the distance between backs of the wheel flanges decrease can effectively reducing the equivalent conicity, the equivalent conicity of 1353 mm, 1352 mm and 1351 mm were calculated respectively, and when the distance between backs of the wheel flanges was reduced by 1 mm and 2 mm, there was a significant decrease of equivalent conicity. The distance between backs of the wheel flanges decrease of 1 mm and 2 mm effectively reducing the equivalent taper, then the bogie lateral acceleration was reduced by 22.4 % and 30.7 %, the lateral acceleration of carbody is decreased by 8.87 % and 24.6 %. At the same time, optimize the anti-yaw vibration absorber stiffness and node positioning stiffness, increasing the longitudinal positioning stiffness and anti-yaw vibration absorber stiffness can effectively reduce the lateral acceleration of the bogie and carbody. However, the selection of this parameter should be combined with other dynamic indexes and wheel wear.

Optimization of Rail Profiles to Improve Vehicle Running Stability in Switch Panel of High-Speed Railway Turnouts

A method for optimizing rail profiles to improve vehicle running stability in switch panel of high-speed railway turnouts is proposed in this paper. The stock rail profiles are optimized to decrease the rolling radii difference (RRD). Such characteristics are defined through given rail profiles, and the target rolling radii difference is defined as a function of lateral displacements of wheel set. The improved sequential quadratic programming (SQP) method is used to generate a sequence of improving profiles leading to the optimum one. The wheel-rail contact geometry and train-turnout dynamic interaction of the optimized profiles and those of nominal profiles are calculated for comparison. Without lateral displacement of wheel set, the maximum RRD in relation to a nominal profile will be kept within 0.5 mm–1 mm, while that in relation to an optimized profile will be kept within 0.3 mm–0.5 mm. For the facing and trailing move of vehicle passing the switch panel in the through route, the lateral wheel-rail contact force is decreased by 34.0% and 29.9%, respectively, the lateral acceleration of car body is decreased by 41.9% and 40.7%, respectively, and the optimized profile will not greatly influence the vertical wheel-rail contact force. The proposed method works efficiently and the results prove to be quite reasonable.

Analysis of creep force and its sensitivity on stability and vertical-lateral ride for railway vehicle

This paper presents a detailed creep force analysis at wheel-rail interaction using linear creepage-creep force relationship for a 37 DOF model of an ICF coach formulated using Lagrangian dynamics. The mathematical model is validated by simulating PSD vertical and lateral acceleration of carbody and comparing the same obtained from actual testing results. The sensitivity of longitudinal, lateral creep force and lateral/spin creep moment on stability and vertical-lateral ride is analysed. It is found from the present analysis that creep forces are helpful in improving lateral ride and lateral stability for railway vehicles.

Rail vehicle response to lateral carbody excitations imitating crosswind

Repeatable field tests to measure the vehicle response to unsteady crosswinds are not practical due to safety and economic reasons. Simulations are therefore necessary to gather information on the vehicle response to crosswind. However, in turn, these simulations need to be validated. This study presents results of measured quasi-static and dynamic responses of a stationary rail vehicle due to defined lateral carbody excitations imitating unsteady crosswind, which are reflected by multibody simulations. The vehicle responses are measured in terms of suspension deflections, lateral carbody accelerations and vertical wheel/rail forces. The vehicle dynamic response to a gust-like event results in an overshoot of wheel unloading. In general the measurements and simulations show good agreement. However, the simulations partly overestimate the responses slightly and an influence due to airspring levelling can be observed in the measured values of quasi-static load cases.

Parameters Analysis of Train Running Performance on High-Speed Bridge during Earthquake

A model of coupled vehicle-bridge system excited by earthquake and irregular track is established for studying train running performance on high-speed bridge during earthquake, by the methods of bridge structure dynamics and vehicle dynamics. The results indicate that under Qian’an earthquake waves vehicle dynamical responses hardly vary with the increasing-height pier, but vehicle dynamical responses increase evidently while the height of pier is 18m, which the natural vibration frequency is approaching to dominant frequency of earthquake waves. Dynamic responses are linearly increasing with earthquake wave strength. Dynamic response of vehicles including lateral car body accelerations and every safety evaluation index all increase with train speed, so the influences of train speed must be taken into account in evaluating running safety of vehicles on bridge during earthquakes, but lateral displacement of bridge is varying irregularly. Dynamic responses and lateral displacement of bridge reduce under the higher dominant frequency of earthquake wave. Derailment coefficient, later wheel-rail force and lateral vehicle acceleration become small with increasing damping ratio. Vertical vehicle acceleration and reduction rate of wheel load are hardly varying with damping ratio.

A201 Tilt Control System for Railway Vehicles Using Air Springs

In recent years, there has been growing needs to improve maximum speed on curved tracks. For this purpose, there are many tilting systems. However, vehicles that have special tilting mechanism, are much different from the ordinary ones and expensive. Thus we have developed a tilt control system that is constituted from the ordinary car body and bogie truck with less remodeling. Therefore the maximum tilting angle of this system is restricted to 2 degrees. This system mainly consists of a Controller, Air supply valves, Exhaust valves and Height sensors. The control method is programmed. The tilting operation is performed by the controller, which all data of the curved tracks have been memorized. The location of the vehicle is measured by the tachometer generator and the devices (ground coil) that are attached on the sleeper in order to correct running position. From several running test results, we confirmed that stationary lateral acceleration of car body was reduced by tilt control. The running stability and riding comfort was also adequate so the vehicle equipped with this system could run rapidly than the vehicle with the former restricted speed limit on curved track.

Rail Vehicle Active Suspensions for Lateral Ride and Stability Improvement

The potential performance benefits of simple, low power active elements in the lateral secondary, between the truck and carbody is investigated analytically by parametric studies utilizing a fifteen degree of freedom lateral dynamic model subject to alignment and cross-level inputs. It is shown that significant improvements in ride quality can be obtained at current operating speeds by using less than 3 kw per truck by sensing lateral carbody accelerations and utilizing lateral force actuators between the truck and carbody. It is also shown that in order to improve the truck critical speed and/or to improve the ride quality at very high speeds requires control of the truck kinematic mode. This can be achieved, at the expense of increased power requirements, by sensing absolute truck lateral and yaw velocities and utilizing combined lateral force actuators to exert a yaw moment on the truck. It is concluded that significant ride quality improvements can be achieved by low power, small bandwidth actuators while stabilty improvements requires increased power and larger bandwidth systems.