A Novel Prediction Model for Car Body Vibration Acceleration Based on Correlation Analysis and Neural Networks

Zheng, Shibao; Zhong, Qianwen; Chai, Xiaodong; Chen, Xingjie; Peng, Lele

doi:10.1155/2018/1752070

Cited by 10 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e sample is a twolayer concrete bonding structure. e size of the first layer is 1000 × 1000 × 50 mm 3 , and the physical parameters are as is disposed between the first layer and the second layer of the sample to be inspected. Exciting and receiving sensors are disposed on both sides of the cavity defect.…”

Section: Finite Element Simulationmentioning

confidence: 99%

“…However, its internal damage is substantially increased because of the influence of dynamic load, environmental temperature, and other factors. e internal damages of concrete, such as cavity defect, seriously affect vehicle speed and safety [1][2][3]. erefore, the effective characterization of the degree and scope of concrete cavity is an urgent problem for researchers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time‐Domain Topological Energy Imaging Method of Concrete Cavity Defect by Lamb Wave

Zhu

Shao

Peng

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

This paper presents an ultrasonic Lamb wave imaging method based on time-domain topological energy to address artifacts in the results of traditional ultrasound imaging methods. This method is based on topological theory and the calculation of the direct and adjoint sound fields in a defect-free reference medium. It focuses the direct and adjoint sound fields at the cavity defect using time reversal and their time-domain topological energy as the pixel values of the image to reduce the artifacts. The physical mechanism of time-domain topological energy (TDTE) imaging is revealed by finite element simulation and experiment. The feasibility of this method for multilayer concrete cavity defect imaging is verified. Compared with the traditional synthetic aperture focusing technique (SAFT) imaging method, the numerical simulation and experimental results show that the method can overcome the influence of ultrasonic Lamb wave dispersion and locate cavity defects with high accuracy and few artifacts. These features indicate the potential of the method in imaging damage concrete structures.

show abstract

Section: Finite Element Simulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Time‐Domain Topological Energy Imaging Method of Concrete Cavity Defect by Lamb Wave

Zhu

Shao

Peng

et al. 2019

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Machine learning methods can be further categorized into traditional methods and deep learning methods. Traditional machine learning approaches predict vehicle responses including multilayer perception (MLP [10]), a set of backpropagation (BP [11]), decision tree, support vector machines, and other regression algorithms and their comparisons in [12], and NARX neural networks [13].…”

Section: Introductionmentioning

confidence: 99%

Estimation of Vehicle Dynamic Response from Track Irregularity Using Deep Learning Techniques

Yang

Hao

Zhang

et al. 2022

Shock and Vibration

View full text Add to dashboard Cite

To improve the quality of track maintenance work, it is a desire to estimate vehicle dynamic behavior from track geometry irregularities. This paper proposes a deep learning model to predict vehicle responses (e.g., vertical wheel-rail forces, wheel unloading rate, and car body vertical acceleration) using deep learning techniques. In the proposed CA-CNN-MUSE model, convolutional neural networks (CNNs) are used to learn features of track irregularities, and multiscale self-attention mechanisms (MUSE) are employed to capture the long-term and short-term trends of sequences. Coordinate attention (CA) is introduced into CNN to focus on important interchannel relationships and important spatial mileage points. The experiments were performed on a multibody simulation model of the vehicle system and the measured data of the actual high-speed line. The results show that the CA-CNN-MUSE has high prediction accuracy for vertical vehicle responses and fast computation speed. The predicted time-domain waveforms and power spectral densities (PSDs) agree well with the actual vehicle responses. The main features of the lateral vehicle responses can also be captured by the proposed method, yet the results are not as good as the vertical ones.

show abstract

“…In the state-of-the-art, there are many studies that achieve excellent results in predicting the accelerations of the train's coaches. In fact, some of them use advanced predictive algorithms such as neural networks and statistical correlations to predict this variable [7,8]. In addition, other studies address the prediction of comfort values in high-speed trains using multibody dynamic models, including information about the track geometry and a simplified model of the rolling stock [9,10].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

A Novel Prediction Model for Car Body Vibration Acceleration Based on Correlation Analysis and Neural Networks

Cited by 10 publications

References 26 publications

Time‐Domain Topological Energy Imaging Method of Concrete Cavity Defect by Lamb Wave

Time‐Domain Topological Energy Imaging Method of Concrete Cavity Defect by Lamb Wave

Estimation of Vehicle Dynamic Response from Track Irregularity Using Deep Learning Techniques

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

Contact Info

Product

Resources

About