State-of-the-Art Review of Ground Penetrating Radar (GPR) Applications for Railway Ballast Inspection

Wang, Shilei; Liu, Guixian; Jing, Guoqing; Feng, Qiankuan; Liu, Hengbai; Guo, Yunlong

doi:10.3390/s22072450

Cited by 24 publications

(10 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the sleeper support conditions can be assessed and predicted using machine learning technologies based on the acceleration data of track components [ 57 ] and the rail displacement from digital video records [ 36 ]. Ground penetrating radar (GPR) can also reflect the ballast layer condition and the void zone [ 58 ], as well as on the bridge ends for digital twin based monitoring [ 59 , 60 ]. However, monitoring the sleeper support conditions on the ballasted railway line is challenging.…”

Section: Resultsmentioning

confidence: 99%

Multi-Hazard Effects of Crosswinds on Cascading Failures of Conventional and Interspersed Railway Tracks Exposed to Ballast Washaway and Moving Train Loads

Yang

Kaewunruen

2023

Sensors

View full text Add to dashboard Cite

The interspersed railway track is an enhanced timber railway track, spot-replacing damaged wooden sleepers with new concrete sleepers to improve the bearing capacity of existing railway lines. Although this interspersed solution is characterised by low cost and short maintenance time, the interspersed tracks have worse stability than concrete tracks and can deteriorate quickly when exposed to extreme weather conditions such as heavy rains and floods. In many cases, heavy rains and floods are accompanied by strong winds. Ballast washaway can often be observed under flood conditions while the mass of trains is unevenly distributed on two rails due to the effect of lateral wind load and rail irregularities. The current work is the first in the world to investigate the collective multi-hazard effects of ballast washway and uneven axle loads on the vulnerability of conventional and interspersed railway tracks using nonlinear FEM software, STRAND 7. The train bogie is modelled by two sets of point loads. The maximum displacement, bending moment and twists have been studied to evaluate the worst condition. The novel insights will help the railway industry develop proper operations of interspersed railway tracks against naturally hazardous conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-Hazard Effects of Crosswinds on Cascading Failures of Conventional and Interspersed Railway Tracks Exposed to Ballast Washaway and Moving Train Loads

Yang

Kaewunruen

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Railway subgrade is a critical component of the railway system, essentially providing stable support for tracking (ballasted track, slab track), thus ensuring safe train operation [ 1 ]. However, with increased intensive high speed train loading, axle load, and traffic volume, the subgrade has undergone unacceptable rapid degradation, leading to frequent maintenance activities [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Combined CNN and RNN Neural Networks for GPR Detection of Railway Subgrade Diseases

Liu

Wang

Jing

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Vehicle-mounted ground-penetrating radar (GPR) has been used to non-destructively inspect and evaluate railway subgrade conditions. However, existing GPR data processing and interpretation methods mostly rely on time-consuming manual interpretation, and limited studies have applied machine learning methods. GPR data are complex, high-dimensional, and redundant, in particular with non-negligible noises, for which traditional machine learning methods are not effective when applied to GPR data processing and interpretation. To solve this problem, deep learning is more suitable to process large amounts of training data, as well as to perform better data interpretation. In this study, we proposed a novel deep learning method to process GPR data, the CRNN network, which combines convolutional neural networks (CNN) and recurrent neural networks (RNN). The CNN processes raw GPR waveform data from signal channels, and the RNN processes features from multiple channels. The results show that the CRNN network achieves a higher precision at 83.4%, with a recall of 77.3%. Compared to the traditional machine learning method, the CRNN is 5.2 times faster and has a smaller size of 2.6 MB (traditional machine learning method: 104.0 MB). Our research output has demonstrated that the developed deep learning method improves the efficiency and accuracy of railway subgrade condition evaluation.

show abstract

“…Ground penetrating radar (GPR) is a geophysical exploration method that uses high frequency (1 MHz-10 GHz) electromagnetic waves to non-destructively detect invisible targets in the ground. With the advantages of simple operation, high resolution, and strong anti-interference capability, the GPR technology has been widely used in tunnel lining detection [1], [2], geological surveys [3], pipeline detection [4], [5], and many other fields. In the process of exploration, in order to maintain more reflected wave characteristics of targets, the GPR generally uses broadband to record.…”

Section: Introductionmentioning

confidence: 99%

Direct Coupled Wave Removal for GPR Data Based on SVD in the Wavelet Domain

Chen¹,

Xiang²,

Xiong³

et al. 2022

RADIOENGINEERING

View full text Add to dashboard Cite

This paper presents a new algorithm of the singular value decomposition (SVD) in the wavelet domain for ground penetrating radar (GPR) to remove direct coupled waves. In fact, direct coupled waves commonly disturb the reflecting waves from underground targets. Besides, the amplitude and energy of direct coupled waves are large, which reduces the resolution of the images to the targets and adversely affects the subsequent image interpretation work. The GPR signal is decomposed into several levels by Wavelet to obtain approximation components and detailed components of each level. The information of targets is contained in big eigenvalues of detail components, while the direct coupled waves are contained in small ones. Therefore, the SVD in the wavelet domain can reduce the misjudgment of effective signals and improve the signal to noise ratio (SNR) of GPR signals. The simulated and field GPR data show that the SVD in the wavelet domain denoising method has better results for direct coupled wave removal than the traditional methods, which validates the effectiveness of the proposed denoising method.

show abstract

State-of-the-Art Review of Ground Penetrating Radar (GPR) Applications for Railway Ballast Inspection

Cited by 24 publications

References 100 publications

Multi-Hazard Effects of Crosswinds on Cascading Failures of Conventional and Interspersed Railway Tracks Exposed to Ballast Washaway and Moving Train Loads

Multi-Hazard Effects of Crosswinds on Cascading Failures of Conventional and Interspersed Railway Tracks Exposed to Ballast Washaway and Moving Train Loads

Combined CNN and RNN Neural Networks for GPR Detection of Railway Subgrade Diseases

Direct Coupled Wave Removal for GPR Data Based on SVD in the Wavelet Domain

Contact Info

Product

Resources

About