GPR method for continuous monitoring of compaction during the construction of railways subgrade

Shapovalov, Vladimir; Vasilchenko, A.A.; Yavna, V. A.; Kochur, Andrei

doi:10.1016/j.jappgeo.2022.104608

Cited by 6 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The A-Scans from each measurement point are gathered together based on the acquisition interval, resulting in a GPR image of the railway substructure, especially the subgrade. This image visually represents changes in the physical properties of the railway structural layer interface and the subsurface medium, which can be used to identify and extract information necessary to understand the possible defects in the railway substructure [ 30 ].…”

Section: Methodsmentioning

confidence: 99%

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

Liu

Wang

Jing

et al. 2023

Sensors

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

Section: Methodsmentioning

confidence: 99%

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

Liu

Wang

Jing

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, geophysical methods have become popular as they provide a non-destructive approach to profile the subsurface without conducting additional soil tests. Geophysical methods such as electrical resistivity, seismic and GPR have been proven to be able to identify the changes in soil properties such as undrained shear strength, density, moisture content and void ratio [2,3,4]. These methods are able to be utilize in the process of soil quality control as a means of covering more spaces and saving time.…”

Section: Introductionmentioning

confidence: 99%

The effect of different degree of compaction towards electrical resistivity value for cohesive soil

Abd Malik,

Madun,

Abu Talib

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Electrical resistivity is a non-destructive method used to measure the resistivity of ground properties, which is related to soil properties such as porosity and degree of saturation, as described in Archie’s law. In road construction, soil compaction is a crucial process that requires quick quality assessment. Traditional methods, such as sand replacement tests, are time-consuming, limited in coverage, and labour-intensive. Therefore, incorporating electrical resistivity techniques on the current quality control practices may significantly improve efficiency. To achieve this, it is essential to establish the relationship between soil density, moisture content, and electrical resistivity. This study focuses on industrial and natural soil samples compacted using standard proctor moulds using 2.5 kg and 4.5 kg hammers. Resistivity measurements were conducted using the Miller 400A device using Wenner array and 1 cm electrode spacing. The impact of different compaction degrees on electrical resistivity values were compared for the two soil samples. The findings showed that soil dry density increased with the increment of water content until it reached maximum dry density. However, as water content continued to increase, the dry density decreased. Based on the results, electrical resistivity was higher at low water content but reduced with the increments of water contents. The resistivity value for industrial soil decreased from 164 to 12 Ohm.m and 200 to 13 Ohm.m. For natural soil the resistivity value decreased from 45 to 9 Ohm.m and 126 to 11 Ohm.m. The comparison of electrical resistivity values between the two different compaction methods indicated the moisture content limited the capability of the electrical resistivity method to identify the compaction effect in the proctor soil testing. This study demonstrates the potential applicability of electrical resistivity techniques in assessing soil compaction.

show abstract

Railway ballast material selection and evaluation: A review

Guo

Xie²,

Fan³

et al. 2022

Construction and Building Materials

View full text Add to dashboard Cite

GPR method for continuous monitoring of compaction during the construction of railways subgrade

Cited by 6 publications

References 12 publications

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

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

The effect of different degree of compaction towards electrical resistivity value for cohesive soil

Railway ballast material selection and evaluation: A review

Contact Info

Product

Resources

About