The method of detecting ballast bed defects using ground penetrating radar (GPR) is an important method for guiding the maintenance of railway infrastructure. Currently, this technology primarily relies on time–frequency analysis to assess the condition of the ballast bed and manual interpretation of GPR images to identify defect areas and types, resulting in low automation levels. This paper proposes a bimodal deep learning classification model that enables intelligent classification of moisture and mud pumping defects in ballast beds. This model includes two channels, each processing a different data modality. One channel uses a Multilayer Perceptron (MLP) to extract features of A-scan data in the time domain. The other channel utilizes Short-Time Fourier Transform (STFT) to convert time domain signals into frequency domain signals, which are then processed by a ResNet18 to extract frequency domain features. By fusing the time and frequency features, the proposed Time-Frequency-Fusion ResNet model (TFF-ResNet) demonstrates superior performance. Experimental results show that TFF-ResNet outperforms the standalone MLP and ResNet18 models, with performance improvements of approximately 24% and 14% on the validation dataset, and 21% and 34% on the testing dataset, respectively.

This study explores the use of infrared thermography (IRT) technology for the non-destructive evaluation of ballast fouling in railway tracks, focusing on the influence of parent rock types and fouling materials. Utilizing thermal imaging, the research investigates how variations in ballast conditions affect surface temperature, which serves as an indicator of structural integrity and health. The experimental setup involved ballast samples derived from three different rock types—basalt, limestone, and andesite—fouled with commonly encountered materials like sand and clay at varying percentages. Results demonstrate that fouling level and type significantly influence the thermal signatures captured by IRT passive camera. Notably, ballast derived from darker rocks exhibited higher temperatures, indicating greater emissivity, while fouled ballast showed distinct temperature patterns compared to clean samples, emphasizing the potential of thermal imaging in detecting and quantifying fouling in ballast layers. This research underscores the viability of IRT passive camera in the routine maintenance and monitoring of railway infrastructure, providing a foundation for further development of integrated diagnostic tools for railway management systems.

China’s railway covers a broad area, the geological environment and climate along the line are complex and variable, the operation and maintenance of railway are facing tremendous challenges. As an integral part of railway, the maintenance of ballast bed has always attracted considerable attention, nevertheless, the variety and uneven distribution of rock materials, as well as the single ballast material standard and selection in China, which don’t take into consideration factors such as geological conditions and climatic environment, bring a host of issues to railway construction and operation and maintenance. To deal with this problem, this paper summarizes railway ballast selection methods and methodology around the world, compares the ballast material selection criteria for complex environments, summarizes novel ballast materials, and explains the indicators and test approaches used to quantify ballast performance in the standards. Comparing the ballast materials and their matching selection standards in various countries, the main conclusions of this paper are as follows: (1) For the existing ballast specification problems in China, the ballast materials can be considered to be selected according to the geological and climatic factors along the railway line; (2) There is still no method to accurately and rapidly measure the density of ballast bed without damaging it. (3) To achieve the goal of double carbon, novel ballast materials such as construction solid waste and industrial solid waste can be considered on new or modified lines where conditions are favorable.

In practice, the assessment and treatment of rail corrugation are quantitatively based on the corrugation depth. Wheel–rail vertical forces (WRVF), as a direct reflection of wheel–rail interaction, can give expression to the corrugation depth and thus serve as a key parameter for assessing the corrugation. In this paper, we propose an evaluation method for rail corrugation based on the WRVF. First, a 3D wheel–rail dynamic finite element (FE) model was developed with typical parameters of CRTS II slab track and CRH3 vehicle for high-speed railways in China. The accuracy of the model was then validated with the measured WRVF data in the field. Second, using the validated model, the time–frequency domain distribution of WRVF (vehicle speed: 300 km/h) was obtained with consideration of the corrugation wavelength in the range of 40–180 mm. The non-linear least squares method and rational equation were used to fit the function between the large value of WRVF and the corrugation depth value under the conditions of different corrugation wavelengths. Next, effects of the Pinned–Pinned resonance frequency and vibration mode on the fitted parameters were analysed, by which an indicator for corrugation treatment (grinding) was proposed. Finally, the indicator was applied in the monitoring of rail corrugation for high-speed railway lines in the field. The results show that the misjudgement rate of rail grinding decisions (using the proposed indicator) is low with the accuracy at 92.5%. The proposed method can provide a basis for the rail corrugation evaluation and grinding decisions-making.

Ballast layer defects are the primary cause for rapid track geometry degradation. Detecting these defects in real-time during track inspections is urgently needed to ensure safe train operations. To achieve this, an indicator, the track degradation rate (TDR) was proposed. This rate is calculated using track geometry inspection data to locate and predict railway-line sections with ballast layer defects. The TDR is determined by the monthly standard deviation of the rail longitudinal level, which is one aspect of track geometry. The Ballast Layer Health Classification (BLHC) is designed by assessing the two successive TDRs before and after track geometry maintenance actions. The BLHC is used to categorize the conditions of the ballast layer, including normal periodic deterioration, abrupt deterioration, effective maintenance, rising deterioration, and severe deterioration. Both the TDR and BLHC were validated through field assessments of ballast layer conditions, where the two indicators were found to be effective in revealing defects. The results indicate that the TDR is sensitive to ballast layer defects, while the BLHC can quickly identify the location of these defects. Consequently, the BLHC can provide real-time guidance for ballast layer maintenance.

Railway ballast performance is dictated by a complex mix of mechanical properties. These effect its performance at the particle level for example in terms of particle degradation, but also at the track system level in terms of settlement and stability. Therefore this paper seeks to develop new understandings of ballast behaviour and identify opportunities for future research directions. First, ballast particle size and size distribution curves are discussed, considering opportunities to improve breakage, settlement and drainage characteristics. Next, particle geometry is discussed, with a focus on form, angularity and surface texture. This is followed by a discussion on the degradation mechanisms of ballast particles and the effect of fouling on permeability. Next, techniques to assess and improve ballast bulk density are discussed, such as ground penetration radar and dynamic track stabilisation. Testing methods for studying ballast are also reviewed, first considering both smaller-scale tests such as direct shear tests and the Los Angeles abrasion test. Then larger-scale laboratory testing is discussed, including large-diameter dynamic triaxial testing and the use of full-scale laboratory tracks. Finally, conclusions are drawn and suggestions for future research directions are given.

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.

Crumb rubber (CR) has been proposed to apply in the ballast or sub-ballast layer for ballast degradation mitigation and vibration (noise) reduction. The CR can change the ballast layer stiffness, which can affect the train-track-subgrade dynamic performance and cause travel comfort and safety issues. Towards this, this study aims at confirming 1) how much the CR application can affect the dynamic performance of train and ballast layer; 2) to what extent the CR-ballast layer can distribute the train loadings to reduce subgrade surface stress. To achieve this aim, a whole train-track-subgrade system model was built by coupling multibody dynamics (MD), discrete element method (DEM) and finite difference method (FDM). The MD was used to build the train, including one vehicle body, two bogies and four wheelsets. The DEM was used to build the ballasted track, including rail, sleepers and ballast layer. The FDM was used to build the subgrade. Using the coupled model, the dynamic performance of train and track were studied, including the vehicle body acceleration, wheel-rail force, rail dynamical bending moment, sleeper acceleration, sleeper displacement and ballast acceleration. In addition, the energy dissipation of the ballast bed was also presented. For the subgrade, the subgrade surface acceleration and surface stress were measured and analysed. In the model, different CR size and percentage were considered. Results show that using the CR in ballast layer can increase the accelerations of sleeper, rail and train. But it can decrease the ballast degradation, subgrade surface acceleration and subgrade surface stress. CR helps consume train loading energy, reducing the energy that has to be consumed by ballast friction. Small size CR (8–22.4 mm) has greater influence on dynamic performance of the whole train-track-subgrade system than big size CR (9.5–63 mm). In summary, 10% percentage of CR-ballast mixture is recommended, and for CR size it is difficult to give a recommendation. Small size CR increase ballast acceleration more than big size CR, but small size CR are better at improving sleeper displacement, subgrade stress and ballast bed stress.

Ballast layer condition should be more regularly and accurately inspected to ensure safe train operation; however, traditional inspection methods cannot sufficiently fulfil this task. This paper presents a method of ground penetrating radar (GPR) application to reflect ballast layer fouling levels under diverse field conditions (annual gross passing load, cleaning and renewal year, fouling composition and transportation type). The results show that the GPR-based inspection method can assess the ballast layer fouling level with a 1–7% difference from the traditional sieving results. Fouling composition (especially metal materials) has a great effect on the GPR signals, thus affecting the inspection accuracy of ballast layer fouling level. Developing diverse GPR-based fouling indicators (by distinguishing different GPR signal features) can improve the GPR inspection applicability to the diverse field conditions.

Ground penetrating radar (GPR) is a popular technology for inspecting railway ballast layer, mainly on the ballast fouling level. However, different GPR antennas with different frequencies are suitable for different inspection emphasis and diverse railway lines (weather and sub-structure). In addition, the full-scale track model (with subgrade) for experimental tests was not seen in earlier studies. For further application of GPR in China, the GPR inspections (with 400 MHz, 900 MHz and 2 GHz antennas) were performed on a 30 m long full-scale track and three railway lines (different weather and sub-structure). Results show that ballast layer inspection should be performed mainly with the 2 GHz antenna and supplemented by the 400 MHz and 900 MHz antennas. The weather has great influence on the results of GPR inspection. This study is helpful for supplementing the guidance of ballast layer inspection with GPR.

The use of recycled materials is a new tendency in the field of railway engineering. Steel slag aggregates (SSA) are one of the recycled materials derived from the steel industry. The application of SSA in ballasted railway tracks requires mechanical examination. In the present paper, the shear behavior of the ballast layer constructed by SSA and basalt aggregates was considered to assess the use of SSA as a substitution for basalt. In this regard, a series of large-direct shear tests were performed on basalt and SSA under various normal stresses. Based on the results, basalt aggregates have higher shear resistance than SSA for all normal stress. However, steel slag has sufficient shear strength as well as particle abrasion resistance. Overall, it was proven that the SSA has suitable stability against shear forces that could be applied on railway ballast.

The Sichuan−Tibet railway is built under some difficult situations, including limited ballast bed profile, frequent earthquakes and large diurnal temperature variation. These difficulties cause insufficient lateral resistance of ballasted track, which is an urgent problem for the stability and resilience of the continuously welded rail (CWR). Aiming to improve and quantify the stability and resilience of CWR, the lateral resistance of frictional sleepers (designed as that normal sleeper with arrowhead shape groove) is evaluated with the single sleeper push test (SSPT). By performing SSPT, the increment of lateral resistance of ballast bed with frictional sleepers is measured. Shapes of sleeper grooves are properly designed and optimized (three groove shapes with the same size and volume but different arrowhead directions). Whether frictional sleeper applied to ballast bed (reduced ballast shoulder width) will provide enough lateral resistance for the ballast bed at Sichuan−Tibet railway line. Results show that frictional sleepers can increase the lateral resistance by minimum 7% and maximum 21%. Arrowhead directions significantly influence the lateral resistance, which is increased by 7% (same pushing direction) and 24% (opposite pushing direction), compared to normal sleepers. Therefore, strict attention should be paid to the laying direction when laying in curved sections of ballasted track. After reducing the ballast shoulder width from 50 cm to 30 cm, using the frictional sleeper (single arrowhead direction pushed in reversed direction) can still provide enough lateral resistance, which is the same value as a mono-block Type Ⅲ sleeper with 50 cm shoulder width.

Railway ballast is normally made of crushed rocks with grading (particle size distributions). Ballast is inevitably suffering from more rapid degradation. Because ballast keeps undergoing and dissipating most of the train loadings, furthermore, the train speed and freight weight are increasing, causing more intensive loadings to ballast. To prolong ballast service time and reduce ballast maintenance cost, more studies need to be performed on the ballast degradation reduction, ballast inspection, and ballast assessment. Therefore, earlier distinguished studies on these three aspects are introduced, summarized and discussed in this chapter, toward the final goal of providing research gaps, engineering guidance, and maintenance advice.

Ground penetrating radar (GPR) has been applied for ballast layer inspection for two decades, mainly for the analysis of ballast layer fouling levels. However, some issues that affect the inspection quality remain unsolved, such as issues involving the GPR equipment quality (antenna) and the correlation between the GPR indicator and fouling index. With the aim of solving these two issues, in this paper, we investigated the difference between the results of two different antennas, the GPR data processing technique, indicators for the fouling level (by GPR signal processing) and the correlation between the indicators and fouling index (obtained by sieving). The results show that the antenna quality determines the inspection quality. The indicators can reflect the ballast layer fouling level, and they correlate the best with the fouling index (obtained by the percentage of particles passing through a 5 mm sieve size). This study is helpful for the future modification of railway ballast maintenance standards.

Lateral and longitudinal resistance of ballasted track are two main indicators for the track stability quantification. Aiming at improving the lateral and longitudinal resistance, nailed sleeper is studied with single sleeper push tests (SSPTs) and discrete element modelling (DEM). The SSPTs were applied to study how much resistance the nailed sleeper can improve, considering different nail lengths (100, 200, 400 mm), and also used to calibrate and validate the DEM models. With the validated DEM models, different simulation conditions were performed and compared to confirm the optimal nail length (100, 200 mm) and nail number (2, 4). Results show that applying nailed sleepers improves the lateral resistance by 53.7% and the longitudinal resistance by 39.2%. 4 nails, compared to 2 nails, can increase lateral and longitudinal resistance by 20.2% and 10.6% (nail length: 100 mm) as well as 37.0% and 33.5% (nail length: 200 mm), respectively.