Rail Defects Research Articles

SH guided wave excitation in rails for defect and stress monitoring

Monitoring rail defects and thermal stress is imperative in ensuring the safety of railway transportation. Guided-wave-based inspection techniques emerge as a promising solution for concurrently detecting both the defects and thermal stress in rails. However, the substantial multimodal and dispersive nature of guided waves in the rail poses limitations on the application and advancement of this technology. This study systematically investigates the propagation characteristics of the SH0-like wave (the lowest-order shear horizontal-like wave) in the rail and its effectiveness in defect and axial stress monitoring through finite element simulations and experiments. A method based on dual opposite polarization active elements, and the corresponding piezoelectric transducers are proposed to excite SH0-like wave in the rail web and rail foot. Results show that SH0-like wave can travel stably across a broad frequency range in the rail web and rail foot. Additionally, both the simulations and experiments confirm that the SH0-like wave in the rail web is suitable for monitoring axial stress, as its velocity changes linearly with axial stress variations. Furthermore, the ability of the SH0-like wave to detect cracks and hole defects in the rail web is experimentally demonstrated. Given that the SH0-like wave is quasi-nondispersive in a broad frequency range and an SH0-like wave with high SRN can be effectively generated using the proposed method, this research aims to offer a practical technical solution to overcome the challenges of multimodal and dispersive effects in the guided-wave-based rail inspection techniques. It also sets the stage for developing a comprehensive system capable of simultaneously monitoring the defects and thermal stress in rails.

Use of operational track dynamics logger measurement data on Norwegian railway tracks to analyze rail joints and rail welding degradation

Since 2022, the Bane Nor Measurement train is equipped with a TDL (Track Dynamics logger) designed by SD&M - France. The TDL captures, by means of 4 triaxial accelerometers on the bearings of a bogie and 4 water resistant microphones, both the forces and noise emission generated by the complete Norwegian railway network, automatically and without need for any user interaction. The acquired data (0-20kHz) is processed towards parameters usable for noise mitigation and maintenance planning, and both raw and processed data are transferred through a 4G/5G connection to a dedicated cloud repository. In Norway, about 4000 kilometers of tracks are covered by the TDL, recording parameters for protection of the infrastructure (rails, sleepers, ballast), for troubleshooting annoyance of citizens (noise, vibrations), and for verification of maintenance activities (grinding, tamping, switches, etc.). Roughness spectra (1-50 cm wavelengths), squat detection, and railpad damping properties are some examples of parameters that can be extracted from the data. Here we will focus mainly on detection or rail defects such as squats, studs, and weldings, by applying advanced signal processing such as band filtering, wavelets, and specific issue-detection algorithms. A comparison can be made with other measurement techniques, e.g., laser scanning or high-speed photography.

Причины возникновения и развития дефектов рельсов в кривых на участках обращения поездов повышенной массы и длины

Purpose: determine the causes of defects in rails in areas of circulation of trains of increased weight and length through modeling the operation of rails in curved sections of the railway track using digital twins. Methods: t study the influence of various factors on rail wear in curved sections of the track, software systems were used ased on the numerical solution of differential equations for the movement of rolling stock and the operation of the railway track under the train. To determine the stresses in the rails in order to predict the development of contact-fatigue defects, dynamic calculations using the finite element method were used. Results: it was revealed that in order to reduce rail wear in a curved section of the track in sections with predominantly freight traffic, the elevation of the outer rail must be calculated based on the actually realized speeds of freight trains. It has been established that at the moment the influence of the amount of rail inclination on rail wear has not been sufficiently studied. As an analysis of the position of the rails at various inclines has shown, for the curve under consideration it is most advisable to use a 1/30 inclination within the limits of a circular curve and with a 1/20 to 1/30 inclination within the transition curve. To reduce the likelihood of contact-fatigue defects occurring in such areas, it is necessary to provide for the implementation of measures to lubricate the side working edge of the outer rail thread and the rolling surface of the inner rail thread within the entire curve. Practical importance: the research results indicate the need to revise the approach to calculating the elevation of the outer rails in curves with heavy freight train traffic. The possibility of extending the service life of rails by revising the system for planning and implementing work on lubricating and grinding rails in curves in areas where trains of increased mass and length operate

Переходные участки бесстыкового пути, примыкающие к стрелочным переводам

Purpose: consider the problem of interaction between turnouts and adjacent sections of a seamless railway track. Methods: statistical data analysis. Results: an analysis of the results of domestic and foreign studies has been carried out, which show that in such areas there is a jump with subsequent extrusion of material of less rigidity and an increase in the slope of the elastic unevenness, i. e., an undesirable phenomenon occurs — a shock wave. The impact force depends on the mass of the rolling stock and the speed of movement, the geometric evenness of the rail track and the chosen approaches to designing the transition zone as a whole. Jump and mainly occurs due to compression and pushing out of structural layers and materials of lower rigidity in the under-rail area. The impact force depends on the mass of the rolling stock and the speed of movement, the geometric evenness of the rail track and the chosen approaches to designing the transition zone as a whole. Jump and mainly occurs due to compression and pushing out of structural layers and materials of lower rigidity in the under-rail area. Shock waves caused by uneven rigidity of sections have negative consequences (the appearance of deviations in level, subsidence, distortions, increased intensity of rail wear, the appearance of rail defects), which increase the cost of maintenance of the railway track. An analysis of the accumulation of residual deformations has been carried out, which shows the systematic formation of geometric irregularities in adjacent areas in the turnout area. Practical importance: from the point of view of the design of the transition zone, the expected advantage will be the differentiation of structural materials and elements and their influence on achieving the optimal gradation of railway track rigidity in the vertical and horizontal (transverse, longitudinal directions), selection of the optimal ratio of the mechanical properties of individual elements of the superstructure structure. It should also be noted that it is necessary to conduct an additional feasibility study of the feasibility of constructing transition sections in the area where the track and switches meet, taking into account the operational features of individual railway lines.

Signal reconstruction with infrared thermographic data in the application of rail defect detection

Signal reconstruction with infrared thermographic data in the application of rail defect detection

Research on Rail Surface Defect Detection Based on Improved CenterNet

Rail surface defect detection is vital for railway safety. Traditional methods falter with varying defect sizes and complex backgrounds, while two-stage deep learning models, though accurate, lack real-time capabilities. To overcome these challenges, we propose an enhanced one-stage detection model based on CenterNet. We replace ResNet with ResNeXt and implement a multi-branch structure for better low-level feature extraction. Additionally, we integrate SKNet attention mechanism with the C2f structure from YOLOv8, improving the model’s focus on critical image regions and enhancing the detection of minor defects. We also introduce an elliptical Gaussian kernel for size regression loss, better representing the aspect ratio of rail defects. This approach enhances detection accuracy and speeds up training. Our model achieves a mean accuracy (mAP) of 0.952 on the rail defects dataset, outperforming other models with a 6.6% improvement over the original and a 35.5% increase in training speed. These results demonstrate the efficiency and reliability of our method for rail defect detection.

Исследование параметров системы аспирации рельсошлифовального поезда

The rail-grinding technology is used for the railway network of the JSC RZhD to eliminate rail defects and extend the lifecycle of the railway track. In order to implement the rail-grinding technology, currently, rail-grinding trains RShP-48 are used. Rails are ground with special grinding wheels made of zirconium electro-corundum manufactured based on aluminum oxide and zirconium oxide, with bakelite organic bond as a binder. In addition, the abrasive wheel composition includes various chemical components. When an abrasive tool is destructed, grinding waste in the form of suspensions is generated during its mechanic work. The suspensions spread over long distances and negatively affect both the environment and the working conditions of the rail-grinding train maintenance personnel. Today, the company «Sinara — Transport Machines» is developing a new rail-grinding train RShP 2.0 with a pre-installed aspiration system to collect grinding wastes for further utilization. When developing the technical design of RShP 2.0, the main characteristics of the aspiration system have been determined. In order to confirm the efficiency of the obtained parameters of the aspiration system, laboratory tests have been conducted on a special rail-grinding unit. According to the results, the aspiration system with the stated technical characteristics absorbs the fine fraction of grinding products which is about 50 % of the total lost mass of the grinding wheel. Considering a large abrasive that sticks to the spark arrestors together with metal chips, the aspiration system RShP 2.0 will enable removing up to 90 % of grinding waste.

Experimental study on test of wheel-rail impact based on iron plate strain of fastener system

The wheel-rail impact load can reach up to 3–4 times the normal wheel load, with two peaks including a high-frequency impact force (P1) and a mid-frequency or quasi-static impact force (P2). To effectively monitor the wheel-rail impact, this study utilizes strain gauges adhered to bottom of iron plates of fastener to measure rail-seat force, and conducts indoor static load and wheel-drop tests. A finite element model is established for verification and analysis. By analyzing the transmission law of the wheel-rail impact, a monitoring method through rail-seat force is proposed. The results reveal that the strain change of the iron plate in the static load test remains stable and exhibits a linear relationship with rail-seat force. Through a full-scale wheel-drop test, it demonstrates that rail-seat force can effectively monitor P2 force of wheel-rail impact. Compared to traditional method of directly adhering strain gauges to rail, the method of adhering strain gauges to iron plate enabled wheel-rail impact invalid test sections measurement. The peak value of wheel-rail impact P2 can be deduced from peak value of rail-seat force under different impact location, impact levels, and elastic pad stiffness. The proposed monitoring method of based on fastener iron plate strain offers a more efficient alternative for identifying wheel defects and rail defects.

Hybrid physics machine learning for ultrasonic field guided 3D generation and reconstruction of rail defects

Ultrasonic technology is widely used in the field of rail defects detection. 3D reconstruction of rail defects can intuitively restore the 3D size and spatial position of the defects inside the rail. Currently, ultrasound-based 3D reconstruction requires a multi-probe or mechanical scanning platform in a laboratory setting, which is not suitable for the railway environment. In addition, 3D reconstruction requires a large amount of data, making it difficult to collect sufficient ultrasonic 3D defect data for long-distance rail inspections. This paper proposes an ultrasonic field-guided 3D reconstruction method combined with machine learning hybrid physics for rail defects. It combines both sound field GAN model to reconstruct the defect 3D model from the 2D B-scan data. The proposed method can generate a defect cross-sectional image using a deep learning algorithm guided by the acoustic field in the B-scan space, and extract the 3D size information of the defect from the 2D B-scan information by establish a defect echo model. By stablishing a spatial mapping relationship between the B-scan and the rail coordinate system, the position of the defect in the rail coordinate system is obtained. The defect data of standard damage rails are tested. Experiment results indicate that the defects in different parts of the rail can be reconstructed by the proposed method. The average size error rate is 9.56%–21.14 %, and the average height error is 3.458mm–6.353 mm.

Rail Surface Defect Detection Based on Dual-Path Feature Fusion

With the rapid development of rail transit, the workload of track maintenance has increased, making the intelligent identification of rail surface defects crucial for improving detection efficiency. To address issues such as low defect detection accuracy, the loss of feature information due to single-path architecture backbones, and insufficient information interaction in existing rail defect detection methods, we propose a rail surface defect detection method based on dual-path feature fusion (DPF). This method initially employs a dual-path structure to separately extract low-level and high-level features. It then utilizes a combination of attention mechanisms and feature fusion techniques to integrate these features. By doing so, it preserves richer information and enhances detection accuracy and robustness. The experimental results demonstrate that the comprehensive performance of the proposed model is superior to mainstream algorithms.

Detection of Rail Defects Caused by Fatigue due to Train Axles Using Machine Learning

Detection of Rail Defects Caused by Fatigue due to Train Axles Using Machine Learning

Corrugation and Squat Classification and Detection with VGG16 and YOLOv5 Neural Network Models

Railway track defects in Malaysia pose significant risks of train derailments and accidents, underscoring the urgency for early and accurate defect detection and classification. This study presents a novel approach utilizing deep learning models, VGG16 and YOLOv5, for detecting and classifying railway track defects, explicitly focusing on corrugation and squat defects. The research's uniqueness lies in its application of these specific models and the composition of a dataset collected from extensive field measurements and inspections across various railway tracks within the Track Network Maintenance Ampang Line in Malaysia. The results demonstrate that these models achieve high precision in defect classification and detection of defects by more than 80%. The proposed methodology provides the railway industry with a powerful tool to streamline maintenance planning and prioritize defect remediation efficiently. Early defect detection can prevent potential accidents and improve safety and operational efficiency. Future studies can expand on these findings by exploring the extension of the proposed techniques to address other types of rail defects. Incorporating a diverse range of scenarios and operating conditions in the dataset could further enhance the models' performance and generalization. Real-time deployment and integration with existing maintenance systems are crucial for practical adoption. This research has strengths but acknowledges limitations. Additional evaluation metrics and a diverse dataset are essential for model performance. Leveraging deep learning models offers a reliable solution for railway maintenance, enhancing safety and efficiency. Addressing these limitations will drive proactive defect management, ensuring safe and reliable railway networks.

Identification Methods for Modal Parameters of Track Structures and Their Application Status and Prospects

Rail transit’s wheel–rail system periodically encounters defects such as wheel polygons, rail corrugation, and rail fastener failure, which are intricately linked to the modal parameters of track structures. Identifying these modal parameters is essential for refining wheel–rail dynamics models, understanding track defect mechanisms, and defect detection. This study reviews the current methodologies for identifying track structure modal parameters, emphasizing their significance in track engineering. It categorizes various identification techniques, examines their development, and highlights their application in updating track dynamics theoretical models. The relationship between track modal parameters and wheel–rail defects is discussed, alongside a summary of modal parameter-based defect remediation strategies globally. The paper also evaluates the current state of defect identification research utilizing track modal parameters. In the “prospects” section, three forward-looking research avenues are proposed. These approaches are poised to streamline and improve the efficiency of modal parameter extraction, marking potential breakthroughs in the field.

Research on detection of switch rail defects based on pulse reflection method of the dominant mode

Guided wave structural health monitoring offers a promising way for continuous surveillance and identification of structural damage. However, due to the variable cross-section properties of the switch rail in the longitudinal direction, there are different modes present on different cross-sections, so the guided wave signals excited are very complex. The traditional baseline subtraction method can be used to extract defect echo features, but it is prone to false positives due to the influence of external factors such as field temperature change and environmental noise. This paper proposes a switch rail defect detection method based on the pulse reflection method of the dominant mode. Initially, eight typical cross-sections are chosen based on the cross-sectional dimensions of the switch rail. Semi-analytical finite element(SAFE) method is utilized to solve the dispersion curves and wave structure matrix of guided waves in the switch rail. According to the 3σ rule, the dominant mode whose node amplitude is much higher than other modes is selected, and the excitation signal is applied at the maximum value of the mode, which successfully excites the dominant mode. Through simulation and experimental validation, the reflected waves of the dominant mode at the defect are observable and visible, and the pulse reflection method can be used to detect the defects at the switch rail foot with a positioning error of less than 10 cm. The pulse reflection method of the dominant mode proposed in this paper, which has high detection efficiency and is not affected by the ambient temperature, provides a new idea and way to detect defects of the switch rail based on the ultrasonic guided wave method.

The Remaining Life Prediction of Rails Based on Convolutional Bi-Directional Long and Short-Term Memory Neural Network with Residual Self-Attention Mechanism

In the railway industry, the rail is the basic load-bearing structure of railway tracks. The prediction of the remaining useful life (RUL) for rails is important to avoid unexpected system failures and reduce the cost of maintaining the system. However, the existing detection of rail flaws is difficult, the rail deterioration mechanisms are diverse, and the traditional data-driven methods have insufficient feature extraction. This causes low prediction accuracy. With objectives set in relation to the problems outlined above, a rail RUL prediction approach based on a convolutional bidirectional long- and short-term memory neural network with a residual self-attention (CNNBiLSTM-RSA) mechanism is designed. Firstly, the pre-processed vibration data are taken as the input for the convolutional bi-directional long- and short-term memory neural network (CNNBiLSTM) to extract the forward and backward dependencies and features of the rail data. Secondly, the RSA mechanism is introduced in order to obtain the contributions of the features at different moments during the degradation process of the rail. Finally, an end-to-end RUL prediction implementation based on the convolutional bi-directional long- and short-term memory neural network with the residual self-attention mechanism is established. The experiments were carried out using the full life-cycle data of rails collected at the railway site. The results show that the method achieves a higher accuracy in the RUL prediction of rails.

Rail Flaw Detection via Kolmogorov Entropy of Chaotic Oscillator Based on Ultrasonic Guided Waves.

Ultrasonic guided wave (UGW) inspection is an emerging non-destructive testing(NDT) technique for rail flaw detection, where weak UGW signals under strong noise backgrounds are difficult to detect. In this study, a UGW signal identification model based on a chaotic oscillator is established. The approach integrates the UGW response into the critical state of the Duffing system to serve as a disturbance control variable. By evaluating the system's motion state before and after introducing the UGW response, identification of UGW signals can be realized. Thus, the parameters defining the critical state of Duffing oscillators are determined by Ke. Moreover, an electromagnetic transducer was specifically devised to enable unidirectional excitation for UGWs targeted at both the rail base and rail head. Experimental studies showed that the proposed methodology effectively detected and located a 0.46 mm notch at the rail base and a 1.78 mm notch at the rail head. Furthermore, Ke was directly proportional to the notch size, which could be used as a quantitative index to characterize the rail flaw.

Evaluation of typical rail defects by induction thermography: experimental results and procedure for data analysis during high-speed laboratory testing

ABSTRACT Rail inspection via non-destructive testing (NDT) techniques is a critical area of research in the railway industry, significantly affecting transport safety and security. Conventional NDT methods face limitations in on-site applications, with emerging techniques improving defect detectability and inspection speed. Recent advances have highlighted infrared thermography, particularly induction thermography, as a promising alternative due to its non-contact, full-field capabilities for detecting both surface and subsurface rail defects. This study explores induction thermography in detecting key defects such as transversal cracks and head checks in different rail tracks. Novel approaches and procedure for data reconstruction that enhance the thermographic inspection results and allow for dynamic testing conditions are proposed. Additionally, the potential for high-speed on-site applications was investigated, utilizing infrared mirrors and optimally shaped coils. Various test parameters, including geometrical resolution, excitation power, and inspection speed up to 20 km/h, were systematically examined.

Improved YOLOv8 for B-scan image flaw detection of the heavy-haul railway

With the high speed and heavy duty of railway transportation, internal flaw detection of railway rails has become a hot issue. Existing rail flaw detection systems have problems of low detection accuracy and occasional missed flaw detection. In this paper, a high-precision flaw detection based on data augmentation and YOLOv8 improvement is proposed. Firstly, three data augmentation algorithms based on the characteristics of B-scan images are designed to enrich the dataset of rail flaws. Then, the small target detection layer and the cross-layer connectivity module are added to capture more information for small targets. Finally, the introduction of dynamic weights to coordinate attention can adjust the attentional weights and capture long-range information. The experimental results show that the mAP50 of the model after data enhancement and algorithm improvement is 97.9%, which is improved by 4.4% from the baseline model, and the frame per second is 64.52. The proposed method effectively detects many typical flaws, including the railhead flaw, rail jaw flaw, screw hole crack, and bottom flaw, which can provide technology supports for on-site maintenance staff.

Deep learning techniques to detect rail indications from ultrasonic data for automated rail monitoring and maintenance

The increasing number of passengers and services using railways and the corresponding increase in rail use has caused the acceleration of rail wear and surface defects which makes rail defect identification an important issue for rail maintenance and monitoring to ensure safe and efficient operation. Traditional visual inspection methods for identifying rail defects are time-consuming, less accurate, and associated with human errors. Deep learning has been used to improve railway maintenance and monitoring tasks. This study aims to develop a structured model for detecting railway artifacts and defects by comparing different deep-learning models using ultrasonic image data. This research showed whether it is practical to identify rail indications using image classification and object detection techniques from ultrasonic data and which model performs better among the above-mentioned methods. The methodology includes data processing, labeling, and using different conventional neural networks to develop the model for both image classification and object detection. The results of CNNs for image classification, and YOLOv5 for object detection show 98%, and 99% accuracy respectively. These models can identify rail artifacts efficiently and accurately in real-life scenarios, which can improve automated railway infrastructure monitoring and maintenance.

ECARRNet: An Efficient LSTM-Based Ensembled Deep Neural Network Architecture for Railway Fault Detection

Accidents due to defective railway lines and derailments are common disasters that are observed frequently in Southeast Asian countries. It is imperative to run proper diagnosis over the detection of such faults to prevent such accidents. However, manual detection of such faults periodically can be both time-consuming and costly. In this paper, we have proposed a Deep Learning (DL)-based algorithm for automatic fault detection in railway tracks, which we termed an Ensembled Convolutional Autoencoder ResNet-based Recurrent Neural Network (ECARRNet). We compared its output with existing DL techniques in the form of several pre-trained DL models to investigate railway tracks and determine whether they are defective or not while considering commonly prevalent faults such as—defects in rails and fasteners. Moreover, we manually collected the images from different railway tracks situated in Bangladesh and made our dataset. After comparing our proposed model with the existing models, we found that our proposed architecture has produced the highest accuracy among all the previously existing state-of-the-art (SOTA) architecture, with an accuracy of 93.28% on the full dataset. Additionally, we split our dataset into two parts having two different types of faults, which are fasteners and rails. We ran the models on those two separate datasets, obtaining accuracies of 98.59% and 92.06% on rail and fastener, respectively. Model explainability techniques like Grad-CAM and LIME were used to validate the result of the models, where our proposed model ECARRNet was seen to correctly classify and detect the regions of faulty railways effectively compared to the previously existing transfer learning models.