Search Results (190)

Rolling contact fatigue cracks at the contact surface between a wheel and rail are evaluated based on the results of an external inspection (visual inspection). We developed a rail damage assessment technique using a fast regional convolutional neural network deep learning-based image analysis framework. We collected rail specimens from in-service tracks and performed scanning electron microscopy to correlate surface damage with subsurface crack formation, including crack depth, length, and angle. This data was input into an artificial neural network (ANN) to assess internal crack conditions using visual information obtained from rail surface damage. The resulting model achieved an average accuracy of 94.9%, outperforming other algorithms. We integrated this model into a developed rail damage diagnosis app with deep learning that links field photographs with cloud-based big data to learn, quantitatively diagnose, and present the type and scale of rail damage. We examined the field applicability of the application at a rail damage site. The standard deviation of the rail damage diagnosis results was 0.2–1.5% between different users. Appropriateness of the rail damage assessment technique using the proposed ANN image analysis technique was verified experimentally. Consistent diagnosis results could be derived regardless of the inspector, minimizing human error. Full article

Ultrasonic testing is a prevalent method for non-destructive evaluation of railway rails; however, conventional Time-of-Flight (ToF) approaches applied in practical dry-coupled inspections often rely on simplified assumptions regarding wave propagation velocity and neglect complex waveform characteristics. This paper presents a robust depth estimation framework for surface-breaking cracks that enhances sizing accuracy through effective velocity calibration and Hilbert envelope extraction. Unlike standard methods that assume the free-space speed of sound in air (343 m/s) for wave propagation within the air-filled gap of a surface-breaking crack, we propose an effective velocity model derived from in situ calibration to account for the boundary layer viscosity and thermal conduction effects within narrow crack geometries. The signal processing chain incorporates spectral analysis, band-pass filtering, and Hilbert Transform-based envelope detection to mitigate noise and resolve phase ambiguities. Experimental validation on steel specimens with controlled defects (0.2–10.0 mm) demonstrates that the proposed method achieves an exceptional linear correlation (R² ≈ 0.9976). The calibrated effective velocity was determined to be 289.3 m/s, approximately 15.6% lower than the speed of sound in air, confirming the significant influence of confinement effects. Furthermore, excitation parameters were optimized, identifying that high-voltage excitation (≥110 V) and a tuned pulse width (≈150 ns) are critical for maximizing the signal-to-noise ratio. The results confirm that combining physical model calibration with advanced signal analysis significantly reduces systematic errors, paving the way for portable, high-precision rail inspection systems. Full article

Railway transport is increasingly promoted as a sustainable and low-carbon mode of transportation. However, track-induced vibration propagation remains a significant challenge, particularly in metro systems situated near residential areas, where vibrations can transmit through the infrastructure into nearby buildings, disturbing residents and damaging structures. This study aimed to evaluate the cause of the significantly different vibration impact on nearby buildings caused by two nominally identical adjacent slab tracks on a metro line in Austria. Controlled weight drop tests were carried out in both track directions, and accelerations were measured to characterize wave transmission and energy dissipation. The data were processed using frequency response functions and Short-Time Fourier Transform to extract time–frequency signatures, modal parameters, and propagation delays. A three-dimensional finite element model of the railway superstructure was then calibrated against the experimental modal properties and transfer functions and used to simulate cracking or stiffness loss in the sleeper–slab region. The simulations reproduced the observed increase in slab acceleration and underground strain energy, linking the anomalous vibration transmission to hidden stiffness loss rather than to global design differences. Overall, the study demonstrates that combining impact testing, advanced signal processing, and calibrated finite element modelling provides an effective framework for diagnosing track defects and guiding the design and maintenance of more sustainable, low-vibration urban rail infrastructure. Full article

Artificial-intelligence-driven wayside monitoring has become a promising solution for early identification of railway wheel flats, enabling safer operations and more efficient maintenance planning. This study introduces a comparative investigation of supervised and unsupervised machine learning strategies for wheel flat identification, with particular emphasis on real-time applicability and sensor cost reduction. Support Vector Machines (SVMs) and k-means clustering are evaluated as representative supervised and unsupervised approaches using vibration data obtained from numerically simulated train–track interactions under realistic operating conditions, including train speeds of 120 km/h and 200 km/h and multiple wheel flat severities. A key contribution of this work is the proposal of a simplified supervised classification framework that directly exploits Auto-Regressive features extracted from rail-mounted accelerometers, eliminating the need for feature normalization and multi-sensor data fusion. This simplification significantly reduces computational effort, making the approach suitable for real-time deployment in operational railway environments. In parallel, a systematic sensitivity analysis is conducted to assess the influence of sensor placement and to identify the minimum sensor configuration required to achieve reliable damage classification. The outputs from the current study show that an SVM emerges with more accurate defect classification than the k-means clustering, allowing a wayside system with fewer sensors. Full article

Federated Learning (FL) enables collaborative model training without sharing raw data, offering a promising solution for privacy-sensitive applications. However, in real-world deployments, significant disparities in client computational capabilities lead to imbalanced model updates, resulting in slow convergence and degraded model generalization. To address this challenge, this paper proposes a novel federated aggregation optimization method, FedAWR, which features adaptive adjustment of learning rates and weights. Specifically, during the global aggregation phase, our method dynamically adjusts each client’s aggregation weight based on its computational capability and configures an appropriate learning rate to balance training progress. Experiments on multi-classification tasks using the Steel Rail Defect and CIFAR-10 datasets demonstrate that the proposed method exhibits significant advantages over mainstream federated algorithms in both convergence efficiency and model generalization performance, thereby validating its effectiveness and superiority. Full article

To address the challenges of accurately extracting features from elongated scratches, irregular defects, and small-scale surface flaws on high-precision linear guide rails, this paper proposes a novel instance segmentation algorithm tailored for guide rail surface defect detection. The algorithm integrates the YOLOv8 instance segmentation framework with deformable convolutional networks and multi-scale feature fusion to enhance defect feature extraction and segmentation performance. A dedicated guide rail surface Defect (GSD) segmentation dataset is constructed to support model training and evaluation. In the backbone, the DCNv3 module is incorporated to strengthen the extraction of elongated and irregular defect features while simultaneously reducing model parameters. In the feature fusion network, a multi-scale feature fusion module and a triple-feature encoding module are introduced to jointly capture global contextual information and preserve fine-grained local defect details. Furthermore, a Channel and Position Attention Module (CPAM) is employed to integrate global and local features, improving the model’s sensitivity to channel and positional cues of small-target defects and thereby enhancing segmentation accuracy. Experimental results show that, compared with the original YOLOv8n-Seg, the proposed method achieves improvements of 3.9% and 3.8% in Box and Mask mAP₅₀, while maintaining a real-time inference speed of 148 FPS. Additional evaluations on the public MSD dataset further demonstrate the model’s strong versatility and robustness. Full article

To ensure the coordinated interaction between the beam and track of large-span bridges and achieve smooth rail transition at beam joints, rail expansion regulators and beam-end expansion devices are essential at bridge ends. However, these devices are structurally fragile, making them a weak link in the seamless track system. This study selected a long-span railway bridge and its expansion devices as research objects, summarized typical in-service diseases of beam-end expansion devices (e.g., adjustable sleeper offset, sleeper skewing, and expansion device jamming), and constructed a train–track–bridge coupled model incorporating these devices. The model was used to analyze the structural performance and train operation safety under defective conditions. Based on the analysis findings, a maintenance evaluation method for the beam-end region was proposed. Criteria include adjustable sleeper offset, lateral displacement difference between adjacent beam-ends, horizontal rotation angle of adjacent beams, vertical rotation angle of beam-ends, and longitudinal expansion amount of beam-end expansion devices in order to address the corresponding issues and achieve sustainable maintenance and operation of bridge structures. Full article

Aiming at the core issues of the traditional YOLO11n model in rail surface defect detection—fine-grained feature loss of small defects, insufficient micro-target recognition accuracy, and the mismatch of existing downsampling/fusion methods for micro-defect feature extraction—this paper proposes an improved YOLO11n algorithm with two-dimensional network structure innovations. First, the Adaptive Downsampling (ADown) module is introduced into the backbone network for the first time, retaining global features via 2D average pooling and extracting local details through channel-split multi-path convolution/max pooling to avoid fine texture loss. Second, the original SOEP-RFPN-MFM neck network is designed, integrating SNI, GSConvE and MFM modules to achieve dynamic weighted fusion of multi-scale features and break the bottleneck of inefficient small-target feature aggregation. Trained and verified on a 4020-image rail dataset covering four defect types (Spalling, Squat, Wheel Burns, Corrugation), the improved algorithm achieves 93.7% detection accuracy, 92.4% recall and 95.6% mAP, realizing incremental improvements of 1.2, 2.6 and 0.8 percentage points, respectively, compared with the original YOLO11n, which is particularly optimized for rail micro-defect detection scenarios. This study provides a new deep learning method for rail transit micro-defect detection and a reference for scenario-specific improvement of lightweight YOLO11n models. Full article

In this study, with the rapid development of the field of rail vehicles, the laser welding process with high energy and small thermal deformation is selected, which reduces the working hours of post-welding grinding, repainting, and other processes, and ensures the industrial design requirements of the beautiful body after welding. The welding process for the non-penetration laser lap welding of SUS301L stainless-steel plates was optimized to address the problem of welding marks on the outer surface of railway vehicle car bodies. The impact of laser power, welding speed, and defocusing amount on weld penetration and tensile shear load was investigated using the response surface methodology. The results showed that the optimal response model for tensile shear load was the linear model, while the optimal response model for weld penetration was the 2FI model. The defocusing amount had the greatest influence on tensile shear load and weld penetration. When the laser power was 1.44 kW, the welding speed was 15 mm/s, and the defocusing amount was −4 mm, the tensile shear load reached its maximum by prediction. The actual tensile shear load of welded joints using these parameters was 4293 N with an error of merely 0.31% relative to the predicted value. The shear strength of laser-welded joints was measured at 429.3 N/mm, meeting the criteria established by the relevant standards. The tensile fracture shows characteristics of brittle fracture. The surface of the welded joints was bright white and well-formed, while the back side of the lower plate exhibited no signs of melting or welding marks. The microstructure of the weld zone (WZ) exhibited irregular columnar austenite and plate-like ferrite, while the heat-affected zone (HAZ) comprised columnar austenite and elongated bars or networks of δ-ferrite. The small-angle grain in welded joints can reduce grain boundary defects and mitigate stress concentration. After welding, angular deformation occurred, resulting in a residual stress distribution that shows tensile stress near the weld and compressive stress at a distance from the weld. Full article

Quick and reliable in situ non-destructive assessment of the material structure is especially critical in the case of measurement of rail defects concerning the demands of quick, uninterrupted transportation and safety. This paper presents the test results of a patented measuring head that is able to perform ultrasonic rail defect detection at speeds of up to 120 km/h. The experimental data was collected and discussed. Statistical analysis was performed in terms of bottom echo drop as a function of velocity, pressing force, and film thickness between the sensor and the rail material surface, as well as the coupling fluid stream intensity. The results proved the feasibility of the device for usage at high speeds for the state monitoring of rails in service. Full article

In this study, a small core diameter single mode fiber laser was applied to weld an 8 mm thick plate of 6061-T6 aluminum alloy. The microstructural evolution and mechanical properties of the laser welded aluminum alloy specimens were investigated in detail. The results indicated that fully penetrated welded specimens, free of welding defects like porosity, melt sagging, and hot cracking could be achieved by optimizing the processing parameters through response surface methodology. The upper part of the fusion zone consisted mainly of fine equiaxed dendrites, with secondary dendrite arm spacing (SDAS) of approximately 3–5 μm. While the lower region of the fusion zone exhibited pronounced microstructural coarsening, made up mostly of coarse columnar grains, along with some localized equiaxed grains, and an SDAS ranging from 8 to 12 μm. Both the fusion zone and heat affected zone (HAZ) were characterized by a “softened” hardness profile. The fusion zone featured a narrow region with the lowest microhardness across the welded joint with the microhardness value reducing to ~72% of the base metal (BM). Meanwhile, the microhardness of the HAZ was ~87.4% of the BM. The ultimate tensile strength of laser welded specimens was ~243.6 MPa, amounting to approximately 78.3% of the base metal. This study provides a fresh approach for welding medium-thick aluminum alloy plate using a high-quality laser beam, even at the kilowatt level with a fiber laser, and it shows a strong promise for applications in light-alloy manufacturing sectors such as automotive, rail transportation, aerospace, and beyond. Full article

The problem of poor coupling and wheel breakage is a critical issue in the rapid inspection of rails using contact piezoelectric ultrasonic technology for trolleys and vehicles. To overcome this shortcoming, a non-contact unidirectional Shear Vertical Wave EMAT (USV-EMAT) for rapid rail flaw detection with a larger emission angle is proposed and optimized. First, the core characteristics of the USV-EMAT and the Unidirectional Line-Focusing Shear Vertical Wave EMAT (ULSV-EMAT) are compared and analyzed, including emission angle, directivity, intensity, and detection scan distance. The results confirmed that the USV-EMAT is more suitable for rapid rail flaw detection. Secondly, the orthogonal experimental analysis method was used to optimize the structural parameters of the probe. This study systematically identified the key factors influencing the directivity and intensity of acoustic waves excited by the probe, as well as the detection blind zones. Finally, the structural parameters of the integrated 37° USV-EMAT probe were determined by comparing and analyzing the received signal characteristics of the transmit–receive racetrack coil and the self-transmitting–receiving meander coil. The results show that the optimized probe achieves a 14.3 dB SNR for detecting a 5 mm diameter, 50 mm deep transverse hole in the rail, and a 14.0 dB SNR for a 3 mm diameter, 25 mm long, 50 mm deep flat-bottomed hole. Additionally, this study reveals that as the burial depth of the transverse holes increases, the detection scan distance for such defects exhibits an “N”-shaped trend, with the minimum occurring at a depth of 90 mm. Full article

Fine-grained defects on rail surfaces are often inadequately detected by conventional vision-based object detection models in low-light environments. Although this problem can be mitigated by enhancing image brightness and contrast or employing deep learning-based object detectors, these methods frequently distort critical edge and texture information essential for accurate defect recognition. Herein, we propose a preprocessing framework that integrates two complementary modules, namely adaptive illumination enhancement (AIE) and EdgeSeal enhancement (ESE). AIE leverages contrast-limited adaptive histogram equalization and gamma correction to enhance local contrast while adjusting the global brightness distribution. ESE further refines defect visibility through morphological closing and sharpening, enhancing edge continuity and structural clarity. When integrated with the You Only Look Once v11 (YOLOv11) object detection model and evaluated on a rail defect dataset, the proposed framework achieves an ~7% improvement in mean average precision over baseline YOLOv11 and outperforms recent state-of-the-art detectors under diverse low-light and degraded-visibility conditions. The improved precision and recall across three defect classes (defects, dirt, and gaps) demonstrate the robustness of our approach. The proposed framework holds promise for real-time railway infrastructure monitoring and automation systems and is broadly applicable to low-light object detection tasks across other industrial domains. Full article

Squat is a type of rail defect that frequently poses challenges for railway tracks, as they generate dynamics and accelerate track degradation. Detecting rail squats is resource-intensive, given their relatively small size compared to the railway track. Often, by the time they are detected, damage has usually already occurred in other track components. Currently, rail squats are primarily detected using dedicated railway measurement vehicles. There has been a recent trend in research towards utilizing trains in regular traffic to monitor the condition of railway tracks. However, there is a lack of research and general guidelines regarding the optimal placement of accelerometers or sensors on trains for squat detection. In this study, multibody simulation software GENSYS Rel.2209 is employed to simulate a passenger train traversing rail squats under various scenarios, with each scenario characterized by a distinct set of typical feature values for the squats. The results demonstrate that the front wheel set, positioned closest to the defects, exhibits the highest sensitivity to vertical accelerations. Squat length is much more sensitive than depth for detection at typical speeds, and accelerometers on bogies or the car body require speeds below 40 km/h to ensure reliability. The acceleration response mechanism during squat traversal is explored, revealing the effects of varying squat geometries and train speeds. This finding enables a detection method capable of locating squats and estimating their length with over 90% accuracy. Practical recommendations are provided for optimizing squat detection systems, including squat width detection, sensor selection criteria, and suggested train speeds. It offers a pathway to detect squat more efficiently with optimized installation locations of accelerometers on a train. Full article

The vibrations induced by urban rail transit are exerting an increasingly prominent influence on the surrounding buildings and human health. As a prevalent track defect, rail corrugation can exacerbate the vibrations generated during train operation. In this study, on-site measurements were carried out to investigate the characteristics of rail corrugation in the small-radius curve segments of subways. The differences in rail corrugation with and without vibration mitigation measures were analyzed. Additionally, the vibration responses of adjacent buildings in the steel spring floating slab track segments with rail corrugation were examined. The findings of this study indicate that in the small-radius curve segments of the steel spring floating slab track, there exists a rail corrugation phenomenon with a wavelength of 200 mm. This leads to inadequate vibration attenuation in the 80 Hz frequency band, allowing some vibration energy to still be transmitted to adjacent buildings. Nevertheless, the vibration responses of buildings are predominantly governed by their own structural vibration modes. Full article