Search Results (58)

With the rapid expansion of high-speed railways, maintaining track structural health is vital for modern railway systems. Although deep learning has improved defect detection, models still face problems such as varying defect scales, severe background noise (e.g., lubricant residues and ferruginous oxidation), and irregular defect boundaries. To solve these problems, we introduce a new network named Rail-Adaptive-RCNN (RA-RCNN). It uses a Large Selective Kernel (LSK) backbone to dynamically adjust the Effective Receptive Field (ERF) for capturing periodic corrugation. We also added an Efficient Multi-Scale Attention (EMA) module that purifies features by suppressing noise without lowering dimensions. Finally, combining Scylla-IoU (SIoU) Loss with K-means clustering optimizes the regression of odd-shaped defects. Our experiments indicate that RA-RCNN reaches a mean Average Precision (mAP_0.5) of 86.2%, outperforming the baseline Faster R-CNN by 8.8%. Corrugation detection specifically reached 91.4%. With a processing speed of 26 FPS, this method effectively meets the practical needs of real-time automated railway maintenance. 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

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

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

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

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

Detecting metal surface crack defects is of great significance for the safe operation of industrial equipment. However, most existing mainstream deep-object detection models suffer from complex structures, large parameter sizes, and high training costs, which hinder their deployment and application in frontline construction sites. Therefore, this paper optimizes the existing YOLO series head structure and proposes a lightweight detection head structure, ZoomHead, with lower computational complexity and stronger detection performance. First, the GroupNorm2d module replaces the BatchNorm2d module to stabilize the model’s feature distribution and accelerate the training speed. Second, Detail Enhanced Convolution (DEConv) replaces traditional convolution kernels, and shared convolution is adopted to reduce redundant structures, which enhances the ability to capture details and improves the detection performance for small objects. Next, the Zoom scale factor is introduced to achieve proportional scaling of the convolution kernels in the regression branch, minimizing redundant computational complexity. Finally, using the YOLOv10 and YOLO11 series models as baseline models, ZoomHead was used to replace the head structure of the baseline models entirely, and a series of performance comparison experiments were conducted on the rail surface crack dataset and NEU surface defect database. The results showed that the integration of ZoomHead effectively improved the model’s detection accuracy, reduced the number of parameters and computations, and increased the FPS, achieving a good balance between detection accuracy and speed. In the comparative experiment of the SOTA model, the addition of ZoomHead resulted in the model having the smallest number of parameters and the highest FPS, while maintaining the same mAP value as the SOTA model, indicating that the ZoomHead structure proposed in this paper has better comprehensive detection performance. Full article

Rail surface defects pose significant risks to the operational efficiency and safety of industrial equipment. Traditional visual defect detection methods typically rely on high-quality RGB images; however, they struggle in low-light conditions due to small, low-contrast defects that blend into complex backgrounds. Therefore, this paper proposes a novel defect segmentation method leveraging a dual-stream feature fusion network that combines polarization images with DeepLabV3+. The approach utilizes the pruned MobileNetV3 as the backbone network, incorporating a coordinate attention mechanism for feature extraction. This reduces the number of model parameters and enhances computational efficiency. The dual-stream module implements cascade and addition strategies to effectively merge shallow and deep features from both the original and polarization images. This enhances the detection of low-contrast defects in complex backgrounds. Furthermore, the CBAM is integrated into the decoding area to refine feature fusion and mitigate the issue of missing small-target defects. Experimental results demonstrate that the enhanced DeepLabV3+ model outperforms existing models such as U-Net, PSPNet, and the original DeepLabV3+ in terms of MIoU and MPA metrics, achieving 73.00% and 80.59%, respectively. The comprehensive detection accuracy reaches 97.82%, meeting the demanding requirements for effective rail surface defect detection. Full article

With the vigorous development of speedy railway technology, steel rails, as an important structural infrastructure in speedy railways, play a crucial role in ensuring the safety of the entire speedy railway operation. A brand-new type of speedy rail inspection robot and its fault detection method are proposed to solve a number of problems, such as the difficulty and low accuracy of real-time online detection of rail defects and damage in speedy railways. The brand-new rail inspection robot is driven by two drive wheels and adopts a standard rail gauge of 1435 mm, which ensures its speedy and smooth operation on the track as well as accurate motion posture information. Firstly, 12 common types of surface damage of the rail head were analyzed and classified into five categories based on their damage characteristics. The motion state of the rail inspection robot under the five types of surface damage of the rail head was analyzed and subjected to kinematic analysis. This study analyzed the relationship between the distinctive types of damage and the motion posture of the robot during the inspection of the five types of damage. Finally, experimental tests were conducted, and it was found that the robot’s motion posture would undergo sudden changes when inspecting distinctive types of injuries; the highest error rate was 3%. The effectiveness of this method was verified through experiments, and the proposed new track detection robot can greatly improve the track detection efficiency of high-speed railways and has specific academic research value and practical application value. Full article

To address the challenges in existing multi-sensor data fusion methods for rail surface defect diagnosis, particularly their limitations in fully exploiting potential synergistic information among multimodal data and effectively bridging the semantic gap between heterogeneous multi-source data, this paper proposes a diagnostic approach based on a Progressive Joint Representation Graph Attention Fusion Network (PJR-GAFN). The methodology comprises five principal phases: Firstly, shared and specific autoencoders are used to extract joint representations of multimodal features through shared and modality-specific representations. Secondly, a squeeze-and-excitation module is implemented to amplify defect-related features while suppressing non-essential characteristics. Thirdly, a progressive fusion module is introduced to comprehensively utilize cross-modal synergistic information during feature extraction. Fourthly, a source domain classifier and domain discriminator are employed to capture modality-invariant features across different modalities. Finally, the spatial attention aggregation properties of graph attention networks are leveraged to fuse multimodal features, thereby fully exploiting contextual semantic information. Experimental results on real-world rail surface defect datasets from domestic railway lines demonstrate that the proposed method achieves 95% diagnostic accuracy, confirming its effectiveness in rail surface defect detection. Full article

With the widespread application of high-speed and heavy-load railways, the real-time detection of track surface defects has become increasingly crucial. To address the challenges in rail defect detection, this study proposes the PerMSCA-YOLO model, which aims to overcome the limitations of traditional object detection models in multi-scale, small target, and complex background scenarios. By incorporating the lightweight FasterNet backbone network, a multi-scale convolutional attention module, and perceptual loss, the proposed model significantly enhances the detection accuracy and robustness of track defects. Experimental results show that PerMSCA-YOLO achieves an mAP@0.5 of 0.856, an F1-score of 0.79, and an inference frame rate of 142 FPS, demonstrating superior detection accuracy and real-time performance compared to other mainstream models like YOLOv8n. Furthermore, the model exhibits strong adaptability and efficiency when dealing with complex track defects, such as microcracks and corrosion patches, indicating its broad practical application potential. The innovative contribution of this research lies in its effective strategy for improving detection accuracy and real-time performance through multi-scale feature fusion and deep semantic alignment mechanisms, providing a solution that balances both precision and efficiency for defect detection in complex track environments, with substantial engineering application potential. Full article

Detecting track geometry and rail surface defects using on-board vehicle monitoring systems is a key issue for rail infrastructure managers to increase availability and reliability while reducing the costs associated with monitoring and maintenance. Rail corrugation is one of the most common rail surface defects which grows in almost all metro, conventional and high-speed lines. This paper focuses on the development of a methodology to detect rail corrugation using axle box acceleration measurements acquired on an in-service high-speed vehicle. The main purpose of the proposed methodology is to distinguish the effect of rail corrugation on the accelerations from the other excitations that can be observed in the same wavelength range. For this purpose, the accelerations are analysed by calculating the fast Fourier transform and the spectrogram. Based on the characteristics of each excitation, the effects of modes of vibration, resonances, bridges, switches, and wheel defects are identified. From the remaining effects, which have congruent characteristics, a hypothesis of rail corrugation is formulated. The hypothesis is consolidated with multibody dynamics simulations and by comparing the corrugation indicators provided by the railway infrastructure company. Full article

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. Full article

Railways play a pivotal role in national economic development, freight transportation, national defense, and regional connectivity. The detection of rolling contact fatigue (RCF) defects in rail tracks is essential for railway safety and maintenance. Due to its efficiency and non-contact capability in detecting surface and near-surface defects, Eddy Current Pulsed Thermography (ECPT) has garnered significant attention from researchers. However, detecting multi-layer RCF defects remains a challenge. This paper introduces a sweeping Eddy Current Pulsed Thermal-Tomography system (ECPTT) to detect multi-layer RCF defects effectively. This system utilizes varying excitation frequencies to heat defects, altering skin depth and facilitating feature extraction to distinguish multi-layer RCF defects. Skewness and thermographic signal reconstruction (TSR) values are employed as features in the experiments. These features are qualitatively analyzed to differentiate the layers and depths of multi-layer RCF defects. Additionally, five different coils were compared and analyzed quantitatively. The results indicate that the ECPTT system can effectively detect and distinguish multi-layer RCF defects, thereby providing more detailed defect information and enhancing railway safety and maintenance efficiency. Full article

Rail surface defects typically serve as early indicators of railway malfunctions, which may compromise the quality and corrosion resistance of rails, thereby endangering the safe operation of trains. The timely detection of defects is essential to ensure the safe operation of railways. To improve the classification accuracy of rail surface defect detection, this paper proposes a rail surface defects detection algorithm based on MobileNet-YOLOv7. By integrating lightweight deep learning algorithms into the engineering application of rail surface defect detection, a MobileNetV3 lightweight network is used as the backbone network for YOLOv7 to enhance both speed and accuracy in complex defect extraction. Subsequently, the efficient intersection over union (EIOU) loss function is utilized as the positional loss function to bolster system resilience. Finally, the k-means++ clustering algorithm is applied to obtain new anchor boxes. The experimental results demonstrate the effectiveness of the proposed method, achieving superior detection accuracy compared with traditional algorithms. Full article