The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.

The surface cracks on high-speed railway ballastless track slabs directly influence their lifespan, while the efficiency of damage detection and maintenance is crucial for operational safety. Leveraging deep learning image processing technology can significantly enhance detection efficiency. Therefore, in response to the specific attributes of ballastless track slab crack detection, this paper introduces the RSG-YOLO model. By implementing a reparameterized dual-fused feature pyramid structure, we bolster the network’s feature extraction capacity and curtail the loss of crack features during extraction. SIoU is used to replace CIoU to optimize the bounding box regression loss function, reduce the degree of freedom of the loss function, and improve the convergence speed The GAM attention mechanism is integrated to heighten the model’s responsiveness to diverse channel information. The proposed RSG-YOLO model was evaluated against mainstream models in the field of crack detection. The results demonstrated improved detection accuracy and recall rates. Specifically, when compared to baseline models, our approach exhibited significant advancements in reducing both missed detections and false alarms. These improvements were quantified by a 4.34% increase in crack detection accuracy and a 3.08% rise in mAP_0.5. Consequently, the RSG-YOLO model effectively enables the precise detection of track slab cracks.

Large-scale mechanical equipment monitoring involves various kinds and quantities of information, and the present research on multisensor information fusion may face problems of information conflicts and modeling complexity. This paper proposes an analysis method combining correlation analysis and deep learning. According to the characteristics of monitoring data, three types of correlation coefficients between sensors in different states are obtained, and a new composite correlation analytical matrix is established to fuse the multisource heterogeneous data. The matrix represents fault feature information of different equipment states and helps further image generation. Meanwhile, a convolutional neural network-based deep learning method is developed to process the matrix and to discover the relationship between results and equipment states for fault diagnosis. To verify the method of this paper, experimental and field case studies are performed. The results show that it can accurately identify fault states and has higher diagnostic efficiency and accuracy than traditional methods.

Rotating machinery has a complicated structure and interaction of multiple components, which usually results in coupling faults with complex dynamic characteristics. Fault diagnosis methods based on vibration signals have been widely used, however, these methods are intricate when identifying coupling faults, especially in the situation where coupling faults share similar patterns. As a noncontact and nonintrusive temperature‐measuring technique, methods by infrared images can recognize multiple faults through temperature variations; however, it is not effective if the faults are temperature‐insensitive. In this paper, an improved machinery fault diagnosis technique based on information fusion of infrared images and vibration signals is studied, to have better utilization of multisource sensors and to solve the problems when one single type of data is separately used. Firstly, data enhancement for infrared images and data visualization for vibration are performed on the dataset by using the principle of graphics and Short‐Term Fourier Transform, which increases the diversity of the dataset and enhances the generalization ability of the model. Then, a multichannel convolution neural network‐based method is constructed to achieve data‐level information fusion and improve the fault diagnosis accuracy. The effectiveness of the presented method is validated by the experimental studies on a rotor test stand, the results illustrate that the coupling faults can be effectively identified by the information fusion method, and the fault diagnosis accuracy is higher in comparison with the method by a signal from single‐source sensors.

The traditional method of detecting track fasteners can lead to erroneous results due to the presence of rail bolts, wires, and extraneous objects such as stones. Consequently, the study of fastener detection in specific environments is essential. To address these issues, the TSR-Net target detection model is introduced, which employs an efficient vision transformer as a backbone to increase the speed of feature extraction. The global image perception of the network is enhanced by integrating translation convolutions and inverted residual blocks within the neck network. A detection head with a self-supervised equivariant attention mechanism is designed to deal with the occlusion challenges of small fastener targets. The model is implemented on edge AI computing devices. Technical validation indicates that TSR-Net achieves 94.2% detection precision and operates at 47 frames per second, thereby enabling accurate, real-time detection of small-target occlusion fasteners.

Cracks in high-speed rail track slabs are important indicators of aging, and the issue of ineffective crack repairs remains a significant challenge in crack maintenance. However, research on this issue is limited. This paper proposes a novel multi-class crack detection method based on the YOLOv8 framework, addressing the problem of ineffective crack repairs. To enhance the model’s feature extraction capability, we introduce the dynamic snake convolution (DSC) module into the YOLOv8 backbone network and reconstruct the Bottleneck structure in C2f, establishing the C2f-DSC module. This modification replaces some of the C2f modules, enabling better multi-scale feature extraction, particularly for difficult-to-detect ineffective cracks. Additionally, we incorporate the CA attention mechanism in the neck network to improve the model’s ability to focus on critical features and effectively transmit subtle crack details throughout the network. We also replace the CIoU loss function with SIoU, reducing excessive penalization of geometric factors, thereby enhancing the model’s generalization ability. Finally, we validate the proposed method through a comprehensive evaluation of network structure, crack data, classification methods, and environmental conditions. Experimental results show that the proposed Crack-YOLOv8 model significantly improves detection accuracy, reducing both false positives and false negatives. Specifically, the average precision and recall are enhanced by 4.9% and 4.3%, respectively, demonstrating the effectiveness of our approach in accurately detecting ineffective crack repairs in rail track slabs.