Wheel flats are amongst the most common local surface defect in railway wheels, which can result in repetitive high wheel–rail contact forces and thus lead to rapid deterioration and possible failure of wheels and rails if not detected at an early stage. The timely and accurate detection of wheel flats is of great significance to ensure the safety of train operation and reduce maintenance costs. In recent years, with the increase of train speed and load capacity, wheel flat detection is facing greater challenges. This paper focuses on the review of wheel flat detection techniques and flat signal processing methods based on wayside deployment in recent years. Commonly used wheel flat detection methods, including sound-based methods, image-based methods, and stress-based methods are introduced and summarized. The advantages and disadvantages of these methods are discussed and concluded. In addition, the flat signal processing methods corresponding to different wheel flat detection techniques are also summarized and discussed. According to the review, we believe that the development direction of the wheel flat detection system is gradually moving towards device simplification, multi-sensor fusion, high algorithm accuracy, and operational intelligence. With continuous development of machine learning algorithms and constant perfection of railway databases, wheel flat detection based on machine learning algorithms will be the development trend in the future.

The extraction of the light stripe center is a pivotal step in line-structured light vision measurement. This paper addresses a key challenge in the online measurement of train wheel treads, where the diverse and complex profile characteristics of the tread surface lead to uneven gray-level distribution and varying width features in the stripe image, ultimately degrading the accuracy of center extraction. To solve this problem, a region-adaptive multiscale method for light stripe center extraction is proposed. First, potential light stripe regions are identified and enhanced based on the gray-gradient features of the image, enabling precise segmentation. Subsequently, by normalizing the feature responses under Gaussian kernels with different scales, the locally optimal scale parameter (σ) is determined adaptively for each stripe region. Sub-pixel center extraction is then performed using the Hessian matrix corresponding to this optimal σ. Experimental results demonstrate that under on-site conditions featuring uneven wheel surface reflectivity, the proposed method can reliably extract light stripe centers with high stability. It achieves a repeatability of 0.10 mm, with mean measurement errors of 0.12 mm for flange height and 0.10 mm for flange thickness, thereby enhancing both stability and accuracy in industrial measurement environments. The repeatability and reproducibility of the method were further validated through repeated testing of multiple wheels.

Train wheel wear is a critical factor affecting train operational safety, making the accurate and objective evaluation of wheel wear condition essential. However, current approaches are still constrained by inadequate measurement accuracy and incomplete evaluation methods. To address this issue, this study proposes an integrated method for the high-precision measurement and wear condition evaluation of train wheels. A multi-sensor data fusion-based measurement method is developed to synchronously acquire key wear-related parameters, including wheel diameter, flange height, and flange thickness. Based on the measured data, a matter-element model combined with game-theoretic weighting is established to evaluate wheel wear condition. Experimental results show that the proposed online measurement method for in-service wheels achieves standard deviations below 0.15 mm, and the measurement errors satisfy the requirements of Chinese railway industry standards. The evaluation results derived from the high-precision measurement data indicate that wheel wear condition gradually deteriorates with increasing service mileage, and that flange height wear is the dominant factor affecting the wear grade. These findings are consistent with actual operating conditions. The proposed method integrates high-precision multi-parameter measurements with wear condition evaluation, providing a reliable technical basis for wheel condition monitoring and predictive maintenance in rail transit.

Train wheel wear is a critical factor affecting train operational safety, making the accurate and objective evaluation of wheel wear condition essential. However, current approaches are still constrained by inadequate measurement accuracy and incomplete evaluation methods, to address this issue, this study proposes an integrated method for the high-precision measurement and wear condition evaluation of train wheels. A mul-ti-sensor data fusion-based measurement method is developed to synchronously acquire key wear-related parameters, including wheel diameter, flange height, and flange thick-ness. Based on the measured data, an improved matter-element model combined with game-theoretic weighting is established to evaluate wheel wear condition. Experimental results show that the proposed online measurement method for in-service wheels achieves standard deviations below 0.15 mm, and the measurement errors satisfy the re-quirements of Chinese railway industry standards. The evaluation results derived from the high-precision measurement data indicate that wheel wear condition gradually dete-riorates with increasing service mileage, and that flange height wear is the dominant fac-tor affecting the wear grade. These findings are consistent with actual operating condi-tions. The proposed method integrates high-precision multi-parameter measurement with wear condition evaluation, providing a reliable technical basis for wheel condition moni-toring and predictive maintenance in rail transit.