Xiao-Zhou Liu

Interlayer damage is a critical issue affecting the structural integrity and service performance of high‐speed railway slab tracks. Traditional track inspection data‐driven identification methods often rely on manual feature extraction and are limited by insufficient utilization of temporal and multisource inspection data, resulting in limited accuracy and robustness. To address these challenges, this study proposes a tile‐coding neural network (TC‐NN) for the identification and localization of interlayer debonding. The model integrates tile coding with a convolutional neural network to automatically extract spatiotemporal features from multiperiod track inspection data while enabling the fusion of track geometry and car‐body vibration measurements. Comprehensive experiments using real‐world data from two high‐speed railway lines demonstrate that the TC‐NN achieves an identification accuracy of 87.60% using only track irregularity data, and further improves to 89.09% when synchronized multisource inputs are used. The acceleration‐only model shows limited standalone discriminability, whereas the shuffled‐acceleration control experiment indicates that the synchronized relationship between track geometry and car‐body dynamic response provides auxiliary information for the fused model. With the optimized tile‐coding configuration, the proposed framework supports defect localization along the track, achieving a localization recall of 96.00% on a continuous section under a ± 6.45 m tolerance, approximately corresponding to one standard CRTS‐II slab length. These results suggest that the TC‐NN provides a geometry‐dominant and acceleration‐assisted framework for engineering‐oriented screening of interlayer debonding in slab tracks.

Mud pumping in slab tracks poses a significant threat to the structural integrity and operational safety of high-speed railways (HSRs). This study investigates the distribution characteristics and degradation mechanisms of mud pumping defects along a 301 km HSR line in eastern China. Based on multi-year inspection and maintenance data, a novel maintenance decision-making index (M-Index) is proposed to quantitatively assess track geometry degradation associated with mud pumping. Four typical defect scenarios (H1–H4) are defined based on the number of affected slabs and field observations. The M-Index is used to classify track segments into three management levels, corresponding to different stages of defect evolution and maintenance urgency. Degradation rates of track segments are calculated using linear fitting of the M-Index over grouting cycles, and percentile thresholds (70%, 80%, 90%) are introduced to guide condition classification. The study further proposes a data-driven maintenance strategy that incorporates track inspection data, M-Index evaluation, degradation rate analysis, and defect history logging. The results demonstrate that the proposed method enables accurate identification of deteriorating segments and supports timely and cost-effective maintenance planning.

The surface defects on a shield subway tunnel can significantly affect the serviceability of the tunnel structure and may compromise operation safety. To effectively detect multiple surface defects, this study uses a tunnel inspection trolley (TIT) based on the mobile laser scanning technique. By conducting an inspection of the shield tunnel on a metro line section, various surface defects are identified with the TIT, including water leakage defects, dislocation, spalling, cross-section deformation, etc. To explore the root causes of the surface defects, association rules between different defects are calculated using an improved Apriori algorithm. The results show that: (i) there are significant differences in different association rules for various surface defects on the shield tunnel; (ii) the average confidence of the association rule “dislocation & spalling → water leakage” is as high as 57.78%, indicating that most of the water leakage defects are caused by dislocation and spalling of the shield tunnel in the sections being inspected; (iii) the weakest rule appears at “water leakage → spalling”, with an average confidence of 13%. The association analysis can be used for predicting the critical defects influencing structural reliability and operation safety, such as water leakage, and optimizing the construction and maintenance work for a shield subway tunnel.

Surface cracks are typical defects in high-speed rail (HSR) slab tracks, which can cause structural deterioration and reduce the service reliability of the track system. However, the question of how to effectively detect and quantify the surface cracks remains unsolved at present. In this paper, a novel crack-detection method based on infrared thermography is adopted to quantify surface cracks on rail-track slabs. In this method, the thermogram of a track slab acquired by an infrared camera is first processed with the non-subsampled contourlet transform (NSCT)-based image-enhancement algorithm, and the crack is located via an edge-detection algorithm. Next, to quantitatively detect the surface crack, a pixel-locating method is proposed, whereby the crack width, length, and area can be obtained. Lastly, the detection accuracy of the proposed method at different temperatures is verified against a laboratory test, in which a scale model of the slab is poured and a temperature-controlled cabinet is used to control the temperature-change process. The results show that the proposed method can effectively enhance the edge details of the surface cracks in the image and that the crack area can be effectively extracted; the accuracy of the quantification of the crack width can reach 99%, whilst the accuracy of the quantification of the crack length and area is 85%, which essentially meets the requirements of HSR-slab-track inspection. This research could open the possibility of the application of IRT-based track slab inspection in HSR operations to enhance the efficiency of defect detection.

The surface defects of shield subway tunnel can significantly affect the serviceability of the tunnel structure and may compromise the operation safety. To effectively detect the multiple surface defects, this research employs a tunnel inspection trolley (TIT) based on the mobile laser scanning technique. By conducting the inspection of the shield tunnel on a metro line section, various surface defects are identified by the TIT, including water leakage defect, dislocation, spalling, cross-section deformation, etc. To explore the root causes of the surface defects, the association rules between different defects are calculated via an improved Apriori algorithm. Results show that: i) there are significant differences in different association rules of various surface defects of the shield tunnel; ii) the average confidence of the association rule “dislocation & spalling → water leakage” is as high as 57.78%, indicating that most of the water leakage defects are caused by dislocation and spalling of the shield tunnel in the sections being inspected; iii) the weakest rule appears at “water leakage → spalling”, with the average confidence of 13%. The association analysis can be used in predicting the critical defects influencing the structural reliability and operation safety, such as water leakage, and optimizing the construction and maintenance work for the shield subway tunnel.

The surface crack on track slab is the main cause of the service reliability deterioration of the high‐speed rail (HSR) slab track. To realize the rapid and accurate detection of these cracks, infrared thermography (IRT) can be regarded as an effective way in HSR application. However, the performance of IRT can be significantly affected by the testing environment. This study aims to analyze the feasibility of IRT in crack detection for HSR slab track by investigating the key factors affecting the detection accuracy. Firstly, the principle of IRT in detecting surface crack of track slab is given, and the key factors influencing the detection performance are discussed. Considering the difficulty in conducting field tests for slab tracks, this study establishes a finite element (FE) model to simulate the temperature field of track slab with surface cracks. This model is verified by using the field measurement results of track slab temperature. With the FE model, the effects of detection time, ambient temperature, and sensitivity of the thermal imager on the detection accuracy are revealed. The results show that, during the window time for track maintenance (0:00 am–3:00 am), the difference of temperature between crack areas and noncrack areas gradually increases with time, so it is recommended to conduct detection during 2:00–3:00 am; under the condition of no auxiliary heat source, the crack detection is suggested to be arranged in summer with a high incidence of crack; the minimum limit of thermal sensitivity of thermal imager is below 108mk@25°C. The findings in this research can offer guidance for the implementation of IRT‐based crack detection for HSR slab crack.