Explore the vast range of titles available.

With the booming development of the rail transit industry and the increase in the construction and operation of mileage, the health status of infrastructure such as vehicles, tracks, and trains, as well as operational safety, have received widespread attention. Distributed optical fiber sensing technology has the characteristics of long monitoring distance, strong real-time performance, and highly economical, and has broad prospects in rail transit applications. This paper adopts Distributed Acoustic Sensing technology to obtain vibration information along the subway tunnel, analyzes the time-domain signal and frequency-domain energy characteristics of train vibration, as well as the passing time, direction, and location of the train, providing technical support for the safe operation of the subway.

Cracks are an important indicator reflecting the safety status of infrastructures. This paper presents an automatic crack detection and classification methodology for subway tunnel safety monitoring. With the application of high-speed complementary metal-oxide-semiconductor (CMOS) industrial cameras, the tunnel surface can be captured and stored in digital images. In a next step, the local dark regions with potential crack defects are segmented from the original gray-scale images by utilizing morphological image processing techniques and thresholding operations. In the feature extraction process, we present a distance histogram based shape descriptor that effectively describes the spatial shape difference between cracks and other irrelevant objects. Along with other features, the classification results successfully remove over 90% misidentified objects. Also, compared with the original gray-scale images, over 90% of the crack length is preserved in the last output binary images. The proposed approach was tested on the safety monitoring for Beijing Subway Line 1. The experimental results revealed the rules of parameter settings and also proved that the proposed approach is effective and efficient for automatic crack detection and classification.

The most serious fire scene in a subway system is that a train catching on fire has to stop in the tunnel. The objective of this paper is to discuss safety evacuation of this scenario. A subway tunnel in Beijing was selecting as research object, and adopting numerical simulation methods to analyze smoke propagation in the tunnel and train carriage. In addition, the influence of train carriage door opening on the smoke spread was studied in the double narrow space formed by the carriage and tunnel. Results show that the opening method of door would affect the smoke spreading path, and the range of high temperature area. For a fire occurred in train carriage, opening of the end door of train can effectively enhance diffusion of smoke into the tunnel. This research is not only helpful to guide the cabin crew to evacuate efficiently and orderly, but also provide guidance for the planning of subway tunnels.

In complex underground conditions, the excavation of deep foundation pits has a significant impact on the deformation of retaining structures and nearby subway stations. To investigate the influence of deep excavation on the deformation of adjacent structures, a three-dimensional numerical model of the foundation pit, existing subway station, and tunnel structure was established using FLAC 3D software, based on the Shenzhen Bay Super Headquarters C Tower foundation pit project. The study analyzed the deformation characteristics of retaining structures, adjacent subway stations, and tunnels during different stages of deep excavation, and the accuracy of the numerical simulation results was validated through field monitoring data. The results indicate that during the excavation process of the foundation pit, the lateral horizontal displacement of the retaining structure is generally small, with a typical “concave inward” lateral deformation curve; the horizontal displacement value of the contiguous wall section is less than that of the interlocking pile section. The bending moments of the retaining structure show a distribution pattern with larger values in the middle and smaller values at the top and bottom of the pit, with a relatively uniform distribution of internal support forces. The maximum displacement of the nearby subway station is 8.75 mm, and the maximum displacement of the subway tunnel is 2.29 mm. The research findings can provide references for evaluating the impact of newly built foundation pits near subway stations and contribute to the rational design and safe construction of new projects.

Monitoring and predicting ground settlement during tunnel construction is of paramount importance for ensuring the safety of tunnel construction and the stability of the surrounding environment. Existing studies on settlement prediction mainly rely on single settlement values and often overlook temporal characteristics, and that prediction models struggle to capture the nonlinear trends in actual settlements, leading to suboptimal predictive accuracy. In this study, based on the monitoring data of settlement deformation in a subway section of a certain city, a multi-factor-driven prediction method for surface settlement in subway tunnel excavation using the Informer model is proposed. The predictive accuracy is compared and analyzed with other models, including CNN-LSTM, LSTM, SARIMA, and Transformer. The results indicate that: (1) The Informer model outperforms CNN-LSTM, LSTM, SARIMA, and Transformer in terms of RMSE, MAE, and MAPE evaluation metrics, demonstrating that the Informer model exhibits smaller average prediction errors in forecasting surface settlement during subway construction. (2) Compared to LSTM, CNN-LSTM, Transformer, and other models, the Informer model can better capture the temporal characteristics and long-term forecasting ability of settlement data, while the SARIMA model fails to capture the temporal features in actual settlement data effectively. (3) Considering the influencing factors of temperature and soil pressure has a positive impact on the predictive performance of the Informer model, and the relationship between soil pressure information in the case study construction area and surface settlement is more closely associated. In summary, the Informer model, which takes into account temporal characteristics and multiple influencing factors, demonstrates good predictive ability for nonlinear settlement data. It provides a new method for analyzing settlement trends caused by subway tunnel excavation under complex environmental conditions, facilitating efficient and accurate assessment. It also offers objective data support for short-term bridge construction scheduling and long-term construction planning.

Distresses, such as cracks, directly reflect the structural integrity of subway tunnels. Therefore, the detection of subway tunnel distress is an essential task in tunnel structure maintenance. This paper presents the performance improvement of deep learning-based distress detection to support the maintenance of subway tunnels through a new data augmentation method, selective image cropping and patching (SICAP). Specifically, we generate effective data for training the distress detection model by focusing on the distressed regions via SICAP. After the data augmentation, we train a distress detection model using the expanded training data. The new image generated based on SICAP does not change the pixel values of the original image. Thus, there is little loss of information, and the generated images are effective in constructing a robust model for various subway tunnel lines. We conducted experiments with some comparative methods. The experimental results show that the detection performance can be improved by our data augmentation.

Some cities’ subways were constructed early and have been in operation for a long time. A large amount of heat accumulates in the rocks around the subway tunnels, causing the phenomenon of heat accumulation. This situation leads to the inadequate cooling capability of train air-conditioning systems, which, may even cease to function under extreme conditions. Currently, few solutions are available to address this issue. Therefore, this study proposes a new cooling system in subway tunnel. Considering the dusty environment inside the tunnel, the terminal equipment mainly consists of natural convection copper tube finless heat exchangers and a self-flushing device without fans, which cool using piston wind. By comparing field measurements of two tunnels with and without the cooling system in similar locations, the results show that the air temperature in the tunnels is reduced after the cooling system is installed. The results indicate that the average temperature in the tunnels decreases from 30.93 °C to 19.80 °C, marking a reduction of 11.13 °C after the cooling system runs for 24 hours. The temperature change in the tunnel is a long-term process, and actual measurements require significant time consumption. In this study, the long-term effect is predicted using CFD simulation in tunnels. The accuracy and credibility of the CFD simulation have been confirmed through its reasonable agreement with experimental data, with the final temperature after 24 hours achieving a relative error of less than 0.26%. Through the simulation, the temperature at a depth of 10 cm inside the tunnel wall after 24 hours is determined to be 27.56 °C, indicating a reduction of 3.44 °C compared to the initial temperature of 31 °C. This study can provide a reference for other subway tunnel cooling systems and serves as a basis for CFD simulations to verify cooling effects.

The construction of a new generation of smart cities puts forward higher requirements for the digitization and intelligence of subway tunnel engineering. Digital twin technology has shown great potential in high-fidelity modeling, virtual–real mapping, and decision support based on data analysis, but its research is still in its infancy. To this end, this paper first discusses in depth the inherent complexity and safety risks of subway tunnel construction and emphasizes the significant advantages of digital twin technology compared with traditional technology. Then, by summarizing the existing concepts, this paper proposes a specific explanation of DT applicable to subway tunnel engineering. In order to deeply analyze the potential of digital twin technology in subway tunnel engineering, this paper first conducts a bibliometric analysis and organizes the relevant research directions in recent years based on a visual map. Then, the application of DT in the field of subway tunnel engineering is discussed, including the modeling method of the subway digital twin, intelligent management of the construction process, safety guarantee, operation and maintenance, and resource optimization of traffic facilities in subway stations. Finally, this paper discusses the prospects and gaps of digital twin technology in theoretical and practical applications, aiming to promote the practical application of this technology in subway tunnel engineering. Through the summary and prospect of the existing research, this paper provides a valuable reference for future research directions and practical applications.

In the realm of subway shield tunnel operations, the impact of tunnel settlement on the operational performance of subway vehicles is a crucial concern. This study introduces an advanced analytical model to investigate rail geometric deformations caused by settlement within a vehicle-track-tunnel coupled system. The model integrates the geometric deformations of the track, attributed to settlement, as track irregularities. A novel “cyclic model” algorithm was employed to enhance computational efficiency without compromising on precision, a claim that was rigorously validated. The model’s capability extends to analyzing the time-history responses of vehicles traversing settlement-affected areas. The research primarily focuses on how settlement wavelength, amplitude, and vehicle speed influence operational performance. Key findings indicate that an increase in settlement wavelength can improve vehicle performance, whereas a rise in amplitude can degrade it. The study also establishes settlement thresholds, based on vehicle operation comfort and safety. These insights are pivotal for maintaining and enhancing the safety and efficiency of subway systems, providing a valuable framework for urban infrastructure management and long-term maintenance strategies in metropolitan transit systems.

In this paper, we present a novel defect detection model based on an improved U-Net architecture. As a semantic segmentation task, the defect detection task has the problems of background–foreground imbalance, multi-scale targets, and feature similarity between the background and defects in the real-world data. Conventionally, general convolutional neural network (CNN)-based networks mainly focus on natural image tasks, which are insensitive to the problems in our task. The proposed method has a network design for multi-scale segmentation based on the U-Net architecture including an atrous spatial pyramid pooling (ASPP) module and an inception module, and can detect various types of defects compared to conventional simple CNN-based methods. Through the experiments using a real-world subway tunnel image dataset, the proposed method showed a better performance than that of general semantic segmentation including state-of-the-art methods. Additionally, we showed that our method can achieve excellent detection balance among multi-scale defects.