Installing vibration isolation walls on both sides of adjacent tunnels in suburban railways can sometimes worsen vibrations between the walls and the source of the vibrations. This study investigates how composite vibration isolation walls affect these vibrations. First, a detailed numerical model of the train-wheel interaction was developed and applied to a 3D track-soil system model, verified for accuracy. The study then explored how single-material vibration walls of different thicknesses amplify vibrations between the walls and the vibration source. It also examined how composite wall material composition and placement affect vibrations in this area. The results showed that using composite vibration walls instead of single-material walls (like EPS) reduced the increase in vibration acceleration and speed at measurement points above the two tunnels. The lowest amplification of peak acceleration at all points (except directly above the tunnel) occurred when C20 concrete was placed closer to the vibration source. For peak velocity, the lowest amplification was found in the central 20-m-wide area between the tunnels when the EPS material was closer to the vibration source. The least amplification of velocity at points directly above the tunnel occurred when C20 concrete was closer to the vibration source. In terms of frequency, choosing the right material ratio for composite vibration walls is essential, as an improper choice can increase the amplification effects.

This paper attempts to develop a systematic and theoretically consistent machine learning model to quantify and estimate multi-level railway passenger demand, capturing overall demand patterns. This includes estimating boarding and alighting passengers at stations along a corridor, origin–destination trips between stations, and passenger flows loaded onto train lines and corresponding train line segments. Observations are transformed into loss functions and mapped onto a hierarchical flow network to simultaneously estimate these multilayered demand variables. By incorporating a Nested Logit model into the hierarchical flow network, the learning model can further calibrate a series of interpretable parameters associated with key attributes in rail line planning (e.g., line frequency, fare levels, and travel time), enabling policy-sensitive analyses. Unlike pure discrete choice models, the proposed estimation model is constrained by line-based capacity constraints to prevent passenger flow overload on specific train lines and address inconsistencies between different observations. The nonlinear estimation model is reformulated as a computational graph and solved using backpropagation algorithms with off-the-shelf machine learning solvers (e.g., TensorFlow). To validate the applicability of our approach, we conduct a real-world case study on the Beijing–Shanghai high-speed rail corridor. The evolution of multiple loss functions in the case study demonstrates the accuracy and convergence of the method. Fourteen days of ticket sales data (10 days for training and 4 days for validation) are utilized to demonstrate the applicability of the proposed method.

Nonlinear ultrasonic frequency mixing exhibits high sensitivity and good localization capability for closed cracks. In this paper, nonlinear ultrasonic frequency mixing technology is used to investigate the contact acoustic nonlinearity phenomenon in turnout rails. The influence of different frequency mixing mode pairs and crack sizes on the frequency mixing signal is studied by selecting mode pairs suitable for detecting cracks at the rail bottom. The results indicate that the interaction between guided waves and the crack can generate frequency mixing signals. At the mixing frequencies, multiple guided wave modes will be produced, and the mixing signals increase significantly with the size of the cracks. This demonstrates the damage detection capability of nonlinear ultrasonic frequency mixing for closed cracks, providing a basis for damage detection in turnout rails.

Subway tunnels, with their complex underground environment, frequently develop surface defects like cracks and water leakage over time. Traditional manual inspection methods are inadequate for current accuracy and efficiency needs. This paper introduces a deep learning approach to detect and assess these defects in subway tunnels, aiming for real-time detection and quantitative assessment. It proposes a data collection strategy for rapid detection and detailed exploration in subway shield tunnels. A multi-category dataset of tunnel defects was created, alongside an automatic identification method using the YOLO v7 algorithm for operational tunnels. This method, validated against Qingdao Metro’s manual inspection records, markedly reduces manual inspection costs during tunnel operation. Research indicates a strong correlation between image inspection equipment efficiency, defect detection accuracy, and actual project needs in subway tunnels. Image quality is positively linked to tunnel illumination intensity. A balance between inspection speed and focal length is crucial for image size and precision. Lowering the confidence threshold from 0.4 to 0.2 increases detection rates for cracks and water leakage by 20.60 and 4.06%, respectively, minimizing defect oversight. This study presents algorithms, frameworks, and methods for real-time quantification to enhance tunnel operation, maintenance, and manual processing.

This paper focuses on dynamic marshalling cooperative optimization control of permanent magnetic maglev trains. The traditional distributed controller is difficult to adjust the control parameters adaptively for complex and changeable tracking scenarios, resulting in an unsafe, inefficient and uncomfortable marshalling process. This paper proposes a distributed active disturbance rejection resilient controller based on optimized twin delayed deterministic policy gradient (TD3) algorithm. First, an improved distributed active disturbance rejection controller (DADRC) based on the bidirectional leader communication topology is designed to realize the multi-train dynamic marshalling cooperative control and its stability is proved theoretically. Second, different dynamic marshalling processes are adaptively optimized by using the TD3 algorithm to train the DADRC. Third, an adaptive Mayfly (AMA) algorithm with the Steffensen mutation mechanism is proposed to optimize some sensitive hyperparameters of the TD3 algorithm. The simulation results show that compared with the traditional distributed controller, the proposed resilient controller can adaptively adjust its own control parameters and flexibly optimize the dynamic marshalling process according to different tracking scenarios. Compared with the Mayfly-TD3 (MA-TD3) and AMA-deep deterministic policy gradient algorithms, the proposed AMA-TD3 algorithm shows more stable and fast convergence, and can achieve a successful control rate as high as 99.8% and a generalization rate of up to 93.2%.

The high-speed railway (HSR) has become an important means of sustainable transportation, but most HSR lines are facing losses, especially China. Properly selling HSR flexible tickets has been verified to be an effective means to improve revenue. However, passengers’ choice behavior for flexible tickets directly determines whether revenue increases. There is no research identifying the factors influencing HSR flexible ticket choice to help operators appeal potential buyers and design popular flexible tickets. To fill this gap, this research conducted the stated preference survey and constructed the Integrated Choice and Latent Variables model to analyze the key factors that affect passengers’ purchase behavior toward HSR flexible tickets, including individual attributes, travel characteristics, scheme attributes, and potential factors. The results show that HSR flexible tickets are more attractive to passengers with higher education, longer travel distances, traveling alone, and traveling at their own expense, and those with lower perceived risk, higher environmental awareness, and higher technological interests. In addition, through data analysis, it is found that the fare, the earliest and latest departure time interval among the corresponding alternative trains, and the period in which the departure time interval is located will affect passengers’ willingness to purchase a flexible ticket as well as key elements in the design of the HSR flexible ticket. The study’s results can provide references for the design of HSR flexible tickets, suggestions for enhancing the passengers’ willingness to purchase flexible tickets, and choice behavior parameters for flexible ticket revenue management models.