Search Results (271)

The present investigation presents the field measurement and prediction of tunneling-induced surface ground settlement in Tianjin Metro Line 7, China. The cross-section of a metro tunnel exhibits circular symmetry, thereby making it suitable for tunneling with a circular shield machine. The ground surface may deform during the tunneling stage. In the early stage of tunneling, few measurement data can be collected. To obtain a better usable prediction model, two kinds of neural networks according to the model-agnostic meta-learning (MAML) scheme are presented. One kind of deep learning strategy is a combination of the Back-Propagation Neural Network (BPNN) and the MAML model, named MAML-BPNN. The other prediction model is a mixture of the MAML model and the Long Short-Term Memory (LSTM) model, named MAML-LSTM. Founded on several measurement datasets, the prediction models of the MAML-BPNN and MAML-LSTM are successfully trained. The results show the present models possess good prediction ability for tunneling-induced surface ground settlement. Based on the coefficient of determination, the prediction result using MAML-LSTM is superior to that of MAML-BPNN by 0.1. Full article

Urban socioeconomic modeling has predominantly concentrated on extensive location and neighborhood-based features, relying on the localized population footprint. However, networks in urban systems are common, and many urban modeling methods do not account for network-based effects. Additionally, network-based research has explored a multitude of data from urban landscapes. However, achieving a comprehensive understanding of urban mobility proves challenging without exhaustive datasets. In this study, we propose using commute information records from the census as a reliable and comprehensive source to construct mobility networks across cities. Leveraging deep learning architectures, we employ these commute networks across U.S. metro areas for socioeconomic modeling. We show that mobility network structures provide significant predictive performance without considering any node features. Consequently, we use mobility networks to present a supervised learning framework to model a city’s socioeconomic indicator directly, combining Graph Neural Network and Vanilla Neural Network models to learn all parameters in a single learning pipeline. In experiments in 12 major U.S. cities, the proposed model achieves considerable explanatory performance and is able to outperform previous conventional machine learning models based on extensive regional-level features. Providing researchers with methods to incorporate network effects in urban modeling, this work also informs stakeholders of wider network-based effects in urban policymaking and planning. Full article

With the rapid growth of urban populations and the expansion of metro networks, accurate energy consumption prediction has become a critical task for optimizing metro operations and supporting low-carbon city development. Traditional statistical and machine learning methods often struggle to model the complex, nonlinear, and time-varying nature of metro energy data. To address these challenges, this paper proposes MTMM, a novel hybrid model that integrates the multi-head attention mechanism of the Transformer with the efficient, state-space-based Mamba architecture. The Transformer effectively captures long-range temporal dependencies, while Mamba enhances inference speed and reduces complexity. Additionally, the model incorporates multivariate energy features, leveraging the correlations among different energy consumption types to improve predictive performance. Experimental results on real-world data from the Guangzhou Metro demonstrate that MTMM significantly outperforms existing methods in terms of both MAE and MSE. The model also shows strong generalization ability across different prediction lengths and time step configurations, offering a promising solution for intelligent energy management in metro systems. Full article

Establishing a high-precision passenger flow prediction model is a critical and complex task for the optimization of urban rail transit systems. With the development of artificial intelligence technology, the data-driven technology has been widely studied in the intelligent transportation system. In this study, a neural network model based on the data-driven technology is established for the prediction of passenger flow in multiple urban rail transit stations to enable smart perception for optimizing urban railway transportation. The integration of network units with different specialities in the proposed model allows the network to capture passenger flow data, temporal correlation, spatial correlation, and spatiotemporal correlation with the dual attention mechanism, further improving the prediction accuracy. Experiments based on the actual passenger flow data of Beijing Metro Line 13 are conducted to compare the prediction performance of the proposed data-driven model with the other baseline models. The experimental results demonstrate that the proposed prediction model achieves lower MAE and RMSE in passenger flow prediction, and its fitted curve more closely aligns with the actual passenger flow data. This demonstrates the model’s practical potential to enhance intelligent transportation system management through more accurate passenger flow forecasting. Full article

Urban tourism has experienced significant growth driven by platforms such as Airbnb, yet the relationship between short-term rental (STR) location and guest mobility remains underexplored. In this study, a structured survey of STR guests in Madrid during 2024 was administered face-to-face through property managers and luggage-storage services to examine factors influencing public transport (PT) use. Responses on bus and metro usage were combined into a three-level ordinal variable and modeled using ordered logistic regression against tourist demographics, trip characteristics, and accommodation attributes, including geocoded location zones. The results indicate that first-time and international visitors are less likely to use PT at high levels, while tourists visiting more points of interest and those who rated PT importance highly when choosing accommodation are significantly more frequent users. Accommodation in the central almond or periphery correlates positively with higher PT use compared to the city center. Distances to transit stops were not significant predictors, reflecting overall network accessibility. These findings suggest that enhancing PT connectivity in peripheral areas could support the spatial dispersion of tourism benefits and improve sustainable mobility for STR guests. Full article

The rapid expansion of the urban rail network has increased concerns regarding stray current generated by the DC traction power supply system. This stray current, which arises from inadequate insulation between the rail and the ground, can cause electrochemical corrosion and operational challenges to nearby buried metallic infrastructures. A portion of stray current entering utility transformers may induce DC bias risk, thereby affecting the stability and reliability of distribution networks. This review studies the trends in utility transformer-related DC bias caused by metro stray current. Various modeling approaches and suppression measures are discussed, with an emphasis on comprehensively understanding stray current distribution behavior, the DC bias coupling loop, and its impacts. This review underscores the need for a thorough evaluation of existing DC bias suppression measures, and more effective and efficient measures must be developed to enhance the resilience of distribution networks. The gaps in current research are highlighted, and further studies are advocated, particularly those focusing on dynamic metro conditions, supported by advanced modeling, field applications, and interdisciplinary collaboration, to address the challenges of DC bias in urban rail environments. Full article

With the rapid expansion of railway networks and increasing operational complexity, intelligent rail damage detection has become crucial for ensuring safety and improving maintenance efficiency. Traditional physical inspection methods (e.g., ultrasonic testing, magnetic flux leakage) are limited in terms of efficiency and environmental adaptability. This study proposes a machine vision-based approach leveraging deep learning to identify four primary types of rail damages: corrugations, spalls, cracks, and scratches. A self-developed acquisition device collected 298 field images from the Chongqing Metro system, which were expanded into 1556 samples through data augmentation techniques (including rotation, translation, shearing, and mirroring). This study systematically evaluated three object detection models—YOLOv8, SSD, and Faster R-CNN—in terms of detection accuracy (mAP), missed detection rate (mAR), and training efficiency. The results indicate that YOLOv8 outperformed the other models, achieving an mAP of 0.79, an mAR of 0.69, and a shortest training time of 0.28 h. To further enhance performance, this study integrated the Multi-Head Self-Attention (MHSA) module into YOLO, creating MHSA-YOLOv8. The optimized model achieved a significant improvement in mAP by 10% (to 0.89), increased mAR by 20%, and reduced training time by 50% (to 0.14 h). These findings demonstrate the effectiveness of MHSA-YOLO for accurate and efficient rail damage detection in complex environments, offering a robust solution for intelligent railway maintenance. Full article

The paper aims to provide a flood prediction system in the Philippines to increase flood awareness, which may help reduce property damage and save lives. Real-time flood status can significantly increase community awareness and preparedness. A flood model will simulate the flood level with secured data flow from the sensor to the cloud. The algorithms embedded in the flood predicting model include fuzzy logic, LSTM neural network, and genetic algorithm. The project used the Infineon security module (Infineon Technologies Philippines Inc., Metro Manila, Philippines) to create a secure connection from the setup to the AWS. All data transmitted were encrypted when being sent to AWS IoT Core, Timestream, and Grafana. After training and testing, the neuro-fuzzy LSTM network with genetic algorithm solution showed improved flood prediction accuracy of 92.91% compared to the ADAM solver that predicts every 2 h using an 0.02 initial learning rate, 1000 LSTM hidden layers, and 1000 epochs. The best solution predicts a flood every 3 h using an ADAM solver, a 0.01 initial learning rate, and 244 LSTM hidden layers for 158 epochs. Full article

During the cantilever casting construction process of continuous girder bridges, it is crucial to accurately predict the pre-camber of each cantilever segment to ensure smooth closure of the bridge, structural safety, and construction quality. However, traditional methods for predicting pre-camber have limited accuracy and primarily handle linear relationships. Therefore, this paper proposes a pre-camber prediction model based on a Convolutional-Bidirectional Long Short-Term Memory network with a fusion attention mechanism (CNN-BiLSTM-Attention) and utilizes the Dung Beetle Optimizer (DBO) algorithm to optimize the hyperparameters of the CNN-BiLSTM-Attention model to enhance its predictive performance. The research results indicate that compared to several other prediction models, the model proposed in this paper demonstrates superior performance in predicting the pre-camber of continuous girder bridges. Compared to other prediction models, the evaluation metrics MAE, RMSE, and MAPE of the model proposed in this paper are minimized to 2.76 mm, 3.47 mm, and 0.70%, respectively. Applying the model proposed in this paper to the cantilever casting stage of the elevated continuous girder bridges in Shenyang Metro, China, enables pre-camber prediction with an accuracy of an average absolute error of less than 2 mm, providing a new efficient method for pre-camber prediction in cantilever casting construction. Full article

The increasing disparity in global food distribution has amplified the urgency of addressing food waste and food insecurity, both of which exacerbate economic, environmental, and social inequalities. Traditional food bank models often struggle with logistical inefficiencies, limited accessibility, and a lack of transparency in food distribution, hindering their effectiveness in mitigating these challenges. This study proposes a novel Food Bank Network Redesign (FBNR) that leverages the Quito Metro system to create a decentralized food bank network, enhancing efficiency and equity in food redistribution by introducing strategically positioned donation lockers at metro stations for convenient drop-offs, with donations transported using spare metro capacity to designated stations for collection by charities, reducing reliance on dedicated transportation. To ensure transparency and operational efficiency, we integrate a blockchain-based traceability system with smart contracts, enabling secure, real-time tracking of donations to enhance stakeholder trust, prevent food loss, and ensure regulatory compliance. We develop a multi-objective optimization framework that balances food waste reduction, transportation cost minimization, and social impact maximization, supported by a mixed-integer linear programming (MIP) model to optimize donation allocation based on urban demand patterns. By combining decentralized logistics, blockchain-enhanced traceability, and advanced optimization techniques, this study offers a scalable and adaptable framework for urban food redistribution, improving food security in Quito while providing a replicable blueprint for cities worldwide seeking to implement circular and climate-resilient food supply chains. Full article

Predicting pit deformation to prevent safety accidents is the primary objective of pit deformation forecasting. A reliable predictive model enhances the ability to accurately monitor future deformation trends in pits. To enhance the prediction of pit deformation and improve accuracy and precision, an Improved Crown Porcupine Optimization Algorithm (ICPO) based on a Bidirectional Time Convolution Network–Bidirectional Gated Recirculation Unit (BITCN-BIGRU) is developed. This model is utilized to forecast the future deformation trends of the pit. Utilizing site data from a metro station pit project in Chengdu, the accuracy of the predicted values from Historical Average (HA), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models is evaluated against the six models developed in this study, including the ICPO-BITCN-BIGRU model. Comparison of the test results indicates that the ICPO-BITCN-BIGRU prediction model exhibits superior predictive performance. The predicted values from the ICPO-BITCN-BIGRU model demonstrate R² values of 0.9768, 0.9238, and 0.9943, respectively, indicating strong concordance with the actual values. Consequently, the ICPO-BITCN-BIGRU prediction model developed in this study exhibits high prediction accuracy and robust stability, making it suitable for practical engineering applications. Full article

This study departs from conventional stochastic statistical approaches for rock mass structural modeling. Based on deterministic structural surface parameters, including orientation (dip and dip direction), trace length, trace center coordinates, and spacing between structural surface sets, this research investigates the relationships among volumetric density, areal density, structural surface persistence, and inter-set spacing. With a focus on model domain dimensions, positioning of the model center, and mitigation of boundary effects, the methodology systematically addresses key considerations in modeling joints, layers, and faults. A deterministic Discrete Fracture Network (DFN) modeling approach is proposed accordingly. In this framework, joints are represented by disks, whereas lithological interfaces such as layers and faults are modeled as flat planes. The proposed method was applied to the Qingdao Metro Line 15 project. Validation results demonstrate that the surrounding rock classification derived from the model is in good agreement with field geological investigation data. Full article

The rapid growth of urban metro systems requires novel strategies to guarantee operational dependability and energy efficiency. This article describes a new way to use deep reinforcement learning (DRL) to help metro networks with predictive maintenance that adapts to changing conditions and energy optimization. We used real-world transit data from the General Transit Feed Specification (GTFS) to model the maintenance scheduling and energy management problem as a Markov Decision Process. This included important operational metrics like peak-hour demand, train arrival times, and station stop densities. A custom reinforcement learning environment mimics the changing conditions of metro operations. Deep Q-Networks (DQNs) and Proximal Policy Optimization (PPO) sophisticated deep reinforcement learning techniques were used to identify the optimal policies for decreasing energy consumption and downtime. The PPO hyperparameters were additionally optimized using Bayesian optimization by implementing Optuna, which produces a far greater performance than baseline DQNs and basic PPO. Comparative tests showed that our improved DRL-based method improves the accuracy of predictive maintenance and the efficiency of energy use, which lowers operational costs and raises the dependability of the service. These results show that advanced learning and optimization techniques could be added to public transportation systems in cities. This could lead to more sustainable and smart transportation management in big cities. Full article

The construction of subways exacerbates the non-uniformity of surface deformation, which in turn poses a potential threat to the safe construction and stable operation of urban rail transit systems. Beijing, the city with the most extensive subway network in China, has long been affected by land subsidence. Utilizing data from Envisat ASAR, Radarsat-2, and Sentinel-1 satellites, this study employs PS-InSAR technology to monitor and analyze land subsidence within a 2 km buffer zone along Beijing Metro Line 22 over a span of 20 years (from January 2004 to November 2024). The results indicate that land subsidence at Guanzhuang Station and Yanjiao Station along Metro Line 22 is particularly pronounced, forming two distinct subsidence zones. After 2016, the overall rate of subsidence along the subway line began to stabilize, with noticeable ground rebound emerging around 2020. This study further reveals a strong correlation between land subsidence and confined groundwater levels, while geological structures and building construction also exert a significant influence on subsidence development. These findings provide a crucial scientific foundation for the formulation of effective prevention and mitigation strategies for land subsidence along urban rail transit lines. Full article

As urban rail transit networks age, understanding the synergistic impacts of multi-defect interactions on tunnel structural safety has become critical for underground infrastructure maintenance. This study investigates defect interaction mechanisms in shield tunnels and cross passages of Beijing Metro Line 8, integrating field monitoring, numerical simulations, and Bayesian network analysis. Long-term field surveys identified spatiotemporal coupling characteristics of four key defects—lining leakage, structural voids, material deterioration, and deformation—while revealing typical defect propagation patterns such as localized leakage at track beds and drainage pipe-induced voids. A 3D fluid–solid coupling numerical model simulated multi-defect interactions, demonstrating that defect clusters in structurally vulnerable zones (e.g., pump rooms) significantly altered pore pressure distribution and intensified displacement, whereas void expansion exacerbated lining uplift and asymmetric ground settlement. Stress concentrations were notably amplified at tunnel–cross passage interfaces. The Bayesian network risk model further validated the dominant roles of defect volume and burial depth in controlling structural safety. Results highlight an inverse correlation between defect severity and structural integrity. Based on these findings, a coordinated maintenance framework combining priority monitoring of high-stress interfaces with targeted grouting treatments is proposed, offering a systematic approach to multi-defect risk management that bridges theoretical models with practical engineering solutions. Full article