Due to sensor failure, noise interference and other factors, the data collected in the structural health monitoring (SHM) system will show a variety of abnormal patterns, which will bring great uncertainty to the structural safety assessment. This paper proposes an automatic data anomaly diagnosis method for SHM based on a multimodal deep neural network. In order to improve the detection accuracy, both two-dimensional and one-dimensional features of the sensor data are fused in the multimodal deep neural network. The network consists of two convolutional neural network (CNN) channels, one a 2D-CNN channel for extracting time–frequency features of sensor data and the other a 1D-CNN channel for extracting raw one-dimensional features of sensor data. After convolution and pooling operations for the sensor data by the 2D channel and 1D channel separately, the two types of extracted features are flattened into one-dimensional vectors and concatenated at the concatenation layer. The concatenated vector is then fed into fully connected layers for final SHM data anomaly classification. In order to evaluate the reliability of the proposed method, the monitored data lasting for one month of a long-span cable-stayed bridge were used for training, validation, and testing. Six types of training conditions (missing, minor, outlier, over-range oscillation, trend, and drift) are studied and analyzed to address the issue of imbalanced training data. With an accuracy rate of 95.10%, the optimal model demonstrates the effectiveness and capability of the proposed method. The proposed method shows a promising future as a reliable AI-assisted digital tool for safety assessment in structural health monitoring systems.

As an emerging construction method, the lateral launching technique for shield tunneling can ensure launching safety while significantly reducing disturbances to urban traffic. However, the influence of its design parameters on construction stability and economic performance has not yet been systematically investigated, thereby limiting its broader application in complex urban environments. To address this gap, this study proposes a comprehensive analytical framework integrating field monitoring, numerical modeling, orthogonal experiments, and regression-based optimization. Relying on a shield lateral launching project in a central urban district of Guangzhou, a systematic investigation is conducted. Field monitoring data are used to verify the reliability of the three-dimensional finite element model, confirming that deformations of both the retaining structures and the surrounding ground remain within a stable and controllable range. On this basis, the orthogonal experimental method is, for the first time, introduced into the parameter sensitivity analysis of the shield lateral launching technique. The analysis reveals the influence ranking of support parameters on surface settlement. Key parameters are then selected for optimization design according to the sensitivity order, followed by a comprehensive evaluation of deformation control effectiveness and economic performance of the optimized scheme. The results show that the deformation of both the retaining structures and the ground during construction remains below the control limits, indicating good structural stability. Among the supporting parameters, the sensitivity coefficients from high to low are the diaphragm wall thickness H_W, the grouting reinforcement range H_G, the initial support thickness of the lateral-shifting tunnel H₁, the initial support thickness of the advance launching tunnel H₂, and the elastic modulus of the diaphragm wall E_W. Based on the sensitivity ranking, the highly sensitive parameters are selected for optimization, and the optimal parameter combination is determined to be a diaphragm wall thickness of 1000 mm, a grouting reinforcement range of 1600 mm, and an initial support thickness of 100 mm for the lateral-shifting tunnel. This combination meets the safety requirements for surface settlement while effectively reducing material consumption and improving economic performance. The study provides technical and theoretical references for shield launching under complex conditions.

The double-sidewall guide pit method finds extensive application in the construction of large cross-section tunnels in soft rock strata due to its minimal disruption to the surrounding rock, thereby enhancing tunnel stability. To investigate the loading and deformation patterns of the surrounding rock and tunnel support using the double-sidewall guide pit method, this study compares the impacts of various construction sequences on surface settlement, surrounding rock stress, and lining stress using indoor model tests. The experimental results show that after excavating the upper guide hole on one side, the excavation of the lower guide hole on the same side is carried out. The upper and lower support structures form a closed loop, and the structure can better constrain the surrounding rock and control the deformation of the surrounding rock, whereas the lower structure can share the stresses suffered by the upper structure. Therefore, compared with the upper and lower excavation methods, the surface settlement caused by the left and right excavation methods is smaller, the disturbance to the surrounding rock is smaller, and the supporting structure is more evenly and stably stressed in the excavation process.

The rapid expansion of subway systems has led to significant carbon emissions during station construction, yet a systematic and interpretable framework for evaluating low-carbon performance across different construction methods remains underdeveloped. To address this gap, this study proposes a comprehensive evaluation model that integrates a pressure–state–response (PSR) framework with an entropy-weighted TOPSIS method. A multi-dimensional indicator system comprising 17 indicators was established, covering material and energy consumption (pressure), environmental carbon states (state), and management responses (response). The entropy weight method was employed to determine objective indicator weights, and the TOPSIS method was used to rank the overall low-carbon performance of different construction schemes. An empirical study of a subway station in Guangzhou, China, was conducted to compare three construction methods: open-cut, top-down cover excavation, and reverse cover excavation. The results demonstrate that the reverse cover excavation method achieves the highest low-carbon performance. Electricity consumption and concrete-related emissions were identified as the most influential factors, while obstacle analysis revealed key constraints for carbon reduction. The proposed PSR–entropy–TOPSIS framework offers a transparent, data-driven decision-support tool for optimizing construction schemes, contributing to the sustainable development goals of urban rail transit projects.

This study investigates the tri-objective optimization of underground metro station structures, considering structural reliability, life-cycle economic cost, and annualized carbon emissions simultaneously. Using a representative metro station in Guangzhou as a case study, a multi-objective optimization framework is developed. The model defines structural failure probability, discounted life-cycle cost, and average annual carbon emissions as the primary objectives, with decision variables including concrete strength, cover thickness, the use of epoxy-coated reinforcement, and various maintenance/repair strategies. Material quantities are calculated through Building Information Modeling (BIM), while cost–carbon relationships are derived from industry price data and carbon emission factors. An improved multi-objective particle swarm optimization algorithm (OMOPSO) is used to derive the Pareto-optimal front. Case study results show that increasing cover thickness significantly improves durability and reduces carbon emissions with only moderate cost increases. In contrast, epoxy-coated reinforcement is excluded from the Pareto set due to its high cost under the given conditions. To facilitate practical decision-making, a weight-based solution selection method is introduced, and sensitivity analyses are performed to assess the model’s robustness. The study concludes by emphasizing the framework’s applicability and limitations: the findings are specific to the case context and require recalibration for use in other sites or construction practices. This research contributes by integrating durability, cost, and carbon considerations into an engineering-level optimization workflow, providing valuable decision support for sustainable metro station design.

To investigate the strain patterns and shear failure mechanisms of concrete-filled steel tube (CFT) column-end-plate joints during construction, this study designed and fabricated a scaled model of a standard subway station section based on similarity theory. Model tests were conducted under static earth pressure loads, and a finite element model was constructed for comparative analysis. The study focused on the ultimate bearing capacity, failure modes, and force transmission mechanisms of the joint, and optimized the analysis using reinforcement parameters. The results showed significant stress concentrations at the joint corners and core, with shear forces gradually forming annular cracks in the top slab concrete. The bearing system formed by the steel tube column and flange was the primary force transmission mechanism, and even after damage, the steel tube could still effectively restrain the core concrete. Increasing the steel bar diameter and increasing the number of slab reinforcements parallel to the beam significantly improved the joint’s mechanical properties. Improving the material properties of the reinforcement increased the joint’s stress and displacement capacity. This research provides a reference for optimizing the design and construction of slab-column joints in subway stations.