Explore the vast range of titles available.

Gas pipeline leakages in urban underground utility tunnels pose a severe threat to public safety. Leakages of varying aperture sizes trigger differentiated risks of diffusion and explosion; thus, achieving precise identification of leakage hole size has become a critical issue in safety management. To address the difficulty of traditional methods in effectively separating the acoustic features of different leakage levels within complex utility tunnel environments, this paper proposes a gas pipeline leakage risk level identification method based on a lightweight Spatial-Temporal Graph Neural Network (ST-GNN). First, relying on a real utility tunnel simulation platform, acoustic signals under different pressures and leakage hole size are collected, and time-frequency magnitude features are constructed through Short-Time Fourier Transform (STFT). Furthermore, each acoustic sample is independently converted into a graph with STFT time frames as nodes, where temporal neighborhood edges and K-nearest neighbor edges jointly encode local dynamics and non-local spectral similarities. This transforms unstructured acoustic signals into graph-structured data that embodies spatial-temporal coupling relationships. Building upon this, a lightweight Chebyshev graph convolutional network is designed to progressively extract discriminative features strongly correlated with leakage levels using multi-layer convolution. Experimental results on the actual utility tunnel simulation platform dataset demonstrate that the proposed method achieves excellent performance in a three-level leakage classification task. The t-SNE visualization reveals the effective separation of features, progressing from complete mixing in the input layer to distinct separation in the output layer. Through multiple training statistics and ablation experiments, the impact of dataset size and the number of network layers on the identification performance is analyzed, validating the robustness of the proposed model under limited samples and the effectiveness of its lightweight structure. This provides a feasible solution for the automated and refined identification of gas pipeline leakage levels in underground utility tunnels.

This paper proposes a reliability-optimized localization method for underground utility tunnels based on multi-source fusion and a denoising variational autoencoder model. The method acquires a multi-sensor localization dataset aligned with a unified time reference. By employing a convolutional neural network-assisted denoising variational autoencoder (DVAE-CNN), it regulates localization outcomes through three key aspects: a multi-source heterogeneous data quality assessment model, a formulation of the target state transition equation, and an environmental prior-information-aided weight update strategy. This approach overcomes the low-reliability issues caused by information loss and errors in the complex environment of underground utility tunnels. Compared to localization results without reliability regulation mechanisms, the proposed method achieves an average improvement of 73.6% in localization accuracy and 85.2% in localization reliability. Finally, localization experiments conducted in an underground utility tunnel demonstrate that the proposed method can provide highly robust, reliable and continuous positioning services, indicating significant potential for application and broader adoption.

This research combines scaled model experiments with theoretical analysis to investigate the impact of underground utility tunnels (UUTs) on foundation bearing capacity and to examine the interaction between soil-rock composite strata and the stress-strain responses of the tunnel. The findings indicate that UUTs alter the foundation mechanism by reducing soil depth, streamlining the load transfer path, and causing stress to converge at the tunnel’s top. Additionally, the results reveal that the influence range of the tunnel on both sides is approximately 1.5 times its width and remains unaffected by the position of load application, the tunnel’s burial depth, or the width of the composite stratum. Moreover, when the width of the soil-rock composite stratum equals the width of the tunnel, the tunnel experiences a laterally flexural stress state. Within this specific stratum context, the central axis area of the tunnel roof and the connection with the side panels represent the core sensitive areas for crack initiation and propagation. In the failure scenario, the tunnel roof displays typical characteristics of fracture and depression, with the damage degree decreasing from the load center towards both ends. Meanwhile, the side panels do not exhibit characteristics of plastic deformation. This research provides a theoretical framework for the design, construction, and maintenance of UUTs, emphasizing its practical significance in engineering.

The “U-shaped ferrule joint bars connections” have a stable mechanical property, requiring a low level of construction accuracy and a relatively simple connection process, which significantly increase the construction speed. Based on the “U-shaped ferrule joint bars connections” technology, a new type of prefabricated concrete underground utility tunnel was proposed. This prefabricated technology realizes a formwork-free construction and vertical support-free assembly of the top plate on site. Through the full-scale model static test and numerical analyses, the mechanical properties, i.e., the crack development law and bearing capacity, were systematically investigated to validate the effectiveness of the “U-shaped ferrule joint bars connections”. The test results indicated that the performance of the “U-shaped ferrule joint bars connections” is reliable. During the loading process, the prefabricated utility tunnel experienced three stages, i.e., cracking, stiffness degradation, and ultimate failure. The numerical analysis results correlated with the test results well. The simulation results showed that the bearing capacities of the prefabricated underground utility tunnel and the cast-in-place utility tunnel were similar. The longitudinal joint connections of the prefabricated utility tunnel allow the structure as an integration to maintain favourable mechanical properties.

In the maintenance domain of the construction industry, digital twins have been actively introduced based on the technologies of the Fourth Industrial Revolution with growing interest in three-dimensional spatial information facility management and disaster response service using digital twin technology. In particular, disasters or abnormal situations in an underground utility tunnel (UTU) can cause serious casualties and property damage since key elements of a city such as power, communications, water supply, and heating facilities are collectively accommodated in a certain underground space. This study established the methodology for implementing an underground utility tunnel through a digital twin. The novelty of this study is demonstrating a sequential procedure of implementing digital twin technology by configuring major layers such as data acquisition, modeling, and service. This methodology can serve as reference material or a training aid for implementing a digital twin of underground facilities or underground utility tunnels in the future; the proposed methodology will be verified when an actual digital twin service is provided.

The increasing interest in digital twin technology, the digitalization of worn-out social overhead capital (SOC), and disaster management services has augmented the usage of 3D spatial models and information to manage infrastructure. In this study, a digital twin of a subterranean utility tunnel was created, and spatial objects were identified using inbuilt image sensors. The novelty lies in the development of a unique algorithm that breaks down the structure of the utility tunnel into points, lines, and planes, identifying objects using a multimodal image sensor that incorporates light detection and ranging (LiDAR) technology. The three main conclusions of this study are the following: First, a digital twin of the utility tunnel was constructed using building information modeling integrated with a geographic information system (BIM-GIS). Second, a method for extracting spatial objects was defined. Third, image-sensor-based segmentation and a random sample consensus (RANSAC) were applied. In this process, the supplementary algorithm for extracting and updating 3D spatial objects was analyzed and improved. The developed algorithm was tested using point cloud data, showing easier object classification with more precise LiDAR data.

The construction of traditional underground utility tunnels faces prominent challenges, including high costs, long construction cycles, and limited workspace. Although 3D printing technology offers an effective solution to these issues, its practical application is largely constrained by key performance factors such as the printability, early strength, and interlayer bonding of concrete materials. This study aims to develop a 3D-printable concrete material specifically suited for the construction of underground utility tunnels. Through collaborative optimization of parameters such as the water–binder ratio, additives, and fiber content using single-factor and orthogonal tests, the optimal mix proportion was determined: a water–binder ratio of 0.30, a 10% dosage of rapid-hardening sulphoaluminate cement (R·SAC), a sand-to-binder ratio of 1.0, 20% mineral admixtures (15% fly ash + 5% silica fume), and a 1.0% volume fraction of polypropylene fibers. The results indicate that the fresh paste achieved a flowability of 192 mm, demonstrating excellent printability. Specimens printed using a sawtooth toolpath reached a 3-day compressive strength of 37.8 MPa, with 28-day compressive and flexural strengths increasing to 56.3 MPa and 7.8 MPa, respectively, and an interlayer bond strength of 3.5 MPa. Crucially, the compressive and flexural anisotropy coefficients were as low as 0.023 and 0.066, respectively, showing a preliminary exploratory trend superior to levels reported in some literature and suggesting the potential of printed components to improve structural performance consistency. This material system not only meets the requirements of 3D printing for early strength and workability but also, by introducing R·SAC to form a low-alkalinity binder system, provides a potential pathway for enhancing long-term durability in corrosive environments. This study offers a reliable theoretical and experimental basis for the application of 3D printing technology in underground engineering. Long-term durability will remain a primary focus of subsequent research.

In hot and humid regions, urban underground utility tunnels are susceptible to high temperature and humidity due to moist inlet air, cable heat dissipation, and limited ventilation jointly affecting the internal environment. To address this issue, an alternating ventilation strategy, in which fan operation is periodically reversed to switch between air supply and exhaust, is proposed. Compared to conventional mechanical ventilation, this strategy overcomes the constraints of unidirectional airflow and mitigates thermal and humidity stratification, with low retrofit requirements and good adaptability. Ventilation performance was evaluated using non-guarantee rates for temperature and relative humidity, i.e., the ratio of the number of measurement points where the temperature/relative humidity exceeds 40 °C/65% to the total number of measurement points in the utility tunnel (TNGR and RHNGR), non-uniformity coefficients (KT and KRH), and mean temperature (Tm). The alternating mode outperformed the conventional mode, reducing TNGR by 6.0% and Tm by 0.3 °C while improving temperature and humidity distributions and lowering cable temperatures. Although the reduction in Tm appears modest, it is practically meaningful because it helps weaken thermal stratification and local overheating, improves cable operating conditions, and may reduce the need for high-airflow operation when tunnel temperatures approach the permissible limit. Response surface methodology was further used to optimize the alternating ventilation parameters, indicating that the recommended fan commutation frequency is 2 under different inlet air temperatures. CFD validation confirmed the effectiveness of the optimized scheme. At an inlet air temperature of 35 °C, KRH decreased from 11.9% to 11.0% and Tm decreased from 37.5 °C to 36.9 °C.

The defect detection in the urban underground utility tunnel faces the challenges of low illuminance and large shadow region. The images collected have problems such as noise and uneven illumination, posing higher requirements for the image feature extraction ability of the network model. A residual feature pyramid attention network based on dense connections (RFPADNet) is proposed in the defect detection of the urban underground comprehensive pipe in this paper. The proposed network consists of three dense blocks, and each dense block uses four residual feature pyramid attention models (RFPAM) as the main feature extractors. Its focus is to utilize residual learning to obtain the fused multi-scale feature information. Soft mask branches are added to the multi-scale channels to enhance the network model’s ability to extract positive features. The experimental results show that the network model proposed in this paper has a training accuracy of 97.50%. Compared with the existing network models, it could achieve better results in various test sets, which has good feasibility and practicality.

An underground utility tunnel (UUT) is essential for the efficient use of urban underground space. However, current maintenance systems rely on patrol personnel and professional equipment. This study explores industrial detection methods for identifying and monitoring natural gas leaks in UUTs. Via infrared thermal imaging gas experiments, data were acquired and a dataset established. To address the low-resolution problem of existing imaging devices, video super-resolution (VSR) was used to improve the data quality. Based on a convolutional recurrent neural network (CRNN), the image features at each moment were extracted, and the time series data were modeled to realize the risk-level classification mechanism based on the automatic classification of the leakage rate. The experimental results show that when the sliding window size was set to 10 frames, the classification accuracy of the CRNN was the highest, which could reach 0.98. This method improves early warning precision and response efficiency, offering practical technical support for UUT maintenance management.