Jianfeng Gu

The temperature field characteristics of highway tunnels during fire conditions are investigated in this paper. Numerical simulations coupled with reduced-scale physical model tests were conducted to analyze the thermal characteristics of the tunnel interior and lining structure under various ventilation conditions. Taking the extra-long double-tube highway tunnel as a case study, a numerical model was established using FLUENT to simulate a 100 MW fire under different longitudinal ventilation velocities. Furthermore, a reduced-scale physical model with a geometric similarity ratio of 1:2.7 was fabricated to investigate the effect of lining moisture content on the heat transfer characteristics. It is indicated by the results that high-temperature zones above 800 °C are mainly concentrated within roughly 100 m of the fire source, extending approximately 20 m upstream and 80 m downstream. As the ventilation velocity rises, the high-temperature zone adjacent to the fire source is gradually reduced, the upstream smoke backflow length is shortened, and the downstream thermal influence range is expanded. Obvious spatial variations are observed in the cross-sectional temperature distribution: relatively uniform temperatures are found near the fire source, whereas higher temperatures are observed at the crown in upstream and downstream sections, followed by the haunch and sidewalls. A pronounced thermal lag effect is observed in the lining structure, with both slower heating rates and lower peak temperatures being exhibited at larger distances from the fire source and in linings with higher moisture content. A temperature plateau at around 100 °C is detected, which is mainly attributed to latent heat absorption during moisture evaporation. A more significant temperature gradient through the lining thickness is also caused by a higher moisture content. These findings provide valuable references for tunnel fire safety design, smoke control strategies, and evacuation safety analysis.

The construction of new tunnels underneath existing metro lines imposes critical challenges in accurately measuring and forecasting differential settlements, particularly in complex geological and structural settings. This study presents a hybrid measurement and forecasting framework that synergizes sparse strain monitoring with intelligent algorithms to address this issue. The proposed methodology first tackles the inverse problem of full‐line displacement field identification from limited strain gauge data by leveraging a mechanical model derived from the conjugate beam theory. Subsequently, a radial basis function neural network establishes a dynamic correlation between key construction parameters and the identified structural deformations, thereby enabling stage‐wise forecasting of displacement evolution under predefined construction schemes. The proposed framework is validated through controlled numerical simulations and scaled laboratory tests based on the engineering background of Chengdu Metro Line X . Results demonstrate that the method achieves a maximum identification error of 5% for displacement field reconstruction and a maximum prediction error of 7.5% for future displacement trends. The study provides a methodological framework that lays the foundation for proactive risk management in adjacent tunneling projects, enhancing the safety control capabilities under both static and dynamic loading conditions.

For the purpose of ensuring the construction safety of tunnel excavation, it is necessary to adopt a suitable pre-support technology to reinforce the surrounding rock. The pipe roof reinforcement method and the leading ductule method are the most commonly used and classical technologies during tunnel construction. This paper adopts the Huashan tunnel and the Xianglianshan tunnel as the engineering background, the numerical simulation is established based on Midas/GTS to analyze the mechanical performance of the pre-supports formed by the two methods during excavation, then the obtained results, such as stress, deformation, plastic zone, and settlement, are analyzed and discussed. The analysis and discussion illustrate that, during excavation, compared to the leading ductule reinforcement method, the pipe roof reinforcement method can effectively control the vault settlement and improve the stress state of the lining structure, as well as prevent the stress release from the surrounding rock. Thus, the pipe roof reinforcement method shows better reinforcement effectiveness and ensures construction safety.

Accurately structural damage identification remains a significant challenge due to dynamic response fluctuations caused by temperature variations. To address this problem, a novel two-stage damage identification method based on Multi-head Convolutional Neural Network (MCNN) and Improved Beluga Whale Optimization Algorithm (IBWO) is proposed to precisely predict temperatures, localize the damage, and quantify damage severity. First, the MCNN is exploited to forecast the ambient temperature and detect the number of damaged locations. The predicted values are then fed into an iterative optimization process of the IBWO to identify the damage location and severity. Finally, numerical models of simply supported beams and a 3-storey bookshelf structure are employed to verify the effectiveness and robustness of this method under measurement noises. Results demonstrate that the two-stage diagnosis method can accurately identify both single and multiple damages under varying ambient temperatures. The comparison study with two other state-of-the-art methods also demonstrates the superior performance of the two-stage method in damage localization and quantification.

During the operation of fabricated small box girder bridges, which face safety issues such as structural degradation and failure, there is an urgent need to propose a safety evaluation method to cope with the possible risks. This article quantitatively evaluates the safety state of a fabricated small box girder bridge in Wuhan City based on Fuzzy Analytic Hierarchy Process (FAHP) and structural health monitoring (SHM) data. Firstly, the FAHP model is established, and stress, deformation, and temperature are selected as evaluation factors. The safety thresholds of stress and deformation are determined by combining the industry specifications and the historical statistical patterns of the massive SHM data. The temperature field of the bridge is simulated and analyzed by combining ANSYS, HYPERMESH, and TAITHREM, and the most unfavorable temperature gradient is determined as a threshold for the safety evaluation. Finally, the scores of indexes of the bridge are determined based on the measured SHM data, which in turn provides a quantitative description of the safety state. The results show that the thresholds determined by the joint industry specifications and the massive SHM data are reasonable; the temperature field simulation model established in this article is consistent with the measured results, and can accurately determine the temperature gradient of the bridge. The safety evaluation result from the FAHP model is the same as the field test results, which verifies the effectiveness and applicability of the proposed method to actual bridge projects.

This study proposes a novel method to identify structural damage considering ambient temperature variations. In this method, the normalized modal flexibility based index (nMFBI) and autoregressive (AR) coefficients are combined to form the nMFBI-AR hybrid index, and convolutional neural networks (CNN) are exploited to locate and quantify the damage. Moreover, the effects of ambient temperature variations and measurement noise are not considered in the training dataset, which is preferable in practical engineering. To verify the effectiveness of the proposed method, firstly, a numerical structure of a simply supported beam is investigated, and the performance of the nMFBI-AR index is evaluated by making a comparison with the nMFBI and AR indexes. Then, the proposed method is further verified by a test model of a three-story frame and a practical engineering example of a continuous rigid frame bridge. The results demonstrate that although the influence of ambient temperature variations and measurement noise are only considered in the test datasets, this approach has the best performance in locating and quantifying structural damage, and the errors are less than 16%, which is promising. In addition, this paper provides a guideline and a new idea for the study of damage index based on time-frequency hybrid information.

The accuracy of vibration-based structural damage identification is affected by uncertainties in vibration measurements and finite element modeling. Moreover, a sufficient number of sensor measurements are not practical in large-scale structures. In this regard, the frequency domain [frequencies and mode shapes (FMS)] and time domain [acceleration cross-correlation function (ACCF)] indexes are put into a parallel convolutional neural network (P-CNN, a new convolutional neural network architecture with dual-channel) to locate and quantify structural damage. First, this approach is verified by a numerical model of a simply-supported beam, and the performance is evaluated by comparing it with methods using FMS and ACCF indexes input to the conventional 2D-CNN, respectively. The comparative results demonstrate that the proposed method can identify the damage with the lowest error, and the errors are less than 5%. In addition, three sparse measurement conditions are adopted to investigate the effect of the number of measuring points on damage identification. It is found that under the influence of uncertainties, even if only four sensors are used, this approach can identify damage accurately. Second, an engineering example of a continuous rigid frame bridge is adopted to validate the feasibility of the proposed method. The results show that when the number of sensors accounts for 65% and 47% of test sensors, respectively, it performs well in locating and quantifying structural damage. Therefore, this method can not only reduce the number of sensors and eliminate uncertainties effects, but also improve the performance of the 2D-CNN through information fusion and complementarity, which is also beneficial to minimize the cost of sensor layout in actual structures.

Accurate damage identification is of great significance to maintain timely and prevent structural failure. To accurately and quickly identify the structural damage, a novel two-stage approach based on convolutional neural networks (CNN) and an improved hunter–prey optimization algorithm (IHPO) is proposed. In the first stage, the cross-correlation-based damage localization index (CCBLI) is formulated using acceleration and is input into the CNN to locate structural damage. In the second stage, the IHPO algorithm is applied to optimize the objective function, and then the damage severity is quantified. A numerical model of the American Society of Civil Engineers (ASCE) benchmark frame structure and a test structure of a three-storey frame are adopted to verify the effectiveness of the proposed method. The results demonstrate that the proposed approach is effective in locating and quantifying structural damage precisely regardless of noise perturbations. In addition, the reliability of the proposed approach is evaluated using a comparison between it and approaches based on CNN or the IHPO algorithm alone. The comparison results indicate that in single and multiple damage events, the proposed two-stage damage identification approach outperforms the other two approaches on the accuracy, and the average consumption time is 20% less than the method using the IHPO algorithm alone. Therefore, this paper provides a guideline for the study of high-accuracy and quick damage identification using both data-based and model-based hybrid methods.