Temperature is a significant load on bridges, particularly for long-span steel box girder bridges. This study investigates the temperature-induced static r

Temperature is an important load factor affecting the structural performances of bridges. The rapid acquisition of bridge temperature data is significant for bridge temperature effect analysis and assessment. On the bases of ground meteorological shared big data, a bridge temperature prediction method based on long short-term memory (LSTM) neural network is proposed. The proposed method is used to investigate the key issues of data preprocessing, model input feature selection, time-length determination, and hyper-parameter preference. Moreover, the proposed method relies on the maximum information coefficient to quantify the strongly correlated features and uses a two-layer deep LSTM neural network to improve the model’s time series information utilization and prediction capability. The constructed neural grid model is experimentally studied and verified based on the long-term measured data of the scaled bridge model in an outdoor environment. Comparative assessment with other typical time series models, such as NARX, RNN, and GRU, demonstrate that the LSTM neural network model exhibits the best generalization ability and highest temperature prediction accuracy, with a maximum absolute error of approximately 2°C and relative error below 5%. The engineering applicability and effectiveness of LSTM for bridge temperature prediction are verified.

The heat exchange between bridges and external environments is the primary cause of the temperature effect on bridges. The complexity of the two-phase (gas–solid) heat transfer mechanism, the diversity of the surface characteristics of bridge materials, and the uncertainties of the environment in which bridges are located make the numerical calculation of the heat exchange between bridges and external environments difficult. Several studies have been conducted by scholars around the world. In this work, the research on convective and radiative heat exchange between bridges and external environments is surveyed, analyzed, and summarized. The influencing factors and calculation methods of bridge temperature are examined, and the convective heat transfer and radiation mechanisms, theoretical calculations, and experimental measurement methods used to investigate the relation between bridges and external environments are summarized and analyzed. The value determination methods for convective heat transfer and radiation absorption coefficients in the calculation of the bridge temperature field are summarized. In addition, the problems and shortcomings of current research are evaluated, and future research directions are identified and discussed.

Engineering residue soil, a prominent type of construction solid waste, can offer considerable environmental and socioeconomic benefits if efficiently utilized. Unburned brick represents an environmentally friendly and high-value approach to reusing this residue soil. Mud, a primary constituent of residue soil, typically hinders the performance of unburned brick using cement-based materials. This study investigates the effects of mud on the performance of unburned brick made from engineering residue soil based on experimental tests and mechanism analysis. The residue soil is silty clay sourced from the alluvial soil layer in South China. A comprehensive analysis of the physical and chemical properties of the residue soil and mud is conducted to assess the feasibility of using them in unburned brick production. Using ordinary Portland cement as the cementitious material, the unburned residue soil bricks are produced via semi-dry static-press forming and natural curing. The influence of mud type and content on the compressive strength of the unburned brick made with engineering residue soil is investigated and discussed. This experimental study reveals that the influence of mud on unburned brick’s compressive strength is negligible. However, excessively low mud content reduces brick compactness, impairs brick formation, and leads to lower compressive strength. Within the range of solidification, unburned brick’s compressive strength initially increases and then decreases with increasing mud content, with an optimal mud content of approximately 25%. As engineering residue soil often contains a high mud content, reducing it effectively enhances the compressive strength of unburned bricks. Through experiments and mechanism analysis, this research clarifies the impact of mud on the strength and performance of unburned residue soil bricks, providing important theoretical insights and practical guidance for the production of unburned products and promoting the efficient and environmentally friendly resource utilization of engineering residue soil.

Temperature is one of the critical environmental factors affecting bridges’ performance. Accurate temperature distribution is essential for reliable structural condition assessment. Existing studies have predominantly focused on the most adverse thermal conditions under clear skies, but seldom considered the cloudy or rainy conditions, which may not reflect the actual scenario of the bridges in real-time structural monitoring. This study develops a numerical method to calculate the bridge temperature distribution under all-weather conditions, including sunny, cloudy, rainy, and snowy scenarios. According to the illuminance and cloud cover, real-time solar radiation correction models are employed to quantify the shielding effect of clouds on solar radiation during cloudy or rainy weather. These models, combined with other meteorological parameters such as air temperature and wind speed, enable accurate determination of thermal boundary conditions for refined heat-transfer analysis. An automatic computational framework is strategically developed for weather scenario classification, boundary condition determination, and heat-transfer analysis. The proposed framework is applied to three scenarios: An experimental reinforced concrete slab, a practical steel box girder suspension bridge, and a real concrete box girder continuous bridge. Results demonstrate that the proposed correction models significantly enhance the heat-transfer analysis accuracy under various weather conditions. A good agreement has been achieved between simulated and measured temperatures across girder sections with different materials and geometries, thereby verifying the effectiveness of the proposed method. This study establishes a theoretical foundation and practical framework for investigating bridge temperature behaviors under complex weather conditions.