During deep excavation, actual soil parameters undergo changes. To enhance the accuracy of soil parameter selection in finite element simulation and improve the precision of finite element analysis, an inversion method for soil parameters based on a PSO-SVM model is proposed. In this method, the particle swarm optimization (PSO) algorithm is utilized to optimize the penalty parameter C and kernel function parameter g of the support vector machine (SVM) model. The optimized PSO-SVM model is employed to establish a nonlinear mapping relationship between the horizontal displacements of retaining structures in deep excavations and soil parameters through orthogonal experimental design and finite element simulation analysis. Subsequently, soil parameters are inverted from monitoring data of horizontal displacements of retaining structures, and the reliability of the parameters is verified. The deformation of the retaining structures during subsequent cases is then predicted. The results demonstrate that the absolute error of the peak maximum horizontal displacements of the retaining structures after inversion is maintained within 1 mm. The maximum relative error is reduced from 18.96% before inversion to 7.63%, indicating that the inverted soil parameters for the deep excavation possess high accuracy. The precision of the finite element simulation for deep excavation is significantly improved, effectively reflecting the actual mechanical properties of the soil during the construction stage. The inverted parameters can be used for the prediction of subsequent retaining structure deformation. During subsequent construction conditions, the predicted maximum horizontal displacement (deformation) of the retaining structure at monitoring point CX1 is 15.66 mm, and that at monitoring point CX2 is predicted to be 14.22 mm. Neither value exceeds the project warning threshold of 30.00 mm.

Accurate finite element (FE) models are essential for the safety assessment of civil engineering structures. However, obtaining reliable model parameters for existing bridges remains challenging due to the inability to conduct static load tests without disrupting traffic flow. To address this, this study proposes an FE model updating framework that integrates the response surface method and the nutcracker optimization algorithm (NOA). This framework is characterized by the incorporation of ambient vibration data into parameter optimization, thereby enhancing model accuracy. The stochastic subspace identification method is first adopted to extract the bridge’s natural frequencies from vibration data. The response surface method is then employed to construct a response surface function that approximates the FE model. The NOA is subsequently applied to iteratively optimize this response surface function, ensuring rapid convergence and the precise adjustment of the FE model parameter. To validate the effectiveness of the proposed framework, a continuous beam–arch composite bridge with a span of 204.783 m was selected as a case study. The results indicate that the proposed method reduced the average frequency error from 5.58% to 2.75% by updating the model parameters. While the whale optimization algorithm required 21 iterations and the grey wolf optimizer needed 41 iterations to converge near the minimum, the NOA achieved this in merely 13 iterations, demonstrating the NOA’s superior convergence speed. Furthermore, the NOA significantly outperformed both the whale optimization algorithm and the grey wolf optimizer in reducing the error of the first transverse vibration frequency.

The temperature field distribution and temperature effects of concrete box girder bridges were found to be critical to their long-term service safety. Based on long-term structural health monitoring data, the temperature field and temperature effects of a curved continuous concrete box girder bridge in Wuhan were investigated. A finite element model of the temperature field was established through the combined application of finite element software. Extreme weather files were constructed to analyze the bridge’s temperature field and temperature effects. To enhance data reliability, wavelet analysis was employed for denoising the monitoring data. The results indicate a strong correlation between girder temperature and ambient temperature. Under solar radiation, significant vertical temperature differences and certain lateral temperature differences are observed within the concrete box girder. The accuracy of the finite element model was validated through comparison with measured data. Temperature field models featuring the most unfavorable vertical and transverse temperature gradient distribution patterns for concrete box girder bridges under extreme weather conditions in the Wuhan region were established. A distinct temperature difference not covered by specifications exists at the webs and bottom slabs of the bridge. Strong correlations were observed between both pier–girder relative displacement and bottom slab stress with the girder temperature.

Based on the up-floating incident of the basement in a high-rise residential building, the finite element (FE) model of the up-floating destruction region is established to investigate the damage mechanism. The stress states and the deformations of the basement structure are obtained under complex loads including water buoyancy forces, vehicle loads and construction loads. To assess the extent of damage, a novel damage indicator is defined based on two levels: the cracking bending moments and the yield bending moment. The first-level cracking bending moment, second-level cracking bending moment and the yield bending moment can be determined using the section stratification method. By comparing the maximum bending moment of the component with its corresponding cracking moment, one can determine whether the cracks have occurred and assess their severity. Meanwhile, the antifloating failure model is constructed to analyze the mechanism of the up-floating destruction. Finally, a detailed reinforcement treatment plan of ‘decompression first and then reinforcement’ is presented to reinforce and repair the damaged basement structure. The mechanism analysis of the up-floating destruction and the comprehensive reinforcement treatments ensure the simulation of the life cycle of emergence, development and treatment to ensure structural safety.

The residual stresses at U-rib joints have a significant adverse impact on the structure. Therefore, it is necessary to conduct research and analysis on their residual stresses. Based on experimental testing and thermal elastic-plastic finite element analysis (FEA), this study investigates the residual stress (RS) of a U-rib joint using gas metal arc welding in an orthotropic steel bridge deck (OSBD). X-ray diffraction (XRD) was adopted to measure the RS of the U-rib welds, and the measurement results were utilized to verify the FEA. The effects of the weld root gap, weld penetration, and weld groove angle on the RS of U-rib welds were investigated by using FEA. The weld root gap had minor effect on the RS of the U-rib welds. With an increase in weld penetration, the peak values of the transverse tensile RS at both the deck plate and the U-rib weld toes increased. Additionally, an enlargement of the groove angle also resulted in a notable increase in the transverse tensile RS peak at the deck plate weld toe.

During deep excavation construction, deformation impacts on adjacent structures are inevitably induced, and field monitoring data are often contaminated by noise that degrades prediction accuracy. To address these issues, this study develops a joint denoising strategy combining CEEMDAN, sample entropy-based adaptive IMF screening, and an improved wavelet threshold (IWT) function, followed by a Bayesian optimization-based extreme gradient boosting (BO-XGBoost) model for surface settlement prediction. The developed method automatically identifies high-noise IMF components via sample entropy and processes them using an improved threshold function that overcomes the discontinuity of hard thresholding and the constant bias of soft thresholding, thereby preserving useful information while suppressing noise. Experimental results on a Wuhan metro deep excavation project demonstrate that the CEEMDAN-IWT method improves SNR by up to 4.09% and reduces RMSE by up to 8.00% compared with conventional CEEMDAN-wavelet threshold denoising. The BO-XGBoost model trained on denoised data achieves an RMSE of 0.09 mm and a MAPE of 3.54%, outperforming BP, LSTM, standard XGBoost, GRU, CNN-LSTM, TCN, and simple regression baselines. Feature importance analysis confirms that the denoised data retain physical interpretability consistent with soil deformation continuity. This framework provides a practical solution with promising accuracy for deformation monitoring and early warning in deep excavation engineering.