Improving the accuracy of wind speed prediction is crucial for engineering applications and disaster warning due to the highly unstable and unpredictable nature of wind as an energy source. A wind speed prediction model (WT-CNN-LSTM) was constructed based on wavelet decomposition, long short-term memory network (LSTM), and convolutional neural network (CNN) to address the non-stationary characteristics of wind speed in mountainous areas. The wind speed sequence is decomposed into subsequence columns and tested for stationarity using an adaptive program. The data are then decomposed and reconstructed. A prediction model is established using CNN and LSTM. The final wind speed prediction value is obtained by overlaying the predicted values. The results indicated that compared with the WT-CNN and WT-LSTM models, the WT-CNN-LSTM combination model proposed in this paper reduced the MAE, MSE, and RMSE indicators by 0.10%–0.11%, 0.57%–0.63%, and 0.11%–0.13%, respectively. In addition, the adaptive program eliminates the need to rely on traditional manual empirical values to determine parameters, ensuring that the prediction results are not affected by changes in the number of hidden layer nodes. This information can serve as a reference for future mountainous engineering construction.

To make an accurate prediction of the non-Gaussian characteristics of wind pressure for the long-span roof, this study combines the proper orthogonal decomposition (POD) technique, convolutional neural network (CNN), and long short-term memory (LSTM) network to propose a novel POD-CNN-LSTM framework. Then, the proposed framework was well validated based on the wind tunnel testing of a long-span roof structure, and some error criteria, such as mean square root error and correlation coefficient, were adopted to evaluate the prediction accuracy of the non-Gaussian characteristics. Furthermore, two other methods, POD-CNN and POD-LSTM, were also used to conduct a comparative study. The obtained results illustrate that compared to POD-CNN and POD-LSTM, the proposed framework can achieve better performance on the pulsating wind pressure coefficient. For predictions of non-Gaussian characteristics, the output results of the proposed POD-CNN-LSTM show fewer errors, which means the predictions are close to the measured results, including skewness, kurtosis, and wind pressure probability density distributions. To summarize, the proposed POD-CNN-LSTM framework shows superiority over others, which means the proposed framework has good potential for the practical application of non-Gaussian prediction of the engineering structure.

In this paper, a neural network model combining wavelet decomposition and attention mechanism is proposed for the accurate prediction of non-stationary wind pressure on the surface of the glass curtain wall of an airport terminal building under strong wind conditions. The traditional methods often prove difficult in capturing local features and time-frequency variations of non-smooth signals when dealing with them, resulting in limited prediction accuracy. The proposed methodology involves a two-step process. Initially, wavelet decomposition of the original wind pressure coefficient sequence is performed, resulting in the reconstruction of subsequences at high and low frequencies. Subsequently, a convolutional neural network–long short-term memory (CNN–LSTM) neural network model incorporating an attention mechanism is constructed, leading to the attainment of high-precision wind pressure predictions. The experimental results demonstrate that the model performs well in the task of predicting non-stationary wind pressure coefficient sequences, with significantly lower prediction errors compared to a single prediction model. Furthermore, in comparison with alternative models that do not incorporate wavelet decomposition, the wavelet transform–CNN–LSTM–Attention model proposed in this paper has the capacity to enhance the mean absolute error, root mean square error, and mean absolute percentage error metrics by 15% to 18%, 12% to 16%, and 26% to 46%, respectively. This study provides reliable technical support for the safety assessment of glass curtain wall structures of airport terminals under extreme weather conditions, and has important engineering application value.

To investigate the impact of inhomogeneous wind sites on the aerostatic stability of a long-span suspension bridge in mountainous canyon terrain, this study focuses on such a bridge as its subject. Initially, extensive wind measurements were conducted at the bridge site. The data revealed significant variability in wind speed and angle of attack across the bridge’s span, highlighting the wind’s inhomogeneity. Subsequently, a nonlinear analysis method was developed to model the bridge’s static response to the inhomogeneous wind field, integrating empirical wind data and segment model tests. This method was validated through wind tunnel simulations of the inhomogeneous wind field and comprehensive aeroelastic model tests of the full bridge. The results indicate that the inhomogeneous wind field significantly affects the bridge’s aerostatic stability. These findings offer valuable insights for related studies.