The growth environment of corps requires necessary improvements by Chinese solar greenhouses with Pad–Fan Cooling (PFC) systems for reducing their high temperatures in summer. Although computational fluid dynamics (CFD) could dynamically display the changes in humidity, temperature, and wind speed in solar greenhouses, its computational efficiency and accuracy are relatively low. In addition, the use of PFC systems can cool down solar greenhouses in summer, but they will also cause excessive humidity inside the greenhouses, thereby reducing the production efficiency of crops. Most existing studies only verify the effectiveness of a single machine learning (such as ARMA or ARIMA) or deep learning model (such as LSTM or TCN), lacking systematic comparison of different models. In the current study, two machine learning algorithms and three deep learning algorithms were used for their ability to predict a PFC system’s cooling effect, including on humidity, temperature, and wind speed, which were examined using Auto Regression Moving Average (ARMA), Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Time Convolutional Network (TCN), and Glavnoe Razvedivatelnoe Upravlenie (GRU), respectively. These results show that deep learning algorithms are significantly more effective than traditional machine learning algorithms in capturing the complex nonlinear relationships and spatiotemporal changes inside solar greenhouses. The LSTM model achieves R² values of 0.918 for temperature, 0.896 for humidity, and 0.849 for wind speed on the test set. TCN showed strong performance in identifying high-frequency fluctuations and extreme nonlinear features, particularly in wind speed prediction (test set R² = 0.861). However, it exhibited limitations in modeling certain temperature dynamics (e.g., T6 test set R² = 0.242) and humidity evaporation processes (e.g., T7 training set R² = −0.856). GRU delivered excellent performance, achieving a favorable balance between accuracy and efficiency. It attained the highest prediction accuracy for temperature (test set R² = 0.925) and humidity (test set R² = 0.901), and performed only slightly worse than TCN in wind speed prediction. In summary, deep learning models, particularly GRU, offer more reliable methodological support for greenhouse microclimate prediction, thereby facilitating the precise regulation of cooling systems and scientifically informed crop management.

In order to achieve fast and accurate life damage online monitoring of the steam turbine rotor, it was significant to propose an empirical-statistical model using a machine learning algorithm instead of finite element simulation to improve the effect of operation. The finite element method was used to calculate the maximum stress during the start-up schedule. The linear CDM (Continuum Damage Mechanics) and nonlinear CDM were applied to assess the creep-fatigue damage of the steam turbine rotor. A empirical-statistical model of a 600 MW steam turbine rotor was established by using temperature change rate and maximum stress according to the finite element result samples, which is proposed by compared R2 of SVR (Support Vector Regression), LSTM (Long Short-Term Memory) and RRM (Ridge Regression Method), which was also verified by finite element simulation under a random start-up parameters. The results showed that the creep-fatigue damage could be calculated by nonlinear CDM for more safety rather than linear CDM. The R2 of SVR (Support Vector Regression), LSTM (Long Short-Term Memory) and RRM were 0.9377, 0.9647 and 0.999, respectively. RRM was more suitable for the empirical-statistical model establishment of the steam turbine rotor. By comparing the empirical-statistical model result and finite element result under random parameters of the start-up schedule, the error is 0.51%.