The rapid reconstruction of the internal flow field within pressure vessel equipment based on features from limited detection points was of significant value for online monitoring and the construction of a digital twin. This paper proposed a surrogate model that combined Proper Orthogonal Decomposition (POD) with deep learning to capture the dynamic mapping relationship between sensor monitoring point information and the global flow field state during equipment operation, enabling rapid reconstruction of the temperature field and velocity field. Using POD, the order of the tested temperature field was reduced by 99.75%, and the order of the velocity field was reduced by 99.13%, effectively decreasing the dimensionality of the flow field. Our analysis revealed that the first modal coefficient of the temperature field snapshot data, after modal decomposition, had a higher energy proportion compared to that of the velocity field snapshot data, along with a more pronounced marginal effect. This indicates that more modes need to be retained for the velocity field to achieve a higher total energy proportion. By constructing a CSSA-BP model to represent the mapping relationship between the modal coefficients of the temperature and velocity fields and the data collected from the detection points, a comparison was made with the BP method in reconstructing the temperature field of a shell-and-tube heat exchanger. The CSSA-BP method yielded a maximum mean squared error (MSE) of 9.84 for the reconstructed temperature field, with a maximum mean absolute error (MAE) of 1.85. For the velocity field, the maximum MSE was 0.0135 and the maximum MAE was 0.0728. The global maximum errors for the reconstructed temperature field were 4.85%, 3.65%, and 4.29%, respectively. The global maximum errors for the reconstructed velocity field were 17.72%, 11.30%, and 16.79%, indicating that the model established in this study has high accuracy. Conventional CFD simulation methods require several hours, whereas the reconstruction model proposed here can rapidly reconstruct the flow field within 1 min after training is completed, significantly reducing reconstruction time. This work provides a new method for quickly obtaining the internal flow field state of pressure vessel equipment under limited detection points, offering a reference for online monitoring and the development of digital twins for pressure vessel equipment.

For low costs, numerical simulation is an effective method to reveal the internal mechanisms inside a thermal plasma torch. Various simulation models for studying the inside or outside characteristics of thermal plasma torches have been built and discussed. However, to reveal the inside mechanisms of thermal plasma torches under various working conditions to support the materials processing, more attention should be paid to building precise models of laminar plasma torches. Thus, based on the user-defined function (UDF) and user-defined scalar (UDS) of ANSYS Fluent software, the assumptions, governing equations, boundary conditions, and solving method were discussed in detail, and a corresponding numerical model of a homemade laminar plasma torch was first built. For verifying the effectiveness of the proposed numerical model and studying the influence of the gas components on the arc characteristics, the working conditions and experimental setups were introduced in sequence. Finally, the numerical and experimental results of the homemade laminar plasma torch were obtained and discussed in detail. The study results show that: ① The axial temperature of the plasma torch could be divided into three sections along the axis: peak temperature area (10 mm < x < 20 mm), stable temperature area (20 mm < x < 62 mm) and decrease temperature area (62 mm < x < 95 mm). Under the same input conditions, when pure argon gas was used, the peak temperature at the outlet was reached at approximately 7590 K, while for pure nitrogen and 50%Ar + 50%N₂, the corresponding peak temperatures were 6785 K and 7402.2 K, respectively. ② The axial velocity of pure nitrogen is much higher than that of pure argon and 50%Ar + 50%N₂, while that of pure argon and 50%Ar + 50%N₂ has little difference. In addition, when nitrogen gas was used, the peak velocity at the outlet reached 185 m/s, whereas, for argon gas and 50%Ar + 50%N₂, the corresponding peak velocities were 146 m/s and 169 m/s, respectively. ③ The simulated arc voltage trends under different working conditions are well in accordance with the experimental arc voltage trends.

For improving the adaptability of a tracked vehicle equipped with a symmetrical suspension system on complex hilly terrain, based on the coupling method of multi-body dynamics (MBD) and discrete element method (DEM), an MBD-DEM coupling model was built and verified to explore its dynamic behaviors on soil. Firstly, according to the basic parameters of the tracked vehicle equipped with a symmetrical suspension system, a corresponding MBD model was built in Recurdyn V9R4 software. Based on the Euler–Lagrange method, the mathematical structure of the symmetrical suspension system was analyzed, and a corresponding mathematical simulation model was built in Matlab2016/Simulink to verify the MBD model. Secondly, based on the DEM theory and the parameter of the soil in a hilly area, a granular pavement model was built. Then, based on the coupling method of MBD and DEM, the corresponding MBD-DEM coupling model was built. Finally, using the MBD-DEM coupling model, the dynamic behaviors of the tracked vehicle equipped with a symmetrical suspension system under horizontal condition, the climbing condition and the obstacle crossing condition were obtained and discussed. The study results show that the proposed MBD-DEM coupling model could be used effectively to analyze the dynamic characteristics of the tracked vehicle. In addition, according to the analysis of the dynamic characteristics of the proposed tracked vehicle, the tracked vehicle equipped with a symmetrical suspension presents good adaptabilities under various working conditions.

Foam mixers are classified as low-pressure and high-pressure types. Low-pressure mixers rely on agitator rotation, facing cleaning challenges and complex designs. High-pressure mixers are simple and require no cleaning but struggle with uneven mixing for high-viscosity substances. Traditionally, increasing the working pressure resolved this, but material quality limits it at higher pressures. To address the issues faced by high-pressure mixers when handling high-viscosity materials and to further improve the mixing performance of the mixer, this study focuses on a polyimide high-pressure mixer, identifying four design variables: impingement angle, inlet and outlet diameters, and impingement pressure. Using a Full Factorial Design of Experiments (DOE), the study investigates the impacts of these variables on mixing unevenness. Sample points were generated using Optimal Latin Hypercube Sampling—OLH. Combining the Sparrow Search Algorithm (SSA), Convolutional Neural Network (CNN), and Long Short-Term Memory Network (LSTM), the SSA-CNN-LSTM model was constructed for predictive analysis. The Whale Optimization Algorithm (WOA) optimized the model, to find an optimal design variable combination. The Computational Fluid Dynamics (CFD) simulation results indicate a 70% reduction in mixing unevenness through algorithmic optimization, significantly improving the mixer’s performance.