This study analyzed the effects of airflow characteristics on the temperature distribution and drying uniformity of paddy during convective drying. Simulations of the drying process with varying airflow inlet and outlet positions were conducted using COMSOL Multiphysics 6.1 software. The determination coefficient (R²) between the simulated data and experimental values of Sample1 (S1), Sample2 (S2), and Sample3 (S3) was calculated, and its average values were 0.964, 0.963, 0.963, and 0.967, respectively. This study demonstrates that the airflow direction and outlet location have a significant impact on the temperature uniformity of the paddy. The vortex structure generated by the obstruction of the sidewalls and paddy influences both the airflow and temperature distribution within the drying chamber. When the outlet was on the left side and the inlet airflow was in a vertical orientation (VO), the temperature distribution of the paddy exhibited higher temperatures in the edge regions and lower temperatures in the center, with a maximum temperature difference of around 16 °C. The time required for the temperature to reach equilibrium with the outlet positioned on the left was 28.6% shorter than with the outlets positioned in the center or on both sides. Moreover, the temperature uniformity of the three paddy samples was better under this condition. The developed model accurately reflected the paddy drying process. It could also be used to analyze the optimal heating uniformity, providing a technical basis for the design of grain dryers.

Online microwave drying process monitoring has been challenging due to the incompatibility of metal components with microwaves. This paper developed a microwave drying system based on online machine vision, which realized real-time extraction and measurement of images, weight, and temperature. An image-processing algorithm was developed to capture material shrinkage characteristics in real time. Constant-temperature microwave drying experiments were conducted, and the artificial neural network (ANN) and extreme learning machine (ELM) were utilized to model and predict the moisture content of materials during the drying process based on the degree of material shrinkage. The results demonstrated that the system and algorithm operated effectively, and ELM provided superior predictive performance and learning efficiency compared to ANN.

Underwater quadrotor vehicles operating in complex nearshore environments face challenges in three-dimensional path planning, obstacle-triggered replanning, and trajectory tracking under external disturbances. To address these issues, this paper evaluates an enhanced rapidly exploring random tree (iRRT) planner and a model predictive control–proportional–integral–derivative (MPC–PID) tracking strategy with residual disturbance estimation. The planner combines guided sampling, environment-aware adaptive extension, collision-checked reverse greedy pruning, and cubic B-spline smoothing. A bisection-based handoff reconnects the remaining safe path after a newly introduced obstacle; post-solution informed sampling is examined separately as an ablation. The tracking controller is evaluated on a nonlinear six-degree-of-freedom vehicle model under a seeded, wave-shaped disturbance proxy. In 30 runs on the original voxel map, both RRT and iRRT produced safe paths in the static and fixed-obstacle replanning cases under the same additional radius-two voxel-neighborhood test. Relative to RRT, iRRT reduced the mean number of raw path nodes by 37.4% in the static case and 12.8% after replanning, whereas its small mean path-length differences were not conclusive. Under matched paths and disturbance phases, adding residual estimation to MPC–PID reduced mean position RMSE by 12.1% on the static path and 9.7% on the replanned path. Component ablations and additional synthetic maps further examine the contributions and limits of the planning modules. These results support the proposed integration under the stated numerical assumptions; measured hydrodynamics and vehicle experiments remain to be investigated.