Precision fertilizer application technology is necessary to improve the utilization efficiency of fertilizers in agricultural production. Traditional mechanical fertilization systems risk blockages and uneven application when working in multiple crop rows. Pneumatic fertilization systems have improved efficiency and fertilization quality, however, fewer studies have characterized their designs in regards to the motion of the fertilizer particles. Here, we design and evaluate the parameters of the key components of a pneumatic fertilizer discharge system. Numerical simulations were conducted using a coupled EDEM-FLUENT and gas-phase models together with bench tests to examine the effects of inlet wind speed on the efficiency and consistency of the pneumatic fertilization system. The EDEM-FLUENT simulations showed that the number of fertilizer particles in the grid box set by EDEM was 60 particles in the range from t = 0.275 s to t = 0.5 s, and there was no blockage or cut-off in the pipe. The gas-phase simulation showed that there were tiny vortices in the fertilizer conveying pipe, and the maximum flow rate of its backflow was lower than 3.59 m/s, which had little effect on the fertilizer conveyance. The bench test showed that the inlet wind speed was 35–40 m/s, and the fertilization efficiency was 0.29–0.41 kg/s when the maximum variation coefficient of the row discharge consistency of the pneumatic distribution fertilizer discharge system was 5.55%. The coefficient of variation of the average row discharge consistency was 3.93%, and the average fertilizer discharge met the design requirements. Therefore, the pneumatic distribution system achieves stable operation and meets the requirements of fertilization operations.

There are two primary defects in the existing UAV avoidance systems: the system is memoryless; airborne radars are used to detect long-distance barriers, which are unreliable and expensive. The paper adopts the deep learning algorithm and ADS-B communication system based on a satellite base station to solve the above problems. It divides the avoidance problem into two parts: short-distance obstacle avoidance and long-distance route planning. On the one hand, the system establishes the knowledge base storing the previous avoidance experience and the matching mechanism, realizing the correspondence between input and experience through a deep learning algorithm. They can dramatically improve the reaction speed and safety of UAVs. On the other hand, the system realizes the interconnection between UAV and the satellite base station through the ADS-B communication system to replace the radars, putting the task of route planning on the satellite platform. Therefore, the satellite can achieve large-scale and all-weather detection to improve the overall safety of UAVs depending on its high and long-range characteristics. The paper also illustrates the design elements of the RF baseband integrated ADS-B transceiver and the simulation performance of the short-distance avoidance system in the end, whose results show that the system can be applied to dense obstacle environments and significantly improve the security of UAVs in a complex domain.