CFD analysis and RBFNN-based optimization of spraying system for a six-rotor unmanned aerial vehicle (UAV) sprayer

To reduce pesticide waste caused by low spray droplet coverage on target surface, the spraying system parameters of a six-rotor UAV sprayer are optimized. Computational Fluid Dynamics (CFD) is employed to simulate the downwash airflow distribution and droplet deposition for the UAV sprayer. Latin hypercube sampling method is used to obtain 15 sample points to train the surrogate model with CFD results. The validated CFD model is coupled with radial basis function neural networks (RBFNN) and genetic algorithm (GA) to optimize the spraying system parameters, including numbers of nozzles, horizontal position of nozzles and vertical position of nozzles. The overall correlation coefficient (R) of this RBFNN model is about 0.949, indicating good fitting performance. The optimal nozzles number of a six-rotor UAV sprayer is 4. The spraying droplet coverage is increased by 16.27%, 23.25% and 18.24% at a rotor height of 1 m, 2 m and 3 m above from the target surface, respectively, compared with the original six-rotor UAV spraying system structure. The spraying droplet coverage and pesticide utilization of the six-rotor UAV sprayer are improved through optimizing the mounting number and mounting positions of the nozzles in the spraying system. The research results provide a theoretical basis for further design and optimization of the multi-rotor UAV sprayers.