Optimization Of Nebulizer Parameters Based On BP Neural Network And Simulated Annealing Algorithm

The environment is the objective condition and space on which people depend for survival and sustainable socio-economic development.With the rapid development of modern industry,environmental pollution has become increasingly intensified.Among environmental pollution,air pollution is the widest scope of environmental pollution.One of the most influential ones,improving air quality has become a hot spot of research.Among them,mist sprayers have been widely used in dust reduction and dust suppression places.Axial flow fans and nozzles are the core components of mist sprayers.It affects the performance of the nebulizer.Therefore,reasonable optimization of the parameters of the fan and the nozzle is very important to improve the performance of the nebulizer.This paper uses reverse engineering to establish a model of the axial flow fan of the mister,analyzes the performance of the mister by CFD simulation technology,and uses a single variable method to analyze the number of blades,guide vanes,nozzles,nozzle angle,and fog.The influence of the diameter of the droplet particles on the performance of the nebulizer,determine the optimal value range of each parameter,and lay the foundation for the subsequent establishment of a multi-objective database.Within the value range of each parameter,select appropriate values to establish an orthogonal experiment table to provide data samples for the BP neural network,determine the number of neurons in the input and output layers of the network,the number of hidden layers and the number of hidden layer neurons,and learning Rate and transfer function,establish a reasonable BP neural network,and test the fit of the network.At the same time,in order to improve the simulation accuracy,this paper adopts the collaborative optimization method of BP neural network and simulated annealing algorithm,and uses the simulated annealing algorithm to globally optimize the system to obtain the best performance and corresponding parameter combination of the mist sprayer.Finally,the optimization combination is simulated and verified To analyze the difference in performance parameters from the original mist sprayer.