PM2.5 measuring method using RBF neural network combined with PSO algorithm

Abstract

Considering the disadvantage of PM2.5 detection devices, there are many problems such as the low automation, poor test repeatability, and dielectric material loss etc. This paper presents a new PM2.5 detection system using laser diffraction technique based Fraunhefor diffraction theory. The Radial Basis Function (RBF) neural network with the inputs of multiple laser diffraction signals is used to be the micro particles calculating model to improve the detecting precision. To tackle the problems in the training algorithms, the Particle Swarm Optimization (PSO) algorithm is employed to optimize the key parameters of the RBF neural network (RBFNN). The simulation and experiment results show that the new PM2.5 detection system satisfies the detection requirements with the high calculating precision, and effectively overcomes the problems in the conventional detection system.