Nanoparticle detection method and system based on hyperspectral imaging

The invention relates to the field of nano-particle detection, and provides a nano-particle detection method and system based on hyperspectral imaging. The method comprises the following steps: acquiring aerosol with the volume of V1 in air, and filtering to obtain aerosol with the solution volume of V2; extracting the aerosol with the solution volume V3 from the aerosol with the solution volume V2; acquiring a hyperspectral image of the aerosol with the solution volume of V3; identifying the hyperspectral image by adopting a neural network to obtain the components of the aerosol nanoparticles in the aerosol with the solution volume of V3 and the number of the nanoparticles of different components; and calculating to obtain the concentration of the aerosol nanoparticles with different components in the air. According to the method, the neural network is adopted, each hyperspectral sample (pixel) is regarded as a data sequence, microscopic hyperspectral data are analyzed from the perspective of the sequence, a