Orbital angular momentum detection based on diffractive deep neural network

Abstract

Abstract We propose an orbital angular momentum (OAM) state detection method based on diffractive deep neural network (D2NN). The correct classification of the topological charge (TC) of the range [ ± 1, ± 2, …, ± 10] is implement. Based on the designed phase-only, amplitude-only and hybrid type network, we analyzed the influence of the number of diffractive layers and the strength of turbulence on the detection accuracy. The results show that the method can realize the rapid detection of OAM state, which has potential value for free space optical (FSO) communication based on optical vortex (OV) beam.