Direction-of-arrival estimation method based on deep learning

Abstract

The invention discloses a direction-of-arrival estimation method based on deep learning. The method comprises the steps of: discretizing and numbering the range of the direction of arrival, arrangingnarrow-band signals received by each array element of the antenna array in sequence to obtain an array signal vector, and taking Hilbert transform of the array signal vector as an imaginary part and an original narrow-band signal as a real part to obtain the analytic signal vector of the array signal vector; regarding the real part and the imaginary part of each element of the analytic signal vector as a signal channel; and inputting a signal to a pre-trained one-dimensional deep convolutional neural network to extract signal features, inputting the signal features to a full-connection neuralnetwork, taking a softmax function for output, and normalizing the softmax function to obtain a probability that an expected signal arrival direction is a direction corresponding to a serial number. The method can be suitable for the situation that the arrival directions and the intensity of the expected signal and the interference signal are completely unknown, can search the arrival direction ofthe expected signal in a self-adaptive mode, and has very high accuracy, rapidity, credibility and robustness.

Description

technical field [0001] The present invention relates to the field of signal processing, in particular, to a direction-of-arrival estimation method based on deep learning. Background technique [0002] In electronic communication systems, receivers often transmit and receive signals through phased array antennas to increase the flexibility of beam pointing. Estimating the direction of arrival of the desired signal has also become an important issue. Traditional DOA estimation methods generally include subspace-based methods such as multi-signal classification; time-of-arrival delay methods such as generalized cross-correlation methods; methods based on L1 norm penalties such as maximum likelihood methods, etc. However, these methods face many problems in practice, such as unrealistic assumptions on signal and noise models, unreliable performance in real environments, and so on. Contents of the invention [0003] The technical problem solved by the present invention is: to...

AI Technical Summary

Problems solved by technology

However, these methods face many problems in practice, such as unrealistic assumptions about signal and noise models, unreliable performance in real environments, etc.

Images