Low elevation angle DOA estimation method based on RBF neural network

Abstract

The invention discloses a low elevation angle DOA estimation method based on an RBF neural network. The low elevation angle DOA estimation method based on the RBF neural network comprises the following steps: S1, selecting a trace point whose elevation angle is a low elevation angle in measured data, using a true elevation angle corresponding to the trace point with the low elevation angle as a label Y for training the neural network, wherein Y=[y<1>, y<2>,. . . , y<n>], obtaining a data covariance matrix R corresponding to y according to the label y, and extracting corresponding realpart features and imaginary part features from the data covariance matrix R to obtain a column vector r; S2, performing normalization on all the column vectors [r<1>,r<2>,. . . , r<n>] to obtain an input normX for training the RBF neural network; S3, calculating a basis function center of the RBF neural network, and calculating a basis function variance according to the basis function center; S4, calculating a connection weight between a hidden layer and an output layer according to the basis function variance to obtain a trained neural network; and S5, performing normalization processing on test set samples and inputting into the trained neural network to calculate an incoming wave arrival angle. The low elevation angle DOA estimation method based on the RBF neural network providedby the invention improves the target reconnaissance accuracy, reduces the calculation amount, and solves the problem that the DOA estimation accuracy is low and the calculation amount is large in ancomplex environment in the prior art.

Description

technical field [0001] The invention belongs to the technical field of radar, and in particular relates to an RBF neural network-based low-elevation DOA estimation method. Background technique [0002] Signal DOA (Direction of Arrival, direction of arrival) estimation, also known as spectral estimation (spectral estimation), angle of arrival (Angle Of Arrival) estimation, is an important branch in the field of array signal processing. Its basic idea is to use the relevant knowledge of array signal processing to process the echo signal received by the array, so as to obtain the target distance information and azimuth information. Specifically, DOA estimation refers to the use of antenna arrays to sense and receive space signals and electromagnetic signals, and then use modern signal processing methods to quickly and accurately estimate the direction of the signal source, which is of great importance in the fields of electronics, wireless communications, radar, sonar, etc. Va...

AI Technical Summary

Problems solved by technology

[0004] However, the disadvantage of the above method 1 is that when the target elevation angle is low, due to the multipath effect in the low elevation angle receiving environment, there are signals coherent with the target source in the received signal, and the source coherent signals cannot be effectively separated. Therefore, it is impossible to estimate the direction of arrival

The disadvantage of the second method above is that a large amount of matrix reorganization and matrix eigendecomposition are required, the amount of calculation is large, the speed of DOA estimation is slow, and it is not real-time

Images