Low elevation angle DOA estimation method based on RBF neural network
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A neural network, low-elevation technology, applied in the field of radar, can solve the problems of inability to effectively separate source coherent signals, inability to estimate the direction of arrival, slow DOA estimation, etc. The effect of improved angular accuracy
Inactive Publication Date: 2019-09-10
XIDIAN UNIV
View PDF6 Cites 13 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
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
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0041] See figure 1 , figure 1 It is a flowchart of a low-elevation DOA estimation method based on an RBF neural network provided by an embodiment of the present invention;
[0042] A kind of low-elevation DOA estimation method based on RBF neural network provided by the present invention comprises the following steps:
[0043] S1: Select the traces whose elevation angle is low in the measured data, and use the real elevation angle corresponding to the traces of the low elevation angle as the label Y of the training neural network, Y=[y 1 ,y 2 ,...,y n ], according to the label y i Get the corresponding data covariance matrix R i , from the data covariance matrix R i Extract the corresponding real part features and imaginary part features to get the column vector r i ;
[0044] In this embodiment, assuming that the receiving array is a uniform linear array of M array elements, the array receiving signal X(t) is: X(t)=AS(t)+N(t), where X(t) =[x 1 (t),x 2 (t),...,x M...
Embodiment 2
[0062] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail on the basis of the above-mentioned embodiments with reference to the accompanying drawings and specific experiments.
[0063] In this embodiment, the experimental conditions are as follows:
[0064] The target elevation angles used for testing and training are all low elevation angles below 5°, and 25 tracks in the azimuth sector under the complex position within 180°-210° and 330°-360° are selected for analysis, 18 of which are For the training of the RBF network, the training set has a total of 2661 traces, 7 tracks are used for the test of the RBF network, and the test set has a total of 892 traces. The data processing and neural network training part of the experiment were completed on MATLAB2017a. For the training track diagram and test track diagram, please refer to image 3 , image 3 It is the traini...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
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...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more