Two-dimensional DOA Estimation Method for Underwater Acoustic Array Signals Based on Deep Learning
A technology of direction estimation and array signal, applied in the system of determining direction or offset, direction finders using ultrasonic/sonic/infrasonic waves, etc., can solve the noise interference such as man-made and natural, high complexity of two-dimensional DOA estimation, Problems such as low estimation accuracy, to achieve the effect of solving low estimation accuracy, accurate signal direction, and reducing noise interference
Active Publication Date: 2022-04-29
QINGDAO UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the time-varying characteristics of underwater acoustic signals in complex ocean environments, the serious interference of man-made and natural noise, the high complexity and low estimation accuracy of two-dimensional DOA estimation, the present invention proposes a two-dimensional underwater acoustic array signal based on deep learning. Direction of arrival estimation method to make up for the deficiencies of existing technologies
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0073] A method for estimating two-dimensional direction of arrival of underwater acoustic array signals based on deep learning described in this embodiment includes the following steps (such as figure 1 shown):
[0074] Step S1: Model the shallow sea acoustic environment and receive the underwater acoustic signal, the specific steps are as follows:
[0075] S1-1: L-shaped uniform linear array (such as figure 2 (shown) is composed of two M-element uniform linear arrays along the x-axis and y-axis respectively on the plane, and the interval between adjacent array elements is d, which is equal to the half-wavelength of the signal. Array elements are isotropic. Suppose there is a frequency f 0 , the far-field narrow-band underwater acoustic signal with the sound velocity v is incident on the L-shaped array composed of 2M-1 array elements at the wavelength λ, where the angles between the incident signal and the x-axis and y-axis are represented by α and β respectively, and the...
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 method for estimating the direction of arrival of two-dimensional underwater acoustic array signals based on deep learning. The invention first preprocesses the received signals of the type underwater acoustic array based on wavelet transform, extracts the time-frequency characteristics of the underwater acoustic signal, and preserves the original On the premise of important signal information, the linear factor is used to enhance the signal characteristics to reduce noise interference; then the signal is compressed and dimensionally reduced based on singular value decomposition, the signal energy part in the upper left corner of the decomposed matrix is extracted, and the noise energy part in the lower right corner is discarded to enhance The time-frequency characteristics of the preprocessed signal; finally, the two-dimensional direction of arrival estimation model of the underwater acoustic array signal based on the convolutional neural network is trained to obtain the accurately predicted two-dimensional direction of arrival. The invention can effectively enhance the time-frequency characteristic of the signal, reduce noise interference, and more accurately predict the two-dimensional direction of arrival of the underwater acoustic array signal.
Description
technical field [0001] The invention belongs to the technical field of underwater acoustic communication, and in particular relates to a method for estimating a two-dimensional direction of arrival of an underwater acoustic array signal based on deep learning. Background technique [0002] Direction of Arrival (DOA) estimation refers to estimating the direction of arrival of the signal by analyzing and processing the received signal of the array. With the development of underwater acoustic communication technology, DOA estimation technology of underwater acoustic array signal has become the premise and basis for identifying, locating, tracking and detecting underwater acoustic targets. At present, sound wave is the only signal form capable of long-distance underwater propagation. However, the environment in the ocean is complex, the underwater acoustic channel is sparse, a large amount of natural and man-made noise and multipath effects are serious, which increases the limit...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01S3/802
CPCG01S3/802
Inventor 矫禄禄权天祺黄子豪宋娟董新利张德春王景景
Owner QINGDAO UNIV OF SCI & TECH