Unsupervised learning detection method for receiving signal change caused by underwater invasion target

An unsupervised learning and signal receiving technology, which is applied in radio wave measurement systems, measurement devices, and sound wave re-radiation, can solve the problems of insignificant changes in sound field indicators and poor real-time performance, so as to reduce the impact of time-varying environments and improve Detection performance, remarkable effect

Inactive Publication Date: 2019-05-21
NORTHWESTERN POLYTECHNICAL UNIV
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem with this type of traditional method is that when the signal is very weak compared with the intensity of the direct wave, in order to improve the detection effect, it is often necessary to process and judge multiple pulse signals at the same time, and the real-time performance is poor.
In order to solve this problem, although some machine learning methods have been used in detection, the sound field change index is not very significant in the case of direct wave interference

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
  • Unsupervised learning detection method for receiving signal change caused by underwater invasion target
  • Unsupervised learning detection method for receiving signal change caused by underwater invasion target
  • Unsupervised learning detection method for receiving signal change caused by underwater invasion target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0052] Step 1: Preprocessing of received data;

[0053] The received data matrix X is composed of multiple received pulse signals, expressed as follows:

[0054] X(t)=[x 1 (t), x 2 (t),...,x i (t),...,x N (t)]

[0055] where x i (t) is the i-th pulse signal, N is the number of pulses, and t is the relative time. The specific process of preprocessing is:

[0056] 1) Perform Hilbert transformation on the received data matrix X to obtain the pulse envelope matrix H. The specific transformation process is:

[0057] H(t)=[h 1 (t),...,h i (t),... h N (t)]

[0058]

[0059] 2) Normalize the pulse envelope with signal power to obtain a normalized pulse envelope matrix

[0060]

[0061]

[0062] Where M is the number of points relative to time t;

[0063] 3) Discrete Fourier transform (DFT) is performed on the normalized pulse envelope matr...

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

No PUM Login to view more

Abstract

The invention provides an unsupervised learning detection method for receiving signal change caused by an underwater invasion target. Data needing to be tested are preprocessed to serve as training data, a binary tree is sequentially established for the training data from a root node, the number of nodes which the testing data averagely pass through is counted, abnormal scores of the testing pulsedata are calculated, and whether receiving signal abnormal changes caused by forward scattering signals exist or not is judged; an unsupervised learning algorithm is adopted, weak receiving signal abnormity caused by forward scattering of the underwater invasion target is detected, various kinds of known information are fully utilized while the time-varying environment influence is weakened, andgood detection performance is achieved; and compared with an existing method, the method has the advantages that the forward scattering signals can be detected in real time, and compared with a conventional iForest method, the method is more remarkable in effect of detecting sound field changes caused by forward scattering of a target.

Description

technical field [0001] The present invention relates to a detection method that causes a change in a received signal. Background technique [0002] A forward scatter signal is generated when an underwater intruder passes through the line between the receiver and the transmitter. The forward scattered signal interferes with the direct wave, resulting in an abnormal change of the received signal, and the detection of this change can realize the early warning of the intrusion target. However, at a long distance, the forward scattered signal is weaker than the direct wave by more than 20dB, so that the abnormal change of the received signal is extremely weak, and it is difficult to directly detect this weak change. [0003] The current detection method is mainly to compare the difference between the sound field response when there is no target, such as the principal component analysis method, which uses the principal component extraction of the data matrix of the pulse signal r...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01S7/539G01S7/536G01S15/88G06F17/16G06F17/14
Inventor 雷波张遥杨益新卓颉
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap