Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Ship radiation noise characteristic recombination method based on statistical distribution

A technology of radiated noise and statistical distribution, applied in computing, computer components, pattern recognition in signals, etc., can solve problems such as weak robustness and low recognition efficiency

Active Publication Date: 2020-08-18
HARBIN ENG UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a method for recombining ship radiation noise features based on statistical distribution. Under the background of unknown and complex environments, the robustness of ship radiation noise feature extraction results is not strong and the recognition efficiency is low.

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
  • Ship radiation noise characteristic recombination method based on statistical distribution
  • Ship radiation noise characteristic recombination method based on statistical distribution
  • Ship radiation noise characteristic recombination method based on statistical distribution

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0089] Specific embodiment one, refer to figure 1 Shown, a kind of ship radiation noise feature reconstruction method based on statistical distribution, said method comprises the following steps:

[0090] Step 1: Obtain a piece of ship radiation noise sample data, perform 11 / 2-dimensional spectrum analysis on the finite length ship radiation noise power spectrum, and obtain low-frequency line spectrum information;

[0091] Step 2: According to the low-frequency line spectrum distribution in the 11 / 2-dimensional spectrogram obtained in step 1, perform normalization processing to initially obtain the probability distribution of the low-frequency line spectrum in each frequency interval;

[0092] Step 3: According to the ship radiation noise sample data acquired in step 1, analyze the LOFAR spectrogram of the ship radiation noise sample data by short-time Fourier transform method;

[0093] Step 4: According to the LOFAR spectrogram obtained in Step 3, the frequency range is even...

specific Embodiment 2

[0161] Step 1. First of all, for a ship radiation noise sample, it is necessary to ensure the correct feature extraction and reduce the amount of calculation as much as possible. Therefore, 1 second of ship radiation noise data is intercepted as a single feature extraction sample. Obtain the power spectrum X(ω) of the ship radiation sample signal, and its third-order accumulation is C 3x =(τ 1 ,τ 2 ), then its diagonal slice is expressed as C 3x (τ,τ)(τ 1 =τ 2 =τ), the result of Fourier transform of the diagonal slice C 3x (ω) is called the 11 / 2-dimensional spectrum of the original signal, and its expression is:

[0162]

[0163] Simplifies to:

[0164]

[0165] C 3x (ω)=X * (ω)[X(ω)*X(ω)] (22)

[0166] In the formula: X(ω) is the Fourier transform result of x(t); X * (ω) is the complex conjugate of X(ω).

[0167] Step 2. According to the type analysis of ship radiation noise source, the low-frequency line spectrum of ship radiation noise is mainly produced by...

specific Embodiment 3

[0216] Firstly, two ship radiation noise sample data are constructed. Sample 1 is a merchant ship with a tonnage of 20,000 tons, sailing at a speed of 10 knots, and the number of propeller blades is 5. The line spectrum frequencies generated by the mechanical vibration of the ship are 460 and 580 respectively. , 650, 790, 880Hz; Sample 2 is a civilian ship with a tonnage of 15,000 tons, sailing at a speed of 18 knots, with 7 propeller blades, and the line spectrum frequencies generated by the mechanical vibration of the ship are 370, 495, 570, and 695, respectively. , 760, 900Hz; the frequency domain power spectrum signal of two samples is as follows image 3 as shown in image 3 (a) is the frequency domain power spectrum diagram of sample 1, image 3 (b) is the frequency domain power spectrum plot of sample 2.

[0217] First, feature extraction is performed, Figure 4 is the result of feature extraction on sample 2, Figure 4 (a) is the result of 11 / 2-dimensional spectral...

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 a ship radiation noise characteristic recombination method based on statistical distribution. According to ship radiation noise characteristics, 1 / 2-dimensional spectrum analysis, LOFAR spectrum analysis and DEMON spectrum analysis are respectively performed on finite-length original noise signals, and probability distribution characteristics of a line spectrum and a modulation spectrum in a ship radiation noise spectrogram are acquired by using a statistical analysis method. In order to reduce feature information redundancy, the dimension of a feature sample is reducedthrough a principal component analysis method to construct a comprehensive feature sample, and finally the comprehensive feature sample is input into a recognition classifier to be trained and recognized to achieve classification of ship radiation noise. The recognition effect of the ship radiation noise characteristic recombination method is obviously higher than that of a single spectral analysis feature extraction method, and especially the more samples are, the higher the recognition accuracy is; the ship radiation noise characteristic recombination method can effectively solve a problem that the ship features are not obvious in an unknown and complex environment, and reduces the wrong recognition probability of a target; and the recognition efficiency of the comprehensive features isimproved, and the algorithm model is simple.

Description

technical field [0001] The invention relates to a feature recombination method of ship radiation noise based on statistical distribution, and belongs to the technical field of underwater acoustic target recognition. Background technique [0002] Underwater acoustic target recognition refers to the detection of targets in a non-contact and long-distance manner, and the identification of underwater acoustic target types through recognition and classification algorithms. Feature reorganization is to obtain better classification and recognition by recombining the extracted features. effect method. Underwater acoustic target recognition covers three important directions: analysis of underwater acoustic target characteristics, feature extraction of underwater acoustic targets, and selection and design of classifiers. At present, there are mainly four types of methods for underwater acoustic target feature extraction: 1. Time-domain waveform feature extraction. The time-domain wav...

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): G06K9/00
CPCG06F2218/02G06F2218/08Y02T90/00
Inventor 齐滨梁国龙付进王燕孙金王晋晋邹男王逸林张光普
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com