CN111488801A - Ship classification method based on vibration noise identification - Google Patents

Ship classification method based on vibration noise identification Download PDF

Info

Publication number
CN111488801A
CN111488801A CN202010180725.9A CN202010180725A CN111488801A CN 111488801 A CN111488801 A CN 111488801A CN 202010180725 A CN202010180725 A CN 202010180725A CN 111488801 A CN111488801 A CN 111488801A
Authority
CN
China
Prior art keywords
ship
noise
imf
signal
vibration noise
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010180725.9A
Other languages
Chinese (zh)
Inventor
张安民
周健
张佳丽
张豪
丁峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN202010180725.9A priority Critical patent/CN111488801A/en
Publication of CN111488801A publication Critical patent/CN111488801A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)

Abstract

The invention discloses a ship classification method based on vibration noise identification, which comprises the following steps: 1. collecting ship vibration noise and converting the ship vibration noise into a time domain signal; 2. carrying out improved set empirical mode decomposition on the ship vibration signal; 3. performing Hilbert-Huang transformation on the signals subjected to modal decomposition; 4. hilbert spectrum analysis of ship radiation noise; 5. extracting ship noise features; 6. classifying the ship noise characteristics by using a ship classifier based on a support vector machine; 7. verifying the accuracy of the ship classification result, and if the accuracy is correct, finishing the ship classification; and if not, entering the ship classifier to reclassify again. The invention realizes a ship classification method based on vibration noise identification, and provides a new way for marine traffic managers, scientific researchers and military personnel to obtain ship types.

Description

Ship classification method based on vibration noise identification
Technical Field
The invention relates to the technical field of ship type identification, in particular to a ship classification method based on vibration noise identification.
Background
Ship vibration noise feature identification is one of the very leading issues in underwater acoustic signal processing. When a ship passes by, the sonar can realize the sensing, classification, tracking and positioning of the ship through the processing and recognition of the ship vibration noise signals, and has important significance for guaranteeing the ship navigation safety, the marine traffic management, the national defense safety and the like. The ship radiation noise generation mechanism is complex and influenced by the complex marine environment, so that the ship radiation noise generation mechanism has non-smooth and non-linear characteristics. The traditional signal processing methods such as time domain waveform feature extraction, frequency domain spectrum analysis, wavelet transformation in a time-frequency domain and the like have limitations when processing the problems, can not well extract the features of the ship radiation noise signals, and further can not accurately identify and classify ships.
In recent years, a large amount of research has been carried out by scholars at home and abroad on a ship classification method based on acoustic features, and certain results have been obtained, wherein the method based on the Hilbert-Huang transform has prominent advantages in processing the problems. A time-frequency analysis method combining Bark wavelet analysis and Hilbert-Huang transform is proposed in reference [1] (WangShuguang, ZengXiang. robust underserver noise targets classification of an automatic analysis [ J ]. Applied Acoustics,78:68-76.) to classify ships; the method for extracting the complexity characteristic of the radiation noise of the ship based on the multi-scale arrangement entropy is provided on the basis of the ensemble empirical mode decomposition by using a reference document [2] (the philosophy, Liyaan. the ship radiation noise complexity characteristic extraction research [ J ] vibration and impact, 2019,38(12): 225-. The feasibility of the Hilbert-Huang transform and the improved method thereof for extracting and classifying ship noise features is proved by the method, but the method is classified based on single features and does not comprehensively consider information such as energy, frequency, noise amplitude and the like.
Disclosure of Invention
The invention aims to overcome the defects of the technology and provide a ship classification method based on vibration noise identification.
In order to achieve the purpose, the invention adopts the following technical scheme: a ship classification method based on vibration noise identification is characterized by comprising the following steps:
step 1, collecting ship vibration noise, and converting the ship vibration noise into a time domain signal;
step 2, carrying out improved set empirical mode decomposition on the ship vibration signal;
step 3, performing Hilbert-Huang transformation on the signals subjected to modal decomposition;
step 4, Hilbert spectrum analysis of ship radiation noise;
step 5, extracting ship noise characteristics;
step 6, classifying the ship noise characteristics by using a ship classifier based on a support vector machine;
7, verifying the accuracy of the ship classification result, and if the accuracy is correct, finishing the ship classification; and if not, entering the ship classifier to reclassify again.
Preferably, in step 1, the ship vibration noise is acquired from underwater by using sonar and hydrophone equipment.
Preferably, in step 2, a spurious component in the signal is removed by a method of calculating a Permutation Entropy (PE), and a main Intrinsic Mode Function (IMF) component is screened out, so as to suppress the modal aliasing phenomenon.
Preferably, in step 3, the instantaneous frequency of each order of IMF is solved using a hilbert-yellow transform, thereby obtaining an amplitude-time-frequency representation of the signal, i.e. a hilbert spectrum, and the hilbert marginal spectrum is obtained by calculating the integral of the hilbert spectrum over the entire period.
Preferably, in step 4, each type of ship radiation noise is decomposed into a series of IMF components with different numbers and different oscillation periods through MEEMD, and the normalized energy of each IMF component and the correlation coefficient between the IMF component and the original noise signal are obtained.
Preferably, the correlation coefficient represents the similarity between the IMF component and the original noise signal, the IMF component with a larger correlation coefficient has a high similarity with the original noise signal and should have more energy, the IMF component with the highest correlation coefficient is selected as the ship noise characteristic component, which is called the strongest IMF component, and 4 characteristic parameters, namely the strongest IMF component energy, the strongest IMF average amplitude, the strongest IMF average instantaneous frequency and the strongest IMF center frequency, are adopted.
Preferably, the extracted 4 kinds of feature parameters are converted into feature vectors and input into the SVM for vessel classification and identification, and the SVM classification result is compared with the actual value. If the classification is correct, finishing the ship classification; otherwise, the signal is input into the SVM for reclassification.
The ship classification method based on the multi-feature noise component has the advantages that the ship classification method based on the multi-feature noise component is realized, the defect that the classification is carried out by means of single feature in the current method is technically made up, and the improvement of the identification accuracy rate is facilitated. The ship classification method based on vibration noise identification can realize underwater identification and hidden detection, provides an effective ship identification, classification and supervision means without influencing water traffic, and has wide application prospects in the fields of marine traffic management, ship navigation safety, national defense safety and the like.
Drawings
FIG. 1 is a flow chart of a ship classification method based on vibration noise identification according to the present invention;
FIG. 2 is a time domain graph of the radiated noise of a ship according to the present invention;
FIG. 3 shows the MEEMD decomposition result of the ship radiation noise of the present invention;
FIG. 4 is a Hilbert-Huang spectrum of the radiated noise of a ship according to the present invention;
fig. 5 is a hilbert marginal spectrum of the radiated noise of the ship of the present invention.
FIG. 6 is a graph comparing normalized energy and correlation coefficient of the ship radiation noise of the present invention.
Detailed Description
Fig. 1 is a ship classification method based on vibration noise identification according to the present invention, and as shown in fig. 1, the method of this embodiment may include:
step 1, collecting ship vibration noise, and converting the ship vibration noise into a time domain signal;
step 2, carrying out improved set empirical mode decomposition on the ship vibration signal;
step 3, performing Hilbert-Huang transformation on the signals subjected to modal decomposition;
step 4, Hilbert spectrum analysis of ship radiation noise;
step 5, extracting ship noise characteristics;
step 6, classifying the ship noise characteristics by using a ship classifier based on a support vector machine;
7, verifying the accuracy of the ship classification result, and if the accuracy is correct, finishing the ship classification; and if not, entering the ship classifier to reclassify again.
Further, the ship vibration noise collection comprises: the equipment such as sonar and hydrophone is used for acquiring the ship vibration noise from the underwater and converting the ship vibration noise into a time domain signal, and a time domain signal diagram of the ship vibration noise is shown in fig. 2.
Further, the improved ensemble empirical mode decomposition of the ship vibration signal includes: and eliminating false components in the signals by a method of calculating the permutation entropy, screening out main intrinsic mode function IMF components, and further inhibiting the mode aliasing phenomenon. The MEEMD algorithm comprises the following specific steps:
(1) adding white noise signal n with zero mean value to original signal x (t)i(t) and-ni(t), obtaining:
Figure BDA0002412431850000031
Figure BDA0002412431850000032
wherein the white noise amplitude aiFrom 0.1 to 0.2 times the standard deviation of the original signal.
(2) Are respectively paired
Figure BDA0002412431850000041
And
Figure BDA0002412431850000042
performing EMD decomposition to obtain
Figure BDA0002412431850000043
And
Figure BDA0002412431850000044
taking the integrated average to obtain:
Figure BDA0002412431850000045
where N is the number of samples of the signal x (t) to be analyzed.
(3) Calculating IMF'1(t) a entropy value θ, if θ is greater than the predetermined entropy value θ0Then it is considered as an abnormal signal. The preset arrangement entropy value is obtained through a plurality of experiments according to the researched signal, theta0The value is 0.6.
(4) Repeating the processes of (2) - (3) until IMF'p(t) is not an anomaly signal.
Removing the decomposed first p-1 false components from the original signal, and decomposing the residual signal R (t) to obtain:
Figure BDA0002412431850000046
Figure BDA0002412431850000047
wherein C isjAnd (t) and r (t) are respectively an IMF component and a remainder, and m is the number of IMFs obtained by EMD decomposition. The original data sequence is decomposed into the sum of m IMF components and the remainder by the MEEMD method, the remainder represents the average trend of the data, and the MEEMD decomposition result is shown in FIG. 3.
Further, the hilbert-yellow transform is performed on the signal after modal decomposition, and includes: solving the instantaneous frequency of each order of IMF by using Hilbert transform, thereby obtaining an amplitude-time-frequency representation of the signal, namely a Hilbert spectrum; the Hilbert marginal spectrum is obtained by calculating the integral of the Hilbert spectrum over the entire period.
The method comprises the following specific steps:
and performing Hilbert transform on each IMF component obtained by decomposition to obtain:
Figure BDA0002412431850000048
defined by the Hilbert transform
Figure BDA0002412431850000049
And Cj(τ) is a complex conjugate pair whose analytic signal is:
Figure BDA00024124318500000410
calculating the instantaneous amplitude a from the analytic signalj(t) and instantaneous frequency fj(t) is:
Figure BDA00024124318500000411
Figure BDA00024124318500000412
wherein
Figure BDA00024124318500000413
Is the instantaneous phase. The instantaneous frequency extracts the frequency changing along with time in the signal, and compared with signal processing modes with fixed basis functions, such as Fourier transform, wavelet transform and the like, the method has the advantage of self-adaptive signal analysis. The hilbert spectrum of the signal is obtained by calculation and is expressed as:
Figure BDA0002412431850000051
the hilbert spectrum is the distribution of instantaneous amplitude on a frequency-time plane, and has good time-frequency aggregation.
Integration of H (ω, t) in the time domain yields the marginal spectrum:
Figure BDA0002412431850000052
wherein T is the period. The marginal spectrum describes the distribution of the same frequency amplitude or energy superposition value in the frequency domain in the whole time frequency of the signal. Fig. 4-5 are hilbert-spectrum and hilbert marginal spectrum, respectively.
Further, the hilbert spectrum analysis of the ship radiation noise includes: the radiation noise of various ships is decomposed into a series of IMF components with different quantities and oscillation periods through MEEMD. The normalized energy of each IMF component and the correlation coefficient with the original noise signal are found, as shown in fig. 6.
Further, the extraction of the ship noise features comprises: the IMF component with a larger correlation coefficient has a higher similarity to the original noise signal and should also carry more energy. And selecting the IMF component with the highest correlation coefficient as the ship noise characteristic component, namely the strongest IMF component. 4 characteristic parameters of strongest IMF component energy, strongest IMF average amplitude, strongest IMF average instantaneous frequency and strongest IMF center frequency are adopted. Further, let the strongest IMF component include N samples, after Hilbert transform, the instantaneous amplitude of the nth sample is anInstantaneous frequency of fnThen the instantaneous energy of the point
Figure BDA0002412431850000053
The strongest IMF component QmaxIs defined as:
Figure BDA0002412431850000054
mean amplitude a of the strongest IMFmeanIs defined as:
Figure BDA0002412431850000055
strongest IMF mean instantaneous frequency fmeanIs defined as:
Figure BDA0002412431850000056
strongest IMF center frequency
Figure BDA0002412431850000061
Comprises the following steps:
Figure BDA0002412431850000062
further, the ship classifier based on the support vector machine comprises: 4 kinds of extracted ship radiation noise characteristics, namely Qmax、amean、fmean、
Figure BDA0002412431850000063
And converting the characteristic vectors into characteristic vectors, inputting the characteristic vectors into the SVM, and performing ship classification and identification.
Further, the classification result verification includes: and comparing the SVM classification result with the actual value. If the classification is correct, finishing the ship classification; otherwise, the signal is input into the SVM for reclassification.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (7)

1. A ship classification method based on vibration noise identification is characterized by comprising the following steps:
step 1, collecting ship vibration noise, and converting the ship vibration noise into a time domain signal;
step 2, carrying out improved set empirical mode decomposition on the ship vibration signal;
step 3, performing Hilbert-Huang transformation on the signals subjected to modal decomposition;
step 4, Hilbert spectrum analysis of ship radiation noise;
step 5, extracting ship noise characteristics;
step 6, classifying the ship noise characteristics by using a ship classifier based on a support vector machine;
7, verifying the accuracy of the ship classification result, and if the accuracy is correct, finishing the ship classification; and if not, entering the ship classifier to reclassify again.
2. The ship classification method based on vibration noise identification according to claim 1, wherein in step 1, ship vibration noise is acquired from underwater by using sonar and hydrophone equipment.
3. The method of claim 1, wherein in step 2, false components in the signals are removed by calculating a Permutation Entropy (PE), and a main Intrinsic Mode Function (IMF) component is selected to suppress modal aliasing.
4. The method of claim 1, wherein in step 3, the instantaneous frequency of each IMF is solved by using Hilbert-Huang transform to obtain the amplitude-time-frequency representation of the signal, i.e. Hilbert spectrum, and the Hilbert marginal spectrum is obtained by calculating the integral of the Hilbert spectrum over the whole period.
5. The ship classification method based on vibration noise identification according to claim 1, wherein in step 4, each ship radiation noise is decomposed into a series of IMF components with different numbers and different oscillation periods through MEEMD, and the normalized energy of each IMF component and the correlation coefficient between the normalized energy and the original noise signal are obtained.
6. The ship classification method based on vibration noise identification according to claim 5, wherein the correlation coefficient represents the similarity degree between the IMF component and the original noise signal, the IMF component with the larger correlation coefficient has the high similarity degree with the original noise signal and should have more energy, the IMF component with the highest correlation coefficient is selected as the ship noise characteristic component, which is called the strongest IMF component, and 4 characteristic parameters including the strongest IMF component energy, the strongest IMF average amplitude, the strongest IMF average instantaneous frequency and the strongest IMF center frequency are adopted.
7. The ship classification method based on vibration noise recognition of claim 6, wherein the extracted 4 feature parameters are converted into feature vectors and input into SVM for ship classification recognition, and the SVM classification result is compared with an actual value. If the classification is correct, finishing the ship classification; otherwise, the signal is input into the SVM for reclassification.
CN202010180725.9A 2020-03-16 2020-03-16 Ship classification method based on vibration noise identification Pending CN111488801A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010180725.9A CN111488801A (en) 2020-03-16 2020-03-16 Ship classification method based on vibration noise identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010180725.9A CN111488801A (en) 2020-03-16 2020-03-16 Ship classification method based on vibration noise identification

Publications (1)

Publication Number Publication Date
CN111488801A true CN111488801A (en) 2020-08-04

Family

ID=71794414

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010180725.9A Pending CN111488801A (en) 2020-03-16 2020-03-16 Ship classification method based on vibration noise identification

Country Status (1)

Country Link
CN (1) CN111488801A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108388848A (en) * 2018-02-07 2018-08-10 西安石油大学 A kind of multiple dimensioned oil-gas-water three-phase flow mechanical characteristic analysis method
CN112183280A (en) * 2020-09-21 2021-01-05 西安交通大学 Underwater sound target radiation noise classification method and system based on EMD and compressed sensing
CN112525467A (en) * 2020-11-26 2021-03-19 山东科技大学 Impact damage area identification method and device suitable for cantilever beam
CN112651385A (en) * 2021-01-18 2021-04-13 西北工业大学青岛研究院 Magnetic anomaly multi-feature information extraction method based on Hilbert-Huang transform
CN113077813A (en) * 2021-03-22 2021-07-06 自然资源部第一海洋研究所 Ship noise identification method based on holographic spectrum and deep learning
CN113189624A (en) * 2021-04-30 2021-07-30 中山大学 Adaptive classification multipath error extraction method and device
CN113554123A (en) * 2021-09-18 2021-10-26 江苏禹治流域管理技术研究院有限公司 Automatic sand production ship identification method based on acousto-optic linkage
CN118013301A (en) * 2024-04-09 2024-05-10 青岛奥维特智能科技有限公司 BIM-based highway bridge construction information digital management method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732970A (en) * 2013-12-20 2015-06-24 中国科学院声学研究所 Ship radiation noise recognition method based on comprehensive features
CN105954038A (en) * 2016-04-20 2016-09-21 辽宁工业大学 Vibration signal energy feature extraction method based on IMF component
CN108444712A (en) * 2018-05-07 2018-08-24 东南大学 Based on the wind-powered electricity generation transmission system base bearing analysis of vibration signal method for improving HHT and fuzzy entropy
CN109784410A (en) * 2019-01-18 2019-05-21 西安邮电大学 A kind of feature extraction and classification method of ships radiated noise signal
CN110175508A (en) * 2019-04-09 2019-08-27 杭州电子科技大学 A kind of Eigenvalue Extraction Method applied to ultrasonic partial discharge detection
CN110196283A (en) * 2019-05-27 2019-09-03 东南大学 A kind of timber structure damage sound emission lossless detection method based on instantaneous frequency
CN110458073A (en) * 2019-08-01 2019-11-15 北京邮电大学 A kind of fiber-optic vibration signal characteristic extracting methods based on MEEMD-Hilbert and multilevel wavelet decomposition

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732970A (en) * 2013-12-20 2015-06-24 中国科学院声学研究所 Ship radiation noise recognition method based on comprehensive features
CN105954038A (en) * 2016-04-20 2016-09-21 辽宁工业大学 Vibration signal energy feature extraction method based on IMF component
CN108444712A (en) * 2018-05-07 2018-08-24 东南大学 Based on the wind-powered electricity generation transmission system base bearing analysis of vibration signal method for improving HHT and fuzzy entropy
CN109784410A (en) * 2019-01-18 2019-05-21 西安邮电大学 A kind of feature extraction and classification method of ships radiated noise signal
CN110175508A (en) * 2019-04-09 2019-08-27 杭州电子科技大学 A kind of Eigenvalue Extraction Method applied to ultrasonic partial discharge detection
CN110196283A (en) * 2019-05-27 2019-09-03 东南大学 A kind of timber structure damage sound emission lossless detection method based on instantaneous frequency
CN110458073A (en) * 2019-08-01 2019-11-15 北京邮电大学 A kind of fiber-optic vibration signal characteristic extracting methods based on MEEMD-Hilbert and multilevel wavelet decomposition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李余兴等: "基于 VMD 和 SVM 的舰船辐射噪声特征提取及分类识别", 《国防科技大学学报》 *
杨宏: "经验模态分解及其在水声信号处理中的应用", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108388848A (en) * 2018-02-07 2018-08-10 西安石油大学 A kind of multiple dimensioned oil-gas-water three-phase flow mechanical characteristic analysis method
CN112183280A (en) * 2020-09-21 2021-01-05 西安交通大学 Underwater sound target radiation noise classification method and system based on EMD and compressed sensing
CN112525467A (en) * 2020-11-26 2021-03-19 山东科技大学 Impact damage area identification method and device suitable for cantilever beam
CN112525467B (en) * 2020-11-26 2022-09-13 山东科技大学 Impact damage area identification method and device suitable for cantilever beam
CN112651385A (en) * 2021-01-18 2021-04-13 西北工业大学青岛研究院 Magnetic anomaly multi-feature information extraction method based on Hilbert-Huang transform
CN113077813A (en) * 2021-03-22 2021-07-06 自然资源部第一海洋研究所 Ship noise identification method based on holographic spectrum and deep learning
CN113077813B (en) * 2021-03-22 2022-03-01 自然资源部第一海洋研究所 Ship noise identification method based on holographic spectrum and deep learning
CN113189624A (en) * 2021-04-30 2021-07-30 中山大学 Adaptive classification multipath error extraction method and device
CN113189624B (en) * 2021-04-30 2023-10-03 中山大学 Self-adaptive classification multipath error extraction method and device
CN113554123A (en) * 2021-09-18 2021-10-26 江苏禹治流域管理技术研究院有限公司 Automatic sand production ship identification method based on acousto-optic linkage
CN118013301A (en) * 2024-04-09 2024-05-10 青岛奥维特智能科技有限公司 BIM-based highway bridge construction information digital management method
CN118013301B (en) * 2024-04-09 2024-06-11 青岛奥维特智能科技有限公司 BIM-based highway bridge construction information digital management method

Similar Documents

Publication Publication Date Title
CN111488801A (en) Ship classification method based on vibration noise identification
CN106778610B (en) Intra-pulse modulation identification method based on time-frequency image characteristics
Liu et al. Deep learning and recognition of radar jamming based on CNN
CN109190673B (en) Ground target classification method based on random forest and data rejection
CN100507971C (en) Independent component analysis based automobile sound identification method
CN101470194B (en) Torpedo target recognition method
CN107830996B (en) Fault diagnosis method for aircraft control surface system
Yang et al. Ship recognition via its radiated sound: The fractal based approaches
CN104795064A (en) Recognition method for sound event under scene of low signal to noise ratio
Yar et al. A complete framework of radar pulse detection and modulation classification for cognitive EW
Yao et al. An adaptive seismic signal denoising method based on variational mode decomposition
CN108919241B (en) Underwater signal time-frequency endpoint parameter estimation method based on constant false alarm detection
Jin et al. Offshore ship recognition based on center frequency projection of improved EMD and KNN algorithm
CN111680737A (en) Radar radiation source individual identification method under differential signal-to-noise ratio condition
Nelson et al. Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting
Zhou et al. An attention-based multi-scale convolution network for intelligent underwater acoustic signal recognition
Ren et al. Automatic modulation recognition for overlapping radar signals based on multi-domain SE-ResNeXt
Xu et al. Individual radio transmitter identification based on spurious modulation characteristics of signal envelop
Astapov et al. A multistage procedure of mobile vehicle acoustic identification for single-sensor embedded device
Socheleau et al. Detection of mysticete calls: a sparse representation-based approach
CN116340812A (en) Transformer partial discharge fault mode identification method and system
CN113095381B (en) Underwater sound target identification method and system based on improved DBN
Changjun et al. The research of vehicle classification using SVM and KNN in a ramp
Li et al. The learned multi-scale deep filters for underwater acoustic target modeling and recognition
CN112788057A (en) LDoS attack detection method based on FSWT time-frequency distribution

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200804

RJ01 Rejection of invention patent application after publication