CN111709445A - Electromagnetic emission element identification method based on frequency spectrum characteristics - Google Patents
Electromagnetic emission element identification method based on frequency spectrum characteristics Download PDFInfo
- Publication number
- CN111709445A CN111709445A CN202010406224.8A CN202010406224A CN111709445A CN 111709445 A CN111709445 A CN 111709445A CN 202010406224 A CN202010406224 A CN 202010406224A CN 111709445 A CN111709445 A CN 111709445A
- Authority
- CN
- China
- Prior art keywords
- electromagnetic emission
- module
- sample
- classification method
- label
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000001228 spectrum Methods 0.000 title description 5
- 238000012360 testing method Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 230000003595 spectral effect Effects 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 31
- 238000007781 pre-processing Methods 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 24
- 238000000295 emission spectrum Methods 0.000 claims description 17
- 238000013145 classification model Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 8
- 230000010355 oscillation Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000011835 investigation Methods 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a method and a device for identifying electromagnetic emission elements based on spectral features, which adopt a unified analysis measure aiming at different types of electromagnetic emission problems, improve the analysis capability of electromagnetic emission test results and the accuracy of classification when a plurality of elements exist simultaneously by extracting the spectral features, classifying and identifying the electromagnetic emission elements and automatically giving out classification and identification results, and overcome the problems of limitation, subjectivity and the like caused by the fact that the current electromagnetic interference investigation mainly depends on engineering experience of technical personnel.
Description
Technical Field
The invention belongs to the technical field of electromagnetic compatibility, and particularly relates to a method and a device for identifying electromagnetic emission elements based on frequency spectrum characteristics.
Background
The objective of an emc test is generally to assess compliance with relevant technical requirements or to investigate interference problems in a particular field. Whether interference investigation or conformity assessment, it is also fundamentally necessary to accurately extract characteristic information in electromagnetic emission spectrograms. Aiming at the difficult problems of difficult analysis, difficult identification and the like of electromagnetic interference of a tested product, in order to establish the relation between the electromagnetic emission of the tested product and an internal interference source, an electromagnetic emission element theory proposed by the electromagnetic compatibility team of Beijing aerospace university indicates that the characteristics of electromagnetic emission test data can be decomposed into four simple basic element characteristics of an analog source, a digital source, a pulse source and a mismatch source, and the characteristics mainly comprise a sinusoidal signal, a square wave signal, a spike signal and an oscillation attenuation signal. The electromagnetic emission test result is usually a spectrogram with a wide frequency band and a large range, electromagnetic emission in the whole frequency band range usually simultaneously comprises a plurality of electromagnetic emission elements, and if the electromagnetic emission elements can be identified from the spectrogram obtained by testing according to characteristic information and clear classification is given, powerful support is provided for standard exceeding analysis and interference troubleshooting.
However, the existing electromagnetic compatibility fault diagnosis mainly depends on engineering experience of technicians and needs rich design experience and good testing capability as guarantees, so how to quickly and accurately extract the electromagnetic emission characteristics of a tested product from a complex electromagnetic emission spectrogram and identify an electromagnetic interference source through spectral feature analysis is a difficult problem to be solved urgently.
Disclosure of Invention
In order to solve the defects of the prior art, the invention breaks through the traditional electromagnetic interference checking mechanism and provides the electromagnetic emission element identification method and device based on the frequency spectrum characteristics. The specific technical scheme of the invention is as follows:
a method for identifying electromagnetic emission elements based on spectral characteristics is characterized by comprising the following steps:
s1: preprocessing electromagnetic emission spectrum data of a tested object;
s2: extracting the characteristics of the data segments preprocessed in the step S1, wherein the characteristics comprise peak information, envelope information and harmonic information;
s3: constructing a sample for the characteristic information extracted from each frequency band in the step S2;
s4: marking the result of the step S3 by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as labels to give corresponding labels;
s5: repeating the steps S1 to S4 to form a training sample;
s6: training the multi-label classification method by using the training sample of the step S5 to obtain a classification model;
s6: repeating the steps S1 to S3 for the electromagnetic emission spectrum data of the tested object to be classified to form a test sample; and inputting the test sample into the classification model obtained in the step S5 to obtain a classification result.
Further, the data preprocessing of step S1 is specifically to smooth noise elimination by least square moving, remove the envelope trend by piecewise interpolation, and process the frequency deviation.
Further, in step S2, envelope information is extracted by using a local maximum value fitting method, and harmonic information is extracted by using a cepstrum analysis method.
Further, the multi-label classification method of step S5 is a multi-label K nearest neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network, or a multi-label classification method based on naive bayes.
An electromagnetic emission element identification device based on spectral characteristics, comprising:
the preprocessing module is used for preprocessing the electromagnetic emission spectrum data of the tested object;
the extraction module is used for extracting the characteristics of the preprocessed data segments, wherein the characteristics comprise peak information, envelope information and harmonic information;
a sample building module for building a sample according to the characteristic information extracted from each frequency band; marking the result of the extraction module by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as tags, and giving out corresponding tags; the electromagnetic emission spectrum data of the tested object is processed by a preprocessing module, an extraction module and a construction sample module to form a training sample; electromagnetic emission spectrum data of a to-be-classified tested object is subjected to preprocessing module, extraction module and sample building module without adding labels to form a test sample;
the training module is used for training the multi-label classification method by using the training samples to obtain a classification model;
and the classification module is used for inputting the test sample into the classification model to obtain a classification result.
Further, the data preprocessing of the preprocessing module specifically includes smoothing and denoising by least square moving, removing an envelope trend by piecewise interpolation, and processing a frequency deviation.
Furthermore, the extraction module extracts envelope information by adopting a local maximum fitting method and extracts harmonic information by adopting a cepstrum analysis method.
Further, the multi-label classification method of the training module is a multi-label K neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network or a multi-label classification method based on naive Bayes.
The invention has the beneficial effects that:
1. the method of the invention carries out feature extraction and electromagnetic emission element classification and identification on the electromagnetic emission spectrogram, can adopt uniform analysis measures aiming at different types of electromagnetic emission problems, and automatically gives classification and identification results. The problems of limitation, subjectivity and the like caused by the fact that the current electromagnetic interference investigation mainly depends on engineering experience of technicians are solved.
2. The invention is easy to be programmed and realized, can be compiled into special software, can automatically give the electromagnetic emission element identification result after selecting the frequency band of the electromagnetic emission spectrogram, and provides an effective means for standard exceeding analysis and electromagnetic interference elimination.
Drawings
In order to illustrate embodiments of the present invention or technical solutions in the prior art more clearly, the drawings which are needed in the embodiments will be briefly described below, so that the features and advantages of the present invention can be understood more clearly by referring to the drawings, which are schematic and should not be construed as limiting the present invention in any way, and for a person skilled in the art, other drawings can be obtained on the basis of these drawings without any inventive effort. Wherein:
FIG. 1 is a flow chart of a method for identifying electromagnetic emission elements based on spectral signatures in accordance with the present invention;
FIG. 2 is a measured electromagnetic emission spectrum of a device according to one embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
A method for identifying electromagnetic emission elements based on spectral characteristics comprises the following steps:
s1: preprocessing electromagnetic emission spectrum data of a tested object; the main purposes are to eliminate environmental noise and background signals, and to remove the influence of envelope trend and frequency deviation on harmonic information.
S2: extracting the characteristics of the data segments preprocessed in the step S1, wherein the characteristics comprise peak information, envelope information and harmonic information; the peak value information refers to frequency points with amplitude values obviously higher than the left side and the right side in the spectrogram and amplitude values corresponding to the frequency points; the envelope information refers to a curve formed by connecting the highest points of amplitudes of different frequencies in a spectrogram; the harmonic information refers to the interval between fundamental frequency or periodic narrowband frequency components contained in harmonic components in a spectrogram.
S3: constructing a sample for the characteristic information extracted from each frequency band in the step S2;
s4: marking the sample by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as labels, and giving out corresponding labels; for the situation that multiple basic elements exist in the same frequency band, multi-label marking is adopted, namely, the same sample corresponds to multiple labels.
S5: repeating the steps S1 to S4 to form a training sample;
s6: training the multi-label classification method by using the training sample of the step S5 to obtain a classification model;
s6: repeating the steps S1 to S3 for the electromagnetic emission spectrum data of the tested object to be classified to form a test sample; the classification algorithm often has high requirements on training samples, and usually requires that the training samples are sufficient and have independent and same distribution with the test samples. Therefore, the number of samples of the four types of electromagnetic emission basic elements is ensured when the training samples are constructed.
S7: and inputting the test sample into the classification model obtained in the step S5 to obtain a classification result.
The data preprocessing of step S1 is specifically to smooth denoising by least square shift, remove the envelope trend by piecewise interpolation, and process the frequency deviation.
Step S2, envelope information is extracted by a local maximum fitting method, harmonic information is extracted by a cepstrum analysis method, a peak-trough distance threshold is set after an extreme point is obtained based on a known peak extraction method, and peak information meeting a threshold condition is reserved.
The multi-label classification method of step S5 is a multi-label K nearest neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network, or a multi-label classification method based on naive bayes.
An electromagnetic emission element identification device based on spectral features, comprising:
the preprocessing module is used for preprocessing the electromagnetic emission spectrum data of the tested object;
the extraction module is used for extracting the characteristics of the preprocessed data segments, wherein the characteristics comprise peak information, envelope information and harmonic information;
a sample building module for building a sample according to the characteristic information extracted from each frequency band; marking the result of the extraction module by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as tags, and giving out corresponding tags; the electromagnetic emission spectrum data of the tested object is processed by a preprocessing module, an extraction module and a construction sample module to form a training sample; electromagnetic emission spectrum data of a to-be-classified tested object is subjected to preprocessing module, extraction module and sample building module without adding labels to form a test sample;
the training module is used for training the multi-label classification method by using the training samples to obtain a classification model;
and the classification module is used for inputting the test sample into the classification model to obtain a classification result.
The data preprocessing of the preprocessing module specifically comprises smoothing and denoising through least square movement, removing an envelope trend through piecewise interpolation and processing frequency deviation.
The extraction module extracts envelope information by adopting a local maximum value fitting method and extracts harmonic information by adopting a cepstrum analysis method.
The multi-label classification method of the training module is a multi-label K neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network or a multi-label classification method based on naive Bayes.
For the convenience of understanding the above technical aspects of the present invention, the following detailed description will be given of the above technical aspects of the present invention by way of specific examples.
Example 1
(1) Constructing training samples
The first step is as follows: preprocessing electromagnetic emission spectrum data of a tested product, removing an envelope trend through least square moving smoothing and noise elimination and piecewise interpolation, and processing frequency deviation;
the second step is that: carrying out feature extraction on the preprocessed data in a segmented mode, extracting envelope information by adopting a local maximum fitting method, extracting harmonic information by adopting cepstrum analysis, setting a peak-to-trough distance threshold value after acquiring an extreme point on the basis of a known peak extraction method, and keeping peak information meeting a threshold value condition;
the third step: and constructing a sample for the characteristic information extracted from each frequency band in the second step, and giving a corresponding label according to whether the characteristic information contains four types of electromagnetic emission basic elements, namely square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals.
(2) Construction of test specimens
And (3) taking the actually measured radiation emission test data of the equipment in the figure 2 as an analysis object to construct a test sample. As can be seen from FIG. 2, the tested device has significant emissions in both the frequency bands of 1MHz to 10MHz and 50MHz to 1 GHz. The method comprises the steps of preprocessing frequency spectrum data, and then respectively constructing test samples for the data of the two frequency bands.
a) Constructing test sample with frequency range of 1MHz-10MHz
Drawing a spectrogram of 1MHz-10MHz through Matlab software, carrying out peak extraction, envelope extraction and harmonic extraction on the spectrogram to form a test sample, and storing the test sample in a mat file of a Matlab program.
b) Construction of test sample with frequency band of 50MHz-1GHz
Drawing a 50MHz-1GHz spectrogram through Matlab software, carrying out peak extraction, envelope extraction and harmonic extraction on the spectrogram to form a test sample, and additionally storing the sample into a mat file of a Matlab program to form a second test sample.
(3) Training multi-label classification method
Since the electromagnetic emission spectrogram may have multiple basic elements in the same frequency band, a multi-tag classification method is adopted. The multi-label classification method that can be used includes, but is not limited to, multi-label K-nearest neighbor classification method, multi-label classification method based on support vector machine, multi-label classification method based on artificial neural network, and multi-label classification method based on naive bayes. And training the multi-label classification method by using the training samples to generate a classification model.
(4) And inputting the test sample to be classified into the classification model to obtain a classification result.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method for identifying electromagnetic emission elements based on spectral characteristics is characterized by comprising the following steps:
s1: preprocessing electromagnetic emission spectrum data of a tested object;
s2: extracting the characteristics of the data segments preprocessed in the step S1, wherein the characteristics comprise peak information, envelope information and harmonic information;
s3: constructing a sample for the characteristic information extracted from each frequency band in the step S2;
s4: marking the result of the step S3 by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as labels to give corresponding labels;
s5: repeating the steps S1 to S4 to form a training sample;
s6: training the multi-label classification method by using the training sample of the step S5 to obtain a classification model;
s6: repeating the steps S1 to S3 for the electromagnetic emission spectrum data of the tested object to be classified to form a test sample; and inputting the test sample into the classification model obtained in the step S5 to obtain a classification result.
2. The method for identifying electromagnetic emission elements based on spectral features of claim 1, wherein the data preprocessing of step S1 is to smooth noise elimination by least square moving, remove envelope trend by piecewise interpolation, and process frequency deviation.
3. The method for identifying electromagnetic emission elements based on spectral features of claim 1, wherein step S2 employs local maximum value fitting method to extract envelope information, and employs cepstrum analysis method to extract harmonic information.
4. The method for identifying electromagnetic emission elements based on spectral features of claim 1, wherein the multi-label classification method of step S5 is a multi-label K nearest neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network, or a multi-label classification method based on naive bayes.
5. An electromagnetic emission element identification device based on spectral characteristics, comprising:
the preprocessing module is used for preprocessing the electromagnetic emission spectrum data of the tested object;
the extraction module is used for extracting the characteristics of the preprocessed data segments, wherein the characteristics comprise peak information, envelope information and harmonic information;
a sample building module for building a sample according to the characteristic information extracted from each frequency band; marking the result of the extraction module by using four types of electromagnetic emission basic elements of square wave signals, sinusoidal signals, spike signals and oscillation attenuation signals as tags, and giving out corresponding tags; the electromagnetic emission spectrum data of the tested object is processed by a preprocessing module, an extraction module and a construction sample module to form a training sample; electromagnetic emission spectrum data of a to-be-classified tested object is subjected to preprocessing module, extraction module and sample building module without adding labels to form a test sample;
the training module is used for training the multi-label classification method by using the training samples to obtain a classification model;
and the classification module is used for inputting the test sample into the classification model to obtain a classification result.
6. The device for identifying electromagnetic emission elements based on spectral features of claim 5, wherein the data preprocessing module is configured to perform data preprocessing, specifically, smoothing and denoising by least square shift, removing envelope trend by piecewise interpolation, and processing frequency deviation.
7. The device for identifying electromagnetic emission elements based on spectral features of claim 5, wherein the extracting module extracts envelope information by local maximum fitting and extracts harmonic information by cepstrum analysis.
8. The device according to claim 5, wherein the multi-label classification method of the training module is a multi-label K-nearest neighbor classification method, a multi-label classification method based on a support vector machine, a multi-label classification method based on an artificial neural network, or a multi-label classification method based on naive Bayes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010406224.8A CN111709445A (en) | 2020-05-14 | 2020-05-14 | Electromagnetic emission element identification method based on frequency spectrum characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010406224.8A CN111709445A (en) | 2020-05-14 | 2020-05-14 | Electromagnetic emission element identification method based on frequency spectrum characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111709445A true CN111709445A (en) | 2020-09-25 |
Family
ID=72537247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010406224.8A Pending CN111709445A (en) | 2020-05-14 | 2020-05-14 | Electromagnetic emission element identification method based on frequency spectrum characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709445A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591677A (en) * | 2021-07-28 | 2021-11-02 | 厦门熵基科技有限公司 | Contraband identification method and device, storage medium and computer equipment |
| CN116150594A (en) * | 2023-04-18 | 2023-05-23 | 长鹰恒容电磁科技(成都)有限公司 | Method for identifying switch element characteristics in spectrum test data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106443182A (en) * | 2016-09-08 | 2017-02-22 | 北京航空航天大学 | Spectrum feature-based tested object electromagnetic emission amplitude spectrum data classification method |
| CN106485209A (en) * | 2016-09-23 | 2017-03-08 | 北京航空航天大学 | Non-stationary electromagnetic interference signal mode identification method based on EEMD feature extraction and PNN |
| CN106533591A (en) * | 2016-12-02 | 2017-03-22 | 上海无线电设备研究所 | Electromagnetic interference identification method for small base station |
| CN109034054A (en) * | 2018-07-24 | 2018-12-18 | 华北电力大学 | Harmonic wave multi-tag classification method based on LSTM |
| EP3564698A1 (en) * | 2018-05-02 | 2019-11-06 | Rohde & Schwarz GmbH & Co. KG | Method for classifying electromagnetic signals and analysing system |
-
2020
- 2020-05-14 CN CN202010406224.8A patent/CN111709445A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106443182A (en) * | 2016-09-08 | 2017-02-22 | 北京航空航天大学 | Spectrum feature-based tested object electromagnetic emission amplitude spectrum data classification method |
| CN106485209A (en) * | 2016-09-23 | 2017-03-08 | 北京航空航天大学 | Non-stationary electromagnetic interference signal mode identification method based on EEMD feature extraction and PNN |
| CN106533591A (en) * | 2016-12-02 | 2017-03-22 | 上海无线电设备研究所 | Electromagnetic interference identification method for small base station |
| EP3564698A1 (en) * | 2018-05-02 | 2019-11-06 | Rohde & Schwarz GmbH & Co. KG | Method for classifying electromagnetic signals and analysing system |
| CN109034054A (en) * | 2018-07-24 | 2018-12-18 | 华北电力大学 | Harmonic wave multi-tag classification method based on LSTM |
Non-Patent Citations (1)
| Title |
|---|
| DONGLIN SU 等: "Basic Emission Waveform Theory: A Novel Interpretation and Source Identification Method for Electromagnetic Emission of Complex Systems", 《IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591677A (en) * | 2021-07-28 | 2021-11-02 | 厦门熵基科技有限公司 | Contraband identification method and device, storage medium and computer equipment |
| CN116150594A (en) * | 2023-04-18 | 2023-05-23 | 长鹰恒容电磁科技(成都)有限公司 | Method for identifying switch element characteristics in spectrum test data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985279B (en) | Fault diagnosis method and device for MVB waveform of multifunctional vehicle bus | |
| CN103645425B (en) | High-voltage cable insulation defect partial discharge on-line monitoring diagnosis method | |
| Murthy et al. | Insulator condition analysis for overhead distribution lines using combined wavelet support vector machine (SVM) | |
| Chan et al. | Time-frequency sparsity map on automatic partial discharge sources separation for power transformer condition assessment | |
| CN101334434B (en) | Electromagnetic environment test system for extracting electromagnetic leakage signal by utilizing wavelet transformation | |
| CN109375060B (en) | Method for calculating fault waveform similarity of power distribution network | |
| CN111709445A (en) | Electromagnetic emission element identification method based on frequency spectrum characteristics | |
| JP2012251851A (en) | Abnormal sound diagnosis apparatus | |
| CN106371002A (en) | Circuit breaker fault diagnosis method based on Hilbert-Huang transform algorithm | |
| CN108303255A (en) | Low-speed heave-load device Fault Diagnosis of Roller Bearings, equipment and medium | |
| Jaber et al. | A simulation of non-stationary signal analysis using wavelet transform based on LabVIEW and Matlab | |
| CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
| CN104125050A (en) | Ultrahigh-frequency RFID (radio frequency identification) reader protocol conformance testing method | |
| CN116223962B (en) | Method, device, equipment and medium for predicting electromagnetic compatibility of wire harness | |
| CN112881879A (en) | High-voltage cable terminal partial discharge mode identification method, device and equipment | |
| CN102680080B (en) | Unsteady-state signal detection method based on improved self-adaptive morphological filtering | |
| CN116773961A (en) | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis | |
| CN112729531B (en) | Fault studying and judging method and system for distribution transformer equipment | |
| CN102725631A (en) | Cluster analysis system and method to improve sorting performance | |
| Kumar et al. | Classification of PD faults using features extraction and K-means clustering techniques | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| CN109357751B (en) | Power transformer winding looseness defect detection system | |
| Zhao et al. | Research on a vibration signal analysis method for motor bearing | |
| Yan et al. | Research on fault diagnosis method of bogie bearing based on microphone arrays | |
| Bhukya et al. | Wavelet Aided Deep Neural Network for Classification of Partial Discharge Sources in Air Insulated Substations |
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: 20200925 |
|
| RJ01 | Rejection of invention patent application after publication |