CN117828405B - Signal positioning method based on intelligent frequency spectrum sensing - Google Patents

Signal positioning method based on intelligent frequency spectrum sensing Download PDF

Info

Publication number
CN117828405B
CN117828405B CN202410203537.1A CN202410203537A CN117828405B CN 117828405 B CN117828405 B CN 117828405B CN 202410203537 A CN202410203537 A CN 202410203537A CN 117828405 B CN117828405 B CN 117828405B
Authority
CN
China
Prior art keywords
signal
signal acquisition
value
acquisition point
identification
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.)
Active
Application number
CN202410203537.1A
Other languages
Chinese (zh)
Other versions
CN117828405A (en
Inventor
郑礼
闫光辉
汤春阳
廉敬
马文涛
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.)
Lanzhou Jiaotong University
Original Assignee
Lanzhou Jiaotong 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 Lanzhou Jiaotong University filed Critical Lanzhou Jiaotong University
Priority to CN202410203537.1A priority Critical patent/CN117828405B/en
Publication of CN117828405A publication Critical patent/CN117828405A/en
Application granted granted Critical
Publication of CN117828405B publication Critical patent/CN117828405B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Testing Relating To Insulation (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a signal positioning method based on intelligent spectrum sensing, and relates to the technical field of electromagnetic signal detection. The original signal in the working process of the transformer is acquired in real time at the position of the signal acquisition point, and the original signal is subjected to power frequency removal through a band-pass filter, wherein the filtering frequency is smaller thanThe kHz signal is used as an identification signal, a judgment model is constructed, whether the partial discharge signal exists or not is judged according to the judgment model and the frequency of the identification signal, when the partial discharge signal exists, the azimuth angle of the identification signal received by a signal acquisition point is acquired, the power of the received identification signal is calculated, the position of the original signal is positioned according to the acquired power value and azimuth angle information, the discharge signal is detected by adopting a passive detection method, the influence of environmental factors on the attenuation degree in the electromagnetic wave transmission process is comprehensively considered, and the detection probability of the discharge signal and the position positioning accuracy of the discharge signal can be improved.

Description

Signal positioning method based on intelligent frequency spectrum sensing
Technical Field
The invention relates to the technical field of electromagnetic signal detection, in particular to a signal positioning method based on intelligent frequency spectrum sensing.
Background
Partial discharge is a complex physical phenomenon, and generally, the types of insulator defect discharge are roughly classified into surface discharge, corona discharge, and hole discharge. Since partial discharge of the transformer is one of the important reasons for insulation damage of the transformer, it is important to monitor partial discharge signals of the transformer in time, discover faults and alarm in time.
The existing monitoring methods of the partial discharge signals of the transformer mainly comprise an electric pulse method, an ultrasonic monitoring method, a radio frequency monitoring method, a chemical monitoring method, an ultrahigh frequency detection method and the like. The ultra-high frequency detection method is widely adopted, noise is filtered out by adopting an ultrasonic sensor with high-pass characteristics and an additional auxiliary circuit to enable a discharge signal to pass, so that partial discharge signals can be detected, and the position of the discharge signal is positioned by adopting a classical electromagnetic wave positioning method such as a ranging positioning method RSSI based on signal intensity, a positioning method AOA based on angle measurement, a ranging positioning method TOA based on transmission time, TWR and SDS-TWR, a ranging positioning method TDOA based on time difference and the like.
However, in the existing positioning method, the influence of environmental factors on electromagnetic wave positioning accuracy is ignored, and according to related researches, environmental factors such as temperature, humidity, air pressure value and the like can cause attenuation of different degrees in the electromagnetic wave transmission process, so that the detection probability of discharge signals is increased, the positioning difficulty of signal sources is increased, and the accuracy of signal positioning is reduced. For this purpose, we propose a signal localization method based on intelligent spectrum sensing.
Disclosure of Invention
The invention mainly aims to provide a signal positioning method based on intelligent frequency spectrum sensing, which can effectively solve the problems in the background technology.
In order to achieve the above purpose, the invention adopts the technical proposal that,
A signal localization method based on intelligent spectrum sensing, comprising,
Setting a signal acquisition point, acquiring an original signal in the working process of the transformer in real time at the position of the signal acquisition point, and carrying out power frequency removal on the original signal by a band-pass filter, wherein the filtering frequency is smaller than that of the original signalKHz signal as identification signal,/>The value range of the signal acquisition points is [45,50], wherein the signal acquisition points are distributed on two sides of the central line of the transformer, the number of the signal acquisition points is at least two, and at least one signal acquisition point and the rest signal acquisition points are not positioned on the same side of the central line of the transformer at the same time;
Constructing a judging model, and judging whether the partial discharge signal exists or not according to the judging model and the frequency of the identification signal, wherein the expression of the judging model is as follows:
；
In the method, in the process of the invention, For/>Frequency of time original signal,/>For judging the fuzzy threshold, the value range is (50, 55), H 1 represents that the partial discharge signal exists, and H 0 represents that the partial discharge signal does not exist;
When the partial discharge signal is judged to exist, the azimuth angle of the identification signal received by the signal acquisition point is acquired, the power of the received identification signal is calculated, and the calculation formula is as follows:
；
In the method, in the process of the invention, Expressed as/>Power of identification signal received by each signal acquisition point,/>Expressed as/>The energy value of the identification signal received by each signal acquisition point, delta t is the sampling time interval of the identification signal, N is the sampling number of the identification signal,/>Expressed as/>Receiving signals at moment, wherein T is a sampling period of the identification signals;
positioning the position of the original signal according to the power value and azimuth information of the identification signal received by each acquired signal acquisition point, wherein the expression of the positioning model is as follows:
；
In the method, in the process of the invention, For/>Power of identification signal received by each signal acquisition point,/>For/>Power of identification signal received by each signal acquisition point,/>For/>Spatial coordinates of the individual signal acquisition points,/>For/>Spatial coordinates of the individual signal acquisition points,/>Is the spatial coordinates of the original signal position,/>Respectively is/>Distance between spatial coordinates of the individual signal acquisition points and the original signal position,/>For/>Signal acquisition Point and/>Distance between signal acquisition points,/>Respectively is/>The azimuth angle between the spatial coordinates of each signal acquisition point and the original signal position, n is a signal propagation factor, and n is related to the signal propagation environment, and the specific determination method comprises the following steps:
s01: under different environmental conditions, by The signal acquisition point is directed to the (th) >The method comprises the steps of transmitting a plurality of groups of test signals by signal acquisition points, obtaining the transmitting power and the receiving power values of the test signals, calculating the signal propagation factor value in the kth environment according to a formula, wherein the calculation formula is as follows:
；
In the method, in the process of the invention, For/>Signal propagation factor value in seed environment,/>For/>Transmitting power value of test signal under seed environment,/>For/>A reception power value of the test signal in the seed environment;
s02: acquiring environmental information parameters during test signal transmission Wherein/>A q-th type environmental information parameter expressed as a kth environment, wherein the environmental information parameter includes at least two of temperature, humidity, barometric pressure value, air index, rainfall, vapor density, barrier density;
S03: normalizing the acquired environment information parameters and signal propagation factor data under different environments, wherein the normalization formula is as follows:
；
wherein D is normalized data, D min,dmax is the minimum value and the maximum value in the data, and D is an un-normalized data value;
S04: taking the normalized environment information parameters as input variables, and taking signal propagation factor values in different normalized environments as output variables to construct a BP neural network model, wherein the number of input layers of the BP neural network model is equal to the number of the environment information parameters, and the calculation formula of the number s of hidden layer nodes is as follows:
；
In the method, in the process of the invention, Training the established neural network model for the integers of the value range [1,9], and adjusting the number of hidden layers of the model according to errors of the training result and the actual alarm result until the accuracy is not lower than an expected value, wherein the calculation formula of the expected value is as follows,
；
Wherein E (Y) represents an expected value; μ represents the number of neural network model input samples; Representing an output function of the neural network model; /(I) Represents the neural network model-And outputting samples, completing the construction of the BP neural network model, and outputting a predicted value of the signal propagation factor value through the neural network model.
The invention has the following advantages that,
Compared with the prior art, the technical scheme of the invention is that the original signal in the working process of the transformer is collected in real time at the position of the signal collection point by setting the signal collection point, and the original signal is subjected to power frequency removal through the band-pass filter, and the filtering frequency is smaller than that of the original signalThe method comprises the steps of taking a kHz signal as an identification signal, constructing a judging model, judging whether a partial discharge signal exists or not according to the judging model and the frequency of the identification signal, acquiring the azimuth angle of the identification signal received by a signal acquisition point when the partial discharge signal exists, calculating the power of the received identification signal, positioning the position of an original signal according to the power value and azimuth angle information of the identification signal received by each acquired signal acquisition point, detecting the discharge signal by adopting a passive detection method, comprehensively considering the influence of environmental factors on attenuation degree in the electromagnetic wave transmission process, and improving the detection probability of the discharge signal and the positioning accuracy of the discharge signal position.
Drawings
FIG. 1 is a flow chart of a signal positioning method based on intelligent spectrum sensing according to the present invention;
FIG. 2 is a state diagram of one of the signal acquisition point settings of the signal positioning method based on intelligent spectrum sensing according to the present invention;
fig. 3 is another state diagram of signal acquisition point setting of the signal positioning method based on intelligent spectrum sensing according to the present invention.
Detailed Description
The present invention will be further described with reference to the following detailed description, wherein the drawings are for illustrative purposes only and are presented as schematic drawings, rather than physical drawings, and are not to be construed as limiting the invention, and wherein certain components of the drawings are omitted, enlarged or reduced in order to better illustrate the detailed description of the present invention, and are not representative of the actual product dimensions.
Example 1
A flow chart of a signal localization method based on intelligent spectrum sensing is shown in fig. 1.
The specific implementation flow of the scheme of the invention comprises the following steps:
Step 1): setting a signal acquisition point, acquiring an original signal in the working process of the transformer in real time at the position of the signal acquisition point, passing the original signal through a band-pass filter, removing power frequency and filtering frequency to be smaller than KHz signal as identification signal,/>The value range of (a) is [45,50], wherein the signal acquisition points are distributed on two sides of the central line of the transformer, the number of the signal acquisition points is at least two, at least one signal acquisition point is not located on the same side of the center of the transformer with the rest signal acquisition points, in this embodiment, two signal acquisition points are set as examples, as shown in fig. 2 and 3, the area S is the location area of the transformer, the point o is the center point of the transformer, A, B is the locations of the two signal acquisition points, and the AB connection line penetrates through the center point o of the transformer;
Step 2): constructing a judging model, and judging whether the partial discharge signal exists or not according to the judging model and the frequency of the identification signal, wherein the expression of the judging model is as follows:
；
In the method, in the process of the invention, For/>Frequency of time original signal,/>For judging the fuzzy threshold, the value range is (50, 55), H 1 represents that the partial discharge signal exists, and H 0 represents that the partial discharge signal does not exist;
Step 3): when the existence of the partial discharge signal is judged, the azimuth angle of the identification signal received by the signal acquisition point is obtained, the power of the received identification signal is calculated, and the calculation formula is as follows:
；
In the method, in the process of the invention, Expressed as/>Power of identification signal received by each signal acquisition point,/>Expressed as/>The energy value of the identification signal received by each signal acquisition point, delta t is the sampling time interval of the identification signal, N is the sampling number of the identification signal,/>Expressed as/>Receiving signals at moment, wherein T is a sampling period of the identification signals;
Step 4): positioning the position of the original signal according to the power value and azimuth information of the identification signal received by each acquired signal acquisition point, wherein the expression of the positioning model is as follows:
；
In the method, in the process of the invention, For/>Power of identification signal received by each signal acquisition point,/>For/>Power of identification signal received by each signal acquisition point,/>For/>Spatial coordinates of the individual signal acquisition points,/>For/>Spatial coordinates of the individual signal acquisition points,/>Is the spatial coordinates of the original signal position,/>Respectively is/>Distance between spatial coordinates of the individual signal acquisition points and the original signal position,/>For/>Signal acquisition Point and/>Distance between signal acquisition points,/>Respectively is/>The azimuth angle between the spatial coordinates of each signal acquisition point and the original signal position, n is a signal propagation factor, and n is related to the signal propagation environment, and the specific determination method comprises the following steps:
S1: under different environmental conditions, by The signal acquisition point is directed to the (th) >The signal acquisition points transmit a plurality of groups of test signals, the transmitting power and the receiving power values of the test signals are obtained, the signal propagation factor value in the kth environment is calculated according to the formula, and the calculation formula is as follows:
；
In the method, in the process of the invention, For/>Signal propagation factor value in seed environment,/>For/>Transmitting power value of test signal under seed environment,/>For/>A reception power value of the test signal in the seed environment;
s2: acquiring environmental information parameters during test signal transmission Wherein/>The q-th environmental information parameter is expressed as a kth environment, wherein the environmental information parameter comprises at least two of temperature, humidity, air pressure value, air index, rainfall, water vapor density and barrier density, and in the embodiment, all the environmental information parameters are taken as study objects to be explained;
s3: normalizing the acquired environment information parameters and signal propagation factor data under different environments, wherein the normalization formula is as follows:
；
wherein D is normalized data, D min,dmax is the minimum value and the maximum value in the data, and D is an un-normalized data value;
S4: the normalized environmental information parameters are used as input variables, the normalized signal propagation factor values in different environments are used as output variables to construct a BP neural network model, wherein the number m of input layers of the BP neural network model is equal to the number of the environmental information parameters, and in the embodiment, the calculation formula of the number s of hidden layer nodes is as follows:
；
In the method, in the process of the invention, Training the established neural network model for the integers of the value range [1,9], and adjusting the number of hidden layers of the model according to errors of the training result and the actual alarm result until the accuracy is not lower than an expected value, wherein the calculation formula of the expected value is as follows,
；
Wherein E (Y) represents an expected value; μ represents the number of neural network model input samples; Representing an output function of the neural network model; /(I) Represents the neural network model-And outputting samples, completing the construction of the BP neural network model, and outputting a predicted value of the signal propagation factor value through the neural network model.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (1)

1. The signal positioning method based on intelligent frequency spectrum sensing is characterized by comprising the following steps of,
Setting a signal acquisition point, acquiring an original signal in the working process of the transformer in real time at the position of the signal acquisition point, and carrying out power frequency removal on the original signal by a band-pass filter, wherein the filtering frequency is smaller than that of the original signalA signal of kHz is used as an identification signal;
Constructing a judging model, and judging whether the partial discharge signal exists or not according to the judging model and the frequency of the identification signal, wherein the expression of the judging model is as follows:
；
In the method, in the process of the invention, For the frequency of the original signal at time t,/>For the decision fuzzy threshold, the unit kHz, H 1, indicates that a partial discharge signal is present, H 0 indicates that a partial discharge signal is not present;
When the partial discharge signal is judged to exist, the azimuth angle of the identification signal received by the signal acquisition point is acquired, the power of the received identification signal is calculated, and the calculation formula is as follows:
；
In the method, in the process of the invention, Expressed as/>Power of identification signal received by each signal acquisition point,/>Expressed as/>The energy value of the identification signal received by the signal acquisition point, deltat is the sampling time interval of the identification signal, N is the sampling number of the identification signal,The received signal is represented as time T, T being the sampling period of the identification signal;
positioning the position of the original signal according to the power value and azimuth information of the identification signal received by each acquired signal acquisition point, wherein the expression of the positioning model is as follows:
；
In the method, in the process of the invention, For/>Power of identification signal received by each signal acquisition point,/>For/>Power of identification signal received by each signal acquisition point,/>For/>Spatial coordinates of the individual signal acquisition points,/>For/>Spatial coordinates of the individual signal acquisition points,/>Is the spatial coordinates of the original signal position,/>Respectively is/>Distance between spatial coordinates of the individual signal acquisition points and the original signal position,/>For/>Signal acquisition Point and/>Distance between signal acquisition points,/>Respectively is/>Azimuth angles between the spatial coordinates of the individual signal acquisition points and the original signal positions, n being a signal propagation factor;
the signal acquisition points are distributed on two sides of the central line of the transformer, the number of the signal acquisition points is at least two, and at least one signal acquisition point and the rest signal acquisition points are not located on the same side of the central line of the transformer at the same time;
the value range of (1) is [45,50], and the fuzzy threshold value/> The value range of (5) is (55, 50);
the method for determining the signal propagation factor n comprises the following steps:
s01: under different environmental conditions, by The signal acquisition point is directed to the (th) >The method comprises the steps of transmitting a plurality of groups of test signals by signal acquisition points, obtaining the transmitting power and the receiving power values of the test signals, calculating the signal propagation factor value in the kth environment according to a formula, wherein the calculation formula is as follows:
；
In the method, in the process of the invention, For/>Signal propagation factor value in seed environment,/>For/>Transmitting power value of test signal under seed environment,/>For/>A reception power value of the test signal in the seed environment;
s02: acquiring environmental information parameters during test signal transmission Wherein/>Expressed as/>First/>, under seed environmentClass environmental information parameters;
S03: normalizing the acquired environment information parameters and signal propagation factor data under different environments, wherein the normalization formula is as follows:
；
wherein D is normalized data, D min,dmax is the minimum value and the maximum value in the data, and D is an un-normalized data value;
s04: constructing a BP neural network model by taking the normalized environment information parameters as input variables and taking signal propagation factor values in different normalized environments as output variables, training the built neural network model, completing the construction of the BP neural network model when the number of hidden layers of the model is adjusted to be not lower than an expected value according to errors of training results and actual alarm results, and outputting predicted values of the signal propagation factor values through the neural network model;
The environmental information parameters comprise at least two of temperature, humidity, air pressure value, air index, rainfall, water vapor density and barrier density;
the number m of the input layers of the BP neural network model is equal to the number of the environment information parameters, and the calculation formula of the number s of hidden layer nodes is as follows:
；
wherein, alpha is an integer in a value range [1,9 ];
the calculation formula of the expected value of the BP neural network model is that,
；
Wherein E (Y) represents an expected value; μ represents the number of neural network model input samples; Representing an output function of the neural network model; x λ represents the lambda output sample of the neural network model.
CN202410203537.1A 2024-02-23 2024-02-23 Signal positioning method based on intelligent frequency spectrum sensing Active CN117828405B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410203537.1A CN117828405B (en) 2024-02-23 2024-02-23 Signal positioning method based on intelligent frequency spectrum sensing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410203537.1A CN117828405B (en) 2024-02-23 2024-02-23 Signal positioning method based on intelligent frequency spectrum sensing

Publications (2)

Publication Number Publication Date
CN117828405A CN117828405A (en) 2024-04-05
CN117828405B true CN117828405B (en) 2024-05-07

Family

ID=90508119

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410203537.1A Active CN117828405B (en) 2024-02-23 2024-02-23 Signal positioning method based on intelligent frequency spectrum sensing

Country Status (1)

Country Link
CN (1) CN117828405B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6442510B1 (en) * 1997-11-17 2002-08-27 Frank Klefenz Method and apparatus for determining transit-time differentials for signal waveforms for real-time pattern recognition, localization and monitoring of optical and acoustic signals
CN102866334A (en) * 2012-10-19 2013-01-09 上海市电力公司 Vehicle-mounted local discharge locating system for mobile substation and locating method thereof
CN107942212A (en) * 2017-11-17 2018-04-20 国网天津市电力公司 A kind of substation's partial discharge positioning method without blur estimation based on spatial spectrum
CN109752633A (en) * 2019-01-28 2019-05-14 国网山东省电力公司日照供电公司 The method and system that a kind of pair of transformer station partial discharge signals are positioned
CN113419216A (en) * 2021-06-21 2021-09-21 南京信息工程大学 Multi-sound-source positioning method suitable for reverberation environment
CN115453300A (en) * 2022-11-11 2022-12-09 国网江苏省电力有限公司泰州供电分公司 Partial discharge positioning system and method based on acoustic sensor array

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6442510B1 (en) * 1997-11-17 2002-08-27 Frank Klefenz Method and apparatus for determining transit-time differentials for signal waveforms for real-time pattern recognition, localization and monitoring of optical and acoustic signals
CN102866334A (en) * 2012-10-19 2013-01-09 上海市电力公司 Vehicle-mounted local discharge locating system for mobile substation and locating method thereof
CN107942212A (en) * 2017-11-17 2018-04-20 国网天津市电力公司 A kind of substation's partial discharge positioning method without blur estimation based on spatial spectrum
CN109752633A (en) * 2019-01-28 2019-05-14 国网山东省电力公司日照供电公司 The method and system that a kind of pair of transformer station partial discharge signals are positioned
CN113419216A (en) * 2021-06-21 2021-09-21 南京信息工程大学 Multi-sound-source positioning method suitable for reverberation environment
CN115453300A (en) * 2022-11-11 2022-12-09 国网江苏省电力有限公司泰州供电分公司 Partial discharge positioning system and method based on acoustic sensor array

Also Published As

Publication number Publication date
CN117828405A (en) 2024-04-05

Similar Documents

Publication Publication Date Title
CN109283248B (en) Board-like structure multi-defect detection method based on DBSCAN and k-means algorithm
CN108601026B (en) Perception data error attack detection method based on random sampling consistency
CN110440148B (en) Method, device and system for classifying and identifying leakage acoustic signals
CN108038419A (en) Wi-Fi-based indoor personnel passive detection method
CN111798869B (en) Sound source positioning method based on double microphone arrays
CN113567969B (en) Illegal sand dredger automatic monitoring method and system based on underwater acoustic signals
CN106382981A (en) Single station infrasonic wave signal recognition and extraction method
CN111046025B (en) Unmanned aerial vehicle signal detection method and device
CN114545387A (en) High-altitude parabolic detection and discrimination method based on millimeter wave radar data fitting
CN117828405B (en) Signal positioning method based on intelligent frequency spectrum sensing
CN113706840A (en) Partial discharge ultrahigh frequency monitoring grading alarm circuit and alarm device and method thereof
CN113781728A (en) Vibration sensing system and method based on group intelligent optimization
CN105044786B (en) Pipe robot very low frequencies signal supervisory instrument based on quadrature coil sensor
CN112594559A (en) Submarine oil pipeline leakage monitoring system and method
CN117116293A (en) Machine equipment fault diagnosis system in complex sound field environment
CN113917409A (en) Broadband interference identification method based on real-time spectrum analysis
CN114518511A (en) Feature-assisted partial discharge point positioning method
JP2000266570A (en) Signal processor for discriminating steady state and unsteady state
CN112526404A (en) Power transformer fault on-line positioning system based on ultrahigh frequency external sensor
CN112834577A (en) Correlation method for judging marine environment magnetic field and seawater conductivity
CN116599867B (en) Internet of things sensor abnormality detection method and system based on dynamic diagram
CN116244627A (en) Magnetic anomaly detection method based on fully-connected neural network
CN114047260B (en) Damage identification method and system based on multi-scale fuzzy entropy
CN117150265B (en) Robust radio frequency signal open set identification method under low signal-to-noise ratio condition
CN113567063A (en) Construction and application method of water supply pipe network leakage noise database

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
GR01 Patent grant
GR01 Patent grant