CN115602194A - Self-adaptive water pipe leakage detection method and device and storage medium - Google Patents

Self-adaptive water pipe leakage detection method and device and storage medium Download PDF

Info

Publication number
CN115602194A
CN115602194A CN202211576081.0A CN202211576081A CN115602194A CN 115602194 A CN115602194 A CN 115602194A CN 202211576081 A CN202211576081 A CN 202211576081A CN 115602194 A CN115602194 A CN 115602194A
Authority
CN
China
Prior art keywords
pipe
depth
frequency domain
vector
buried
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.)
Granted
Application number
CN202211576081.0A
Other languages
Chinese (zh)
Other versions
CN115602194B (en
Inventor
梁帆
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.)
Guangdong Prophet Big Data Co ltd
Original Assignee
Dongguan Prophet Big Data Co ltd
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 Dongguan Prophet Big Data Co ltd filed Critical Dongguan Prophet Big Data Co ltd
Priority to CN202211576081.0A priority Critical patent/CN115602194B/en
Publication of CN115602194A publication Critical patent/CN115602194A/en
Application granted granted Critical
Publication of CN115602194B publication Critical patent/CN115602194B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
    • F17D—PIPE-LINE SYSTEMS; PIPE-LINES
    • F17D5/00—Protection or supervision of installations
    • F17D5/02—Preventing, monitoring, or locating loss
    • F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M3/00—Investigating fluid-tightness of structures
    • G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
    • G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
    • G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
    • G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
    • G01S11/14—Systems for determining distance or velocity not using reflection or reradiation using ultrasonic, sonic, or infrasonic waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
    • G01S5/22—Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Pathology (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Mathematical Physics (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Examining Or Testing Airtightness (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)

Abstract

The application discloses a self-adaptive water pipe leakage detecting method, a self-adaptive water pipe leakage detecting device and a storage medium, which are used for accurately detecting the water leakage position of a water pipe. The application discloses a self-adaptation water pipe leakage detection method includes: determining a standard frequency domain feature vector of a predetermined material at a predetermined depth; determining a detection frequency domain vector according to a sound signal transmitted from a water pipe collected in a predetermined area; determining a feature extraction vector according to the standard frequency domain feature vector; calculating matching scores of the detection frequency domain vector and the feature extraction vector; determining the material of the detected water pipe and the depth of the buried pipe according to the matching score; calculating according to the standard frequency domain feature vector corresponding to the buried pipe depth to obtain a signal impact score; and detecting whether the water pipe leaks or not according to the signal impact score. The application also provides a self-adaptive water pipe leakage detecting device and a storage medium.

Description

Self-adaptive water pipe leakage detecting method and device and storage medium
Technical Field
The application relates to the technical field of computing, in particular to a self-adaptive water pipe leakage detecting method and device and a storage medium.
Background
The water supply pipe is one of the main influence factors of the leakage of the pipe network, and the pipe is different in form and degree of leakage. Before the water leakage detection work, a leakage detector needs to clearly know the conditions of the material, the pipe diameter, the burial depth, the water pressure and the like of the underground pipeline and select a leakage detection instrument. However, when the pipe and the buried depth are not clear, the leakage cannot be accurately detected. A multi-scene self-adaptive water pipe leakage detection method is urgently needed to solve the technical problem of accurate leakage detection of different pipes under different burial depths.
Disclosure of Invention
In view of the above technical problems, embodiments of the present application provide a method, an apparatus, and a storage medium for adaptive water pipe leakage detection, so as to accurately detect leakage of different pipes and different burial depths.
In a first aspect, an adaptive water pipe leakage detecting method provided in an embodiment of the present application includes:
determining a standard frequency domain feature vector of a predetermined material at a predetermined depth;
determining a detection frequency domain vector according to the sound signal transmitted from the water pipe collected in the preset area;
determining a feature extraction vector according to the standard frequency domain feature vector;
calculating matching scores of the detection frequency domain vector and the feature extraction vector;
determining the material of the detected water pipe and the depth of the buried pipe according to the matching score;
calculating according to the standard frequency domain feature vector corresponding to the buried pipe depth to obtain a signal impact score;
and detecting whether the water pipe leaks or not according to the signal impact score.
In the present invention, the predetermined material includes one of: galvanized pipe, cement pipe, PVC pipe, PE pipe, pig iron pipe.
Preferably, the predetermined depth is a preset buried depth of the water pipe; the predetermined depths include a first predetermined depth of 0.35 meters, a second predetermined depth of 0.4 meters, and a third predetermined depth of 0.45 meters.
Preferably, the determining the standard frequency domain feature vector of the predetermined material at the predetermined depth includes:
collecting sound signals when a water pipe made of a predetermined material and arranged at a predetermined burying depth does not leak water, wherein the time length of each section of collected sound signals is
Figure 727459DEST_PATH_IMAGE001
；
Processing each section of sound signal to obtain frequency domain information of each section of sound signal, wherein the frequency interval of the frequency domain information is
Figure 213935DEST_PATH_IMAGE002
；
Dividing said frequency interval into equal lengths
Figure 770819DEST_PATH_IMAGE003
Obtaining the maximum amplitude value according to the amplitude value in each frequency subinterval, and dividing the maximum amplitude value into a plurality of frequency subintervals
Figure 506693DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 174435DEST_PATH_IMAGE004
Wherein i is 1 or more and 1 or less
Figure 312155DEST_PATH_IMAGE003
，
Figure 508782DEST_PATH_IMAGE005
The maximum value of the amplitude value in the ith frequency subinterval is shown as x, and the number x is the number of the standard frequency domain feature vector and represents the number of the standard frequency domain feature vector of the specific material at the specific depth;
deriving a second frequency from said frequency eigenvectorA rate feature vector, wherein the second frequency feature vector is
Figure 731952DEST_PATH_IMAGE006
And is made of
Figure 937806DEST_PATH_IMAGE007
，
Figure 930033DEST_PATH_IMAGE008
Is a set first judgment threshold value;
determining a set of spatial feature coordinates of the second frequency feature vector
Figure 625456DEST_PATH_IMAGE009
；
The spatial characteristic coordinate sets of all frequency domain information form a full data characteristic coordinate set
Figure 335923DEST_PATH_IMAGE010
；
For the full data characteristic coordinate set
Figure 79888DEST_PATH_IMAGE011
Clustering the inner elements to obtain corresponding cluster center coordinate set
Figure 395463DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 996209DEST_PATH_IMAGE013
；
Determining standard frequency domain characteristic vector of the preset material at the preset depth according to the cluster center coordinate set
Figure 193972DEST_PATH_IMAGE014
；
wherein
Figure 741628DEST_PATH_IMAGE015
Int () is a rounding function;
Figure 708447DEST_PATH_IMAGE016
is a frequency subinterval number of 1 to n 1 Is an integer of (1).
Preferably, the number x of the standard frequency domain feature vector includes:
x is equal to 1 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.35m;
x is equal to 2 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.4m;
x is equal to 3 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.45 m;
x is equal to 4 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.35m;
x is equal to 5 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.4m;
x is equal to 6 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.45 m;
x is equal to 7 and represents the standard frequency domain feature vector of the cement pipe at the buried depth of 0.35m;
x is equal to 8 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.4m;
x is equal to 9 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.45 m;
x is equal to 10 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.35m;
x is equal to 11 and represents the standard frequency domain characteristic vector of the PVC pipe at the buried depth of 0.4m;
x is equal to 12 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.45 m;
x is equal to 13 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.35m;
x is equal to 14 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.4m;
x equals 15 representing the standard frequency domain feature vector of the pig iron pipe at a buried depth of 0.45m.
Preferably, the determining a detection frequency domain vector according to the sound signal transmitted from the water pipe collected in the predetermined area includes:
obtaining corresponding frequency domain information according to the sound signal transmitted from the water pipe collected in the preset detection area, and according to the set frequency interval
Figure 683356DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 102836DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval constitutes the detection frequency domain vector
Figure 454183DEST_PATH_IMAGE017
；
wherein ,
Figure 275509DEST_PATH_IMAGE018
is the maximum value of the signal amplitude of the jth subinterval.
Preferably, the determining a feature extraction vector according to the standard frequency domain feature vector includes:
the feature extraction vector is:
Figure 686898DEST_PATH_IMAGE019
)；
wherein ,
Figure 859254DEST_PATH_IMAGE020
。
preferably, the calculating the matching score of the detection frequency domain vector and the feature extraction vector comprises:
the matching score is as follows:
Figure 748712DEST_PATH_IMAGE021
；
wherein ,
Figure 690123DEST_PATH_IMAGE022
,
Figure 272415DEST_PATH_IMAGE023
,
Figure 666487DEST_PATH_IMAGE024
,
q is a material number, 1 represents a PE pipe, 2 represents a galvanized pipe, 3 represents a cement pipe, 4 represents a PVC pipe, and 5 represents a pig iron pipe.
Preferably, the determining the material of the detected water pipe and the depth of the buried pipe according to the matching score includes:
when in use
Figure 94057DEST_PATH_IMAGE025
Then, the water pipe is judged to be of the q-th material, wherein
Figure 624396DEST_PATH_IMAGE026
A threshold value is determined for a matching score range between the training real data and the standard vector according to the historical data;
if it is
Figure 377588DEST_PATH_IMAGE027
Judging that the buried pipe depth is a second preset depth;
if it is
Figure 258956DEST_PATH_IMAGE028
Judging that the depth of the buried pipe is a first preset depth;
if it is
Figure 552534DEST_PATH_IMAGE029
The buried pipe depth is determined to be a third predetermined depth.
The step of calculating and obtaining the signal impact score according to the standard frequency domain feature vector corresponding to the pipe burying depth comprises the following steps:
based on detected frequency domain vector
Figure 202959DEST_PATH_IMAGE017
And calculating a standard frequency domain feature vector corresponding to the depth of the corresponding buried pipe to obtain a signal impact score:
Figure 861473DEST_PATH_IMAGE030
；
wherein
Figure 964558DEST_PATH_IMAGE031
In order to be an index of the difference in signal,
Figure 999510DEST_PATH_IMAGE032
is the peak impact index, and:
Figure 770020DEST_PATH_IMAGE033
；
when the buried pipe depth is a first preset depth:
Figure 396174DEST_PATH_IMAGE034
，
Figure 252134DEST_PATH_IMAGE035
;
Figure 825198DEST_PATH_IMAGE036
is a buried depth influence index;
when the buried pipe depth is a second preset depth:
Figure 184635DEST_PATH_IMAGE037
,
Figure 247269DEST_PATH_IMAGE038
,
Figure 59367DEST_PATH_IMAGE039
；
when the buried pipe depth is a third predetermined depth:
Figure 701701DEST_PATH_IMAGE037
，
Figure 181224DEST_PATH_IMAGE040
，
Figure 414759DEST_PATH_IMAGE041
。
preferably, the detecting whether water leakage occurs in the water pipe according to the signal impact score includes:
when signal impact score
Figure 714154DEST_PATH_IMAGE042
Sometimes judging the abnormality of the water pipe at the detection position, wherein
Figure 894599DEST_PATH_IMAGE043
Is a set third judgment threshold;
when the abnormal water pipe at the detection position is judged, two signals are collected m meters before and after the abnormal water pipe position and are respectively calculated to obtain corresponding signal impact scores
Figure 25366DEST_PATH_IMAGE044
And
Figure 633065DEST_PATH_IMAGE045
when is coming into contact with
Figure 419756DEST_PATH_IMAGE046
and
Figure 138313DEST_PATH_IMAGE047
And judging that the water pipe at the detection position leaks water.
In a second aspect, an embodiment of the present application further provides an adaptive water pipe leakage detection device, including:
a vector determination module configured to determine a standard frequency domain feature vector of a predetermined material at a predetermined depth;
the depth determination module is configured for determining a detection frequency domain vector according to a sound signal transmitted by the water pipe collected in a preset area, determining a feature extraction vector according to the standard frequency domain feature vector, calculating a matching score of the detection frequency domain vector and the feature extraction vector, and determining the material and the pipe burying depth of the detection water pipe according to the matching score;
and the judging module is configured for calculating to obtain a signal impact score according to the standard frequency domain feature vector corresponding to the buried pipe depth, and detecting whether the water pipe leaks or not according to the signal impact score.
In a third aspect, an embodiment of the present application further provides a self-adaptive water pipe leakage detection device, including: a memory, a processor, and a user interface;
the memory for storing a computer program;
the user interface is used for realizing interaction with a user;
the processor is used for reading the computer program in the memory, and when the processor executes the computer program, the self-adaptive water pipe leakage detecting method provided by the invention is realized.
In a fourth aspect, an embodiment of the present invention further provides a processor-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the adaptive water pipe leakage detection method provided by the present invention is implemented.
By using the self-adaptive water pipe leakage detection method, firstly, the standard frequency domain characteristic vector of a preset material under a preset depth is used as a standard reference for subsequent detection. Then, the sound signal transmitted from the water pipe collected in the predetermined area determines a detection frequency domain vector according to the sound signal. And finally, detecting whether water leakage occurs in the water pipe in the preset area or not according to matching calculation of the detection frequency domain vector and the standard frequency domain characteristic vector. The method solves the technical problem of accurate leakage detection under different buried depths of different pipes.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a leakage detection method for a self-adaptive water pipe according to an embodiment of the present invention;
fig. 2 is a schematic view of an adaptive water pipe leakage detecting device according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of another adaptive water pipe leakage detection device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Some of the words that appear in the text are explained below:
1. in the embodiment of the present invention, the term "and/or" describes an association relationship of an associated object, and indicates that three relationships may exist, for example, a and/or B, and may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
2. In the embodiments of the present application, the term "plurality" means two or more, and other terms are similar thereto.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the display sequence of the embodiment of the present application only represents the sequence of the embodiment, and does not represent the merits of the technical solutions provided by the embodiments.
Referring to fig. 1, a schematic diagram of an adaptive water pipe leakage detection method provided in an embodiment of the present application is shown in fig. 1, where the method includes steps S101 to S107:
s101, determining a standard frequency domain feature vector of a predetermined material at a predetermined depth;
in the present invention, the predetermined material is a material for manufacturing the water pipe, and may be, for example, one of a galvanized pipe, a cement pipe, a PVC pipe, a PE pipe, and a pig iron pipe, or may be another material.
The predetermined depth is a preset buried depth of the water pipe. Preferably, the buried depth may be a plurality of depths, such as a first predetermined depth, a second predetermined depth, and a third predetermined depth. As a preferred example, the first predetermined depth is 0.35 meters, the second predetermined depth is 0.4 meters, and the third predetermined depth is 0.45 meters. The predetermined depth may also include other buried depths, such as a fourth predetermined depth of 0.3 m, a fifth predetermined depth of 0.5 m, a sixth predetermined depth of 0.55 m, etc., specifically including the number of predetermined depths and specific values for each predetermined depth, which is not limited in this application.
As a preferred example, in order to uniformly describe the standard frequency domain feature vector for determining the predetermined material at the predetermined depth, the predetermined material and the predetermined depth may be jointly numbered to form the standard frequency domain feature vector representing the combination of the predetermined material and the predetermined depth, that is, x represents the number of the specific material at the specific depth, and the standard frequency domain feature vector of the number x may uniquely represent the standard frequency domain feature vector of the specific material at the specific depth. For example, if the predetermined materials include five types of pipes, i.e., PE pipe, galvanized pipe, cement pipe, PVC pipe, and pig iron pipe, and the predetermined depths include a first predetermined depth of 0.35m, a second predetermined depth of 0.4m, and a third predetermined depth of 0.45m, a total of 3 × 5=15 combinations can be represented in the following table:
TABLE 1 Combined numbering List I
Value of x A first predetermined depth A second predetermined depth A third predetermined depth
PE pipe 1 2 3
Galvanized pipe 4 5 6
Cement pipe 7 8 9
PVC pipe 10 11 12
Pig iron pipe 13 14 15
I.e. the combination number x can be expressed as:
x is equal to 1 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.35m;
x is equal to 2 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.4m;
x is equal to 3 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.45 m;
x is equal to 4 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.35 meter;
x is equal to 5 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.4 meter;
x is equal to 6 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.45 m;
x is equal to 7 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.35 meter;
x is equal to 8 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.4m;
x is equal to 9 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.45 meter;
x is equal to 10 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.35m;
x is equal to 11 and represents the standard frequency domain characteristic vector of the PVC pipe at the buried depth of 0.4m;
x is equal to 12 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.45 m;
x is equal to 13 and represents the standard frequency domain characteristic vector of the pig iron pipe at the buried depth of 0.35 meter;
x is equal to 14 and represents the standard frequency domain characteristic vector of the pig iron pipe at the buried depth of 0.4m;
x equals 15 represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.45 meter.
For another example, if the predetermined material includes 7 kinds of pipes, including a PE pipe, a galvanized pipe, a cement pipe, a PVC pipe, a pig iron pipe, a copper pipe, and an aluminum alloy pipe, and the predetermined depths include 6 kinds, including a first predetermined depth of 0.35m, a second predetermined depth of 0.4m, a third predetermined depth of 0.45m, a fourth predetermined depth of 0.3 m, a fifth predetermined depth of 0.5 m, and a sixth predetermined depth of 0.55 m, 7 x 6=42 combinations in total, the combination number x may be represented as:
TABLE 2 Combined numbering table II
Value of x A first predetermined depth A second predetermined depth A third predetermined depth A fourth predetermined depth A fifth predetermined depth A sixth predetermined depth
PE pipe 1 2 3 4 5 6
Galvanized pipe 7 8 9 10 11 12
Cement pipe 13 14 15 16 17 18
PVC pipe 19 20 21 22 23 24
Pig iron pipe 25 26 27 28 29 30
Copper pipe 31 32 33 34 35 36
Aluminum alloy pipe 37 38 39 40 41 42
Based on the table, the numbers of different materials at different depths can be known, and further, the standard frequency domain feature vectors of different materials at different depths can be represented, for example, 41 represents the standard frequency domain feature vector of the aluminum alloy pipe at the fifth predetermined depth, and 16 represents the standard frequency domain feature vector of the cement pipe at the fourth predetermined depth.
As a preferred example, the method for determining the standard frequency domain feature vector of the predetermined material at the predetermined depth may be as follows:
a1: collecting sound signals when a water pipe made of a predetermined material and buried at a predetermined depth does not leak water, wherein the duration of each section of collected sound signals is
Figure 389166DEST_PATH_IMAGE001
；
A2: processing each section of sound signal to obtain frequency domain information of each section of sound signal, wherein the frequency interval of the frequency domain information is
Figure 167766DEST_PATH_IMAGE002
；
A3: dividing said frequency interval into equal length
Figure 441752DEST_PATH_IMAGE003
Obtaining the maximum amplitude value according to the amplitude value in each frequency subinterval, and dividing the maximum amplitude value into a plurality of frequency subintervals
Figure 760738DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 69360DEST_PATH_IMAGE004
Wherein i is 1 or more and 1 or less
Figure 753282DEST_PATH_IMAGE003
，
Figure 514565DEST_PATH_IMAGE005
In the ith frequency sub-intervalThe maximum value of the amplitude value, x is the number of the standard frequency domain feature vector, and the number x represents the number of the standard frequency domain feature vector of the specific material at the specific depth;
a4: obtaining a second frequency feature vector according to the frequency feature vector, wherein the second frequency feature vector is
Figure 637241DEST_PATH_IMAGE006
And is made of
Figure 800369DEST_PATH_IMAGE007
，
Figure 655193DEST_PATH_IMAGE008
Is a set first judgment threshold value;
a5: determining a set of spatial feature coordinates of the second frequency feature vector
Figure 966089DEST_PATH_IMAGE009
；
A6: the spatial characteristic coordinate sets of all frequency domain information form a full data characteristic coordinate set
Figure 830139DEST_PATH_IMAGE010
；
A7: for the full data characteristic coordinate set
Figure 582195DEST_PATH_IMAGE011
Clustering the inner elements to obtain corresponding cluster center coordinate set
Figure 139078DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 874953DEST_PATH_IMAGE013
；
A8: determining standard frequency domain characteristic vector of the preset material at the preset depth according to the cluster center coordinate set
Figure 339432DEST_PATH_IMAGE014
；
wherein
Figure 211573DEST_PATH_IMAGE048
Int () is a rounding function;
Figure 673779DEST_PATH_IMAGE049
is a frequency subinterval number of 1 to n 1 Is an integer of (2).
As a preferred example, the determining a detection frequency domain vector according to the sound signal transmitted from the water pipe collected in the predetermined area includes:
obtaining corresponding frequency domain information according to the sound signal transmitted from the water pipe collected in the preset detection area, and according to the set frequency interval
Figure 693687DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 899541DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval forms the detection frequency domain vector
Figure 626188DEST_PATH_IMAGE017
；
wherein ,
Figure 536593DEST_PATH_IMAGE018
is the maximum value of the signal amplitude of the jth subinterval.
As a preferable example, the determining the feature extraction vector according to the standard frequency domain feature vector comprises:
the feature extraction vector is:
Figure 981481DEST_PATH_IMAGE019
)；
wherein ,
Figure 787763DEST_PATH_IMAGE020
。
taking the PE pipe as an example, the following describes the determination of the standard frequency domain feature vector of the predetermined material at the predetermined depth.
The preset material is a PE pipe, the preset depth is a first preset depth of 0.35m, and the standard frequency domain feature vector of the PE pipe at the buried depth of 0.35m needs to be determined. Assuming a total of 5 predetermined materials and 3 predetermined depths, i.e. numbering according to table 1 above, the PE pipe has a standard frequency domain feature vector number of 1 at the first predetermined depth of 0.35m, i.e. x =1.
The duration of each acquired signal is set as
Figure 900075DEST_PATH_IMAGE001
(for example:
Figure 438504DEST_PATH_IMAGE050
the unit is: second), processing each sound signal to obtain frequency domain information (each frequency and corresponding amplitude) of each sound signal, and setting a frequency interval
Figure 433005DEST_PATH_IMAGE002
(for example:
Figure 980661DEST_PATH_IMAGE051
) Dividing the frequency interval into equal lengths
Figure 681900DEST_PATH_IMAGE003
Sub-intervals (for example:
Figure 656810DEST_PATH_IMAGE052
) Obtaining a maximum amplitude value from the amplitude values in each frequency subinterval and applying this
Figure 341869DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 489954DEST_PATH_IMAGE053
Where i is the serial number of the data, and then for the frequency feature vectorEach element
Figure 311279DEST_PATH_IMAGE054
Is processed to obtain
Figure 457090DEST_PATH_IMAGE007
, wherein
Figure 160603DEST_PATH_IMAGE008
For the set first judgment threshold, a boundary value obtained by observing and analyzing historical training data and used for distinguishing real signals from interference noise on the amplitude value is obtained to obtain a new frequency characteristic direction
Figure 50062DEST_PATH_IMAGE055
Measure, and then obtain a new frequency feature vector
Figure 991473DEST_PATH_IMAGE056
Corresponding set of spatial feature coordinates
Figure 42606DEST_PATH_IMAGE009
Then, the space characteristic coordinate sets obtained by all PE pipe data are combined to form a characteristic coordinate set for obtaining full data
Figure 436678DEST_PATH_IMAGE010
To a set of
Figure 926565DEST_PATH_IMAGE011
Clustering the inner elements to obtain corresponding cluster center coordinate set
Figure 722483DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 210096DEST_PATH_IMAGE013
And sorting to obtain the standard frequency domain characteristic vector of the PE pipe under the condition of pipe burying depth of 0.35m
Figure 888202DEST_PATH_IMAGE057
, wherein
Figure 119463DEST_PATH_IMAGE058
Int () is a rounding function.
The standard frequency domain characteristic vector of the PE pipe under the second preset depth of 0.4m (the standard frequency domain characteristic vector number is 2) can be obtained through statistics by the same method as the method for determining the standard frequency domain characteristic vector of the PE pipe under the first buried depth
Figure 504308DEST_PATH_IMAGE059
And counting to obtain the standard frequency domain characteristic vector of the PE pipe at the third preset depth of 0.45m (the standard frequency domain characteristic vector number is 3)
Figure 428402DEST_PATH_IMAGE060
)。
For another example, taking a galvanized pipe as an example, determining standard frequency domain feature vectors of the galvanized pipe under a first predetermined depth, a second predetermined depth and a third predetermined depth, and the steps are as follows:
the predetermined material is galvanized pipe, the predetermined depth is the first predetermined depth of 0.35m, namely the standard frequency domain feature vector of the galvanized pipe at the buried depth of 0.35m is determined. Assuming a total of 5 predetermined materials and 3 predetermined depths, i.e. numbering according to table 1 above, the galvanized pipe has a standard frequency domain feature vector number of 4, i.e. x =4, at a first predetermined depth of 0.35 m.
The time length of each section of collected signals is set as
Figure 593804DEST_PATH_IMAGE001
(for example:
Figure 628756DEST_PATH_IMAGE050
the unit is: second), each section of sound signal is processed to obtain frequency domain information (each frequency and corresponding amplitude) of each section of sound signal, and a frequency interval is set
Figure 868107DEST_PATH_IMAGE002
(for example:
Figure 228682DEST_PATH_IMAGE051
) Dividing the frequency interval into equal lengths
Figure 84642DEST_PATH_IMAGE003
Sub-intervals (for example:
Figure 392127DEST_PATH_IMAGE052
) Obtaining a maximum amplitude value from the amplitude values in each frequency subinterval and applying this
Figure 17143DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 79777DEST_PATH_IMAGE061
Where i is the serial number of the data, and then for each element of the frequency feature vector
Figure 157455DEST_PATH_IMAGE054
Is processed to obtain
Figure 534209DEST_PATH_IMAGE007
, wherein
Figure 13732DEST_PATH_IMAGE008
For the set first judgment threshold, a boundary value obtained by observing and analyzing historical training data and used for distinguishing real signals from interference noise on the amplitude value is obtained to obtain a new frequency characteristic direction
Figure 247267DEST_PATH_IMAGE062
Measure, and then obtain a new frequency feature vector
Figure 812241DEST_PATH_IMAGE063
Corresponding set of spatial feature coordinates
Figure 461528DEST_PATH_IMAGE009
Then, the spatial characteristic coordinates obtained by all the galvanized pipe data are integrated to form a characteristic seat for obtaining the total dataSet of targets
Figure 61137DEST_PATH_IMAGE010
To a set of
Figure 465573DEST_PATH_IMAGE011
Clustering the inner elements to obtain corresponding cluster center coordinate set
Figure 517843DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 970821DEST_PATH_IMAGE013
And finishing to obtain the standard frequency domain characteristic vector of the galvanized pipe under the condition of pipe burying depth of 0.35m
Figure 424936DEST_PATH_IMAGE064
, wherein
Figure 274DEST_PATH_IMAGE065
Int () is a rounding function.
The standard frequency domain characteristic vector under the second preset depth of 0.4m (the standard frequency domain characteristic vector is numbered 5) can be obtained through statistics by the same method as the method for determining the standard frequency domain characteristic vector of the galvanized pipe under the first buried depth
Figure 539840DEST_PATH_IMAGE066
And counting to obtain standard frequency domain characteristic vectors (the standard frequency domain characteristic vector number is 6) of the galvanized pipe under the third preset depth of 0.45m
Figure 796509DEST_PATH_IMAGE067
)。
For another example, taking a pig iron pipe as an example, determining standard frequency domain feature vectors of the pig iron pipe under a first predetermined depth, a second predetermined depth and a third predetermined depth, and the steps are as follows:
the predetermined material is a pig iron pipe, the predetermined depth is 0.35m of the first predetermined depth, namely the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.35m is determined. Assuming that there are 5 predetermined materials and 3 predetermined depths, i.e. numbering according to table 1 above, the standard frequency domain feature vector number of the pig iron pipe at the first predetermined depth of 0.35m is 13, i.e. x =13.
The duration of each acquired signal is set as
Figure 105130DEST_PATH_IMAGE001
(for example:
Figure 851369DEST_PATH_IMAGE050
the unit is: second), each section of sound signal is processed to obtain frequency domain information (each frequency and corresponding amplitude) of each section of sound signal, and a frequency interval is set
Figure 612652DEST_PATH_IMAGE002
(for example:
Figure 673012DEST_PATH_IMAGE051
) Frequency intervals being divided into equal lengths
Figure 836140DEST_PATH_IMAGE003
Sub-intervals (for example:
Figure 753280DEST_PATH_IMAGE052
) Obtaining a maximum amplitude value from the amplitude values in each frequency subinterval and applying this
Figure 267438DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 865910DEST_PATH_IMAGE068
Where i is the serial number of the data, and then for each element of the frequency feature vector
Figure 883544DEST_PATH_IMAGE054
Is processed to obtain
Figure 237165DEST_PATH_IMAGE007
, wherein
Figure 973040DEST_PATH_IMAGE008
For the set first judgment threshold, a boundary value obtained by observing and analyzing historical training data and used for distinguishing real signals from interference noise on the amplitude value is obtained to obtain a new frequency characteristic direction
Figure 375203DEST_PATH_IMAGE069
Measuring, and obtaining new frequency characteristic vector
Figure 247344DEST_PATH_IMAGE070
Corresponding set of spatial feature coordinates
Figure 975128DEST_PATH_IMAGE009
Then, the space characteristic coordinate sets obtained by all the pig iron pipe data are combined to obtain a characteristic coordinate set of the total data
Figure 729458DEST_PATH_IMAGE010
To a set of
Figure 935311DEST_PATH_IMAGE011
Clustering the inner elements to obtain a corresponding cluster center coordinate set
Figure 927538DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 560645DEST_PATH_IMAGE013
And arranging to obtain the standard frequency domain characteristic vector of the pig iron pipe under the condition of pipe burying depth of 0.35m
Figure 67849DEST_PATH_IMAGE071
, wherein
Figure 811814DEST_PATH_IMAGE072
Int () is a rounding function.
True using a standard frequency domain feature vector with a pig iron pipe at a first burial depthThe same method is used, and the standard frequency domain characteristic vector of the pig iron pipe under the second preset depth of 0.4m can be obtained through statistics (the standard frequency domain characteristic vector is numbered as 14)
Figure 658548DEST_PATH_IMAGE073
And counting to obtain the standard frequency domain characteristic vector of the pig iron pipe at the third preset depth of 0.45m (the standard frequency domain characteristic vector number is 15)
Figure 524872DEST_PATH_IMAGE074
)。
Through the same method, the standard frequency domain feature vectors of all the predetermined materials under all the predetermined depths are obtained, that is, all the standard frequency domain feature vectors under all the combinations can be determined according to the number of the predetermined materials and the number of the predetermined depths in table 1 or table 2. For example, all 15 standard frequency domain feature vectors in table 1 are obtained, and all 42 standard frequency domain feature vectors in table 2 are obtained. And the obtained standard frequency domain feature vector is used as a reference standard for subsequent water pipe leakage detection.
S102, determining a detection frequency domain vector according to a sound signal transmitted from a water pipe collected in a preset area;
obtaining corresponding frequency domain information according to the sound signal transmitted from the water pipe collected in the preset detection area, and according to the set frequency interval
Figure 457056DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 4712DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval forms the detection frequency domain vector
Figure 971531DEST_PATH_IMAGE017
；
wherein ,
Figure 743178DEST_PATH_IMAGE018
is the maximum value of the signal amplitude of the jth subinterval.
In the step, after the detected area is determined, the sound signal transmitted from the water pipe of the area is detected, and the sound signal is in a set frequency interval
Figure 162658DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 514005DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval forms the detection frequency domain vector
Figure 132068DEST_PATH_IMAGE017
。
S103, determining a feature extraction vector according to the standard frequency domain feature vector;
and determining a feature extraction vector according to the standard frequency domain feature vector obtained in the step S101. The feature extraction vector is:
Figure 277879DEST_PATH_IMAGE019
)；
wherein ,
Figure 919076DEST_PATH_IMAGE020
。
for example, in the case of the combination according to Table 1, the feature extraction vector of the PE pipe at the buried depth of 0.35m is
Figure 74114DEST_PATH_IMAGE075
) The PE pipe has a feature extraction vector of 0.4m buried depth
Figure 546683DEST_PATH_IMAGE076
) The characteristic extraction vector of the PE pipe at the buried depth of 0.45m is
Figure 128974DEST_PATH_IMAGE077
) The feature extraction vector of the galvanized pipe at the buried depth of 0.35m is
Figure 257467DEST_PATH_IMAGE078
) Galvanized pipe buried depth of 0.4mFeature extraction vector of
Figure 950617DEST_PATH_IMAGE079
) The feature extraction vector of the galvanized pipe at the buried depth of 0.45m is
Figure 543272DEST_PATH_IMAGE080
) The characteristic extraction vector of the cement pipe at the buried depth of 0.35m is
Figure 296465DEST_PATH_IMAGE081
) The characteristic extraction vector of the cement pipe at the buried depth of 0.4m is
Figure 634956DEST_PATH_IMAGE082
) The characteristic extraction vector of the cement pipe at the buried depth of 0.45m is
Figure 131796DEST_PATH_IMAGE083
) The characteristic extraction vector of the PVC pipe at the buried depth of 0.35m is
Figure 578958DEST_PATH_IMAGE084
) The characteristic extraction vector of the PVC pipe at the buried depth of 0.4m is
Figure 503052DEST_PATH_IMAGE085
) The characteristic extraction vector of the PVC pipe at the buried depth of 0.45m is
Figure 606137DEST_PATH_IMAGE086
) The characteristic extraction vector of the pig iron pipe at the buried depth of 0.35m is
Figure 641089DEST_PATH_IMAGE087
) The characteristic extraction vector of the pig iron pipe at the buried depth of 0.4m is
Figure 942757DEST_PATH_IMAGE088
) The feature extraction vector of the pig iron pipe at the buried depth of 0.45m is
Figure 37752DEST_PATH_IMAGE089
)。
S104, calculating matching scores of the detection frequency domain vector and the feature extraction vector;
after the detection frequency domain vector of the acquisition region is obtained in S102 and the feature extraction vector is obtained in S103, the matching score of the detection frequency domain vector and the feature extraction vector is calculated. As a preferred example, the matching score is:
Figure 628134DEST_PATH_IMAGE021
；
wherein ,
Figure 201197DEST_PATH_IMAGE022
,
Figure 622951DEST_PATH_IMAGE023
,
Figure 888848DEST_PATH_IMAGE024
,
q is a material number, and in the case of the combination shown in table 1, that is, 5 materials, q is 1 for PE pipe, 2 for galvanized pipe, 3 for cement pipe, 4 for PVC pipe, and 5 for pig iron pipe.
As another preferable example, in the case of the combination of table 2, that is, 7 kinds of materials, q is 1 for PE pipe, 2 for galvanized pipe, 3 for cement pipe, 4 for PVC pipe, 5 for pig iron pipe, 6 for copper pipe, and 7 for aluminum alloy pipe.
As another preferable example, if Q types of materials are assumed, the values of Q from 1 to Q represent Q types of materials, respectively.
S105, determining the material of the detected water pipe and the pipe burying depth according to the matching score;
when in use
Figure 700946DEST_PATH_IMAGE025
Then, the water pipe is judged to be of the q-th material, wherein
Figure 77701DEST_PATH_IMAGE026
A threshold value is determined for a matching score range between the training real data and the standard vector according to the historical data;
if it is
Figure 557223DEST_PATH_IMAGE027
Judging that the buried pipe depth is a second preset depth;
if it is
Figure 790759DEST_PATH_IMAGE028
Judging that the depth of the buried pipe is a first preset depth;
if it is
Figure 355732DEST_PATH_IMAGE029
The buried pipe depth is determined to be a third predetermined depth.
Taking PE pipe as an example, and 5 materials (i.e. 5 materials, q is 1 for PE pipe, 2 for galvanized pipe, 3 for cement pipe, 4 for PVC pipe, 5 for pig iron pipe) are available, when
Figure 270599DEST_PATH_IMAGE090
When it is determined that the water pipe is a PE pipe, if it is determined that the water pipe is a PE pipe
Figure 666945DEST_PATH_IMAGE091
Judging that the depth of the buried pipe is 0.4m; if it is
Figure 274644DEST_PATH_IMAGE092
Judging that the depth of the buried pipe is 0.35m; if it is
Figure 795755DEST_PATH_IMAGE093
Then, the pipe burying depth is judged to be 0.45m.
For another example, when a PVC pipe is taken as an example and 5 materials are used (i.e., 5 materials are used, q is 1 for PE pipe, 2 for galvanized pipe, 3 for cement pipe, 4 for PVC pipe, and 5 for pig iron pipe), the present invention is applicable to a steel pipe for steel pipe
Figure 779891DEST_PATH_IMAGE094
Time, judgeThe water pipe is a PE pipe if
Figure 30744DEST_PATH_IMAGE095
Judging that the depth of the buried pipe is 0.4m; if it is
Figure 809344DEST_PATH_IMAGE096
Judging that the depth of the buried pipe is 0.35m; if it is
Figure 817752DEST_PATH_IMAGE097
Then, the pipe burying depth is judged to be 0.45m.
For another example, when a pig iron pipe is taken as an example and 5 materials are used (i.e., 5 materials are used, q is 1 for a PE pipe, 2 for a galvanized pipe, 3 for a cement pipe, 4 for a PVC pipe, and 5 for a pig iron pipe), when
Figure 340000DEST_PATH_IMAGE098
When it is determined that the water pipe is a PE pipe, if it is determined that the water pipe is a PE pipe
Figure 445359DEST_PATH_IMAGE099
Then, the pipe burying depth is judged to be 0.4m; if it is
Figure 394861DEST_PATH_IMAGE100
Then, the pipe burying depth is judged to be 0.35m; if it is
Figure 156143DEST_PATH_IMAGE101
Then, the pipe burying depth is judged to be 0.45m.
According to the same method in this step, all the predetermined materials and the corresponding buried depths can be determined.
S106, calculating according to the standard frequency domain feature vector corresponding to the buried pipe depth to obtain a signal impact score;
based on the detected frequency domain vector
Figure 216503DEST_PATH_IMAGE017
And calculating a standard frequency domain feature vector corresponding to the depth of the corresponding buried pipe to obtain a signal impact score:
Figure 441948DEST_PATH_IMAGE030
；
wherein
Figure 562351DEST_PATH_IMAGE031
In order to be an index of the difference in signal,
Figure 545350DEST_PATH_IMAGE032
is the peak impact index, and:
Figure 206139DEST_PATH_IMAGE033
；
when the buried pipe depth is a first preset depth:
Figure 489353DEST_PATH_IMAGE034
，
Figure 515077DEST_PATH_IMAGE035
;
Figure 250952DEST_PATH_IMAGE036
is a burial depth impact index;
when the buried pipe depth is a second preset depth:
Figure 715432DEST_PATH_IMAGE037
,
Figure 853152DEST_PATH_IMAGE038
,
Figure 49778DEST_PATH_IMAGE039
；
when the buried pipe depth is a third predetermined depth:
Figure 272949DEST_PATH_IMAGE037
，
Figure 541119DEST_PATH_IMAGE040
，
Figure 533346DEST_PATH_IMAGE041
。
and S107, detecting whether the water pipe leaks or not according to the signal impact score.
Score when signal impact
Figure 166453DEST_PATH_IMAGE042
The abnormal condition of the water pipe at the detection position is judged, wherein
Figure 611341DEST_PATH_IMAGE043
Is a set third judgment threshold;
when the abnormal water pipe at the detection position is judged, two signals are collected m meters before and after the abnormal water pipe position and are respectively calculated to obtain corresponding signal impact scores
Figure 620885DEST_PATH_IMAGE044
And
Figure 467618DEST_PATH_IMAGE045
when is coming into contact with
Figure 333943DEST_PATH_IMAGE046
and
Figure 266127DEST_PATH_IMAGE047
And judging that water leakage occurs in the water pipe at the detection position.
By the method of the embodiment, the adaptive water pipe leakage detecting method is used, and firstly, the standard frequency domain feature vector of the preset material under the preset depth is used as the standard reference of the subsequent detection. Then, the sound signal transmitted from the water pipe collected in the predetermined area determines a detection frequency domain vector according to the sound signal. And finally, detecting whether water leakage occurs in the water pipe in the preset area or not according to matching calculation of the detection frequency domain vector and the standard frequency domain characteristic vector. The method solves the technical problem of accurate leakage detection under different pipe materials and different burial depths.
Based on the same inventive concept, an embodiment of the present invention further provides a self-adaptive water pipe leakage detection device, as shown in fig. 2, the device includes:
a vector determination module 201 configured to determine a standard frequency domain feature vector of a predetermined material at a predetermined depth;
the depth determination module 202 is configured to determine a detection frequency domain vector according to a sound signal transmitted from a water pipe collected in a predetermined area, determine a feature extraction vector according to the standard frequency domain feature vector, calculate a matching score between the detection frequency domain vector and the feature extraction vector, and determine the material of the detected water pipe and the pipe burying depth according to the matching score;
and the judging module 203 is configured to calculate a signal impact score according to the standard frequency domain feature vector corresponding to the buried pipe depth, and detect whether water leakage occurs in the water pipe according to the signal impact score.
As a preferred example, the determining the predetermined material includes one of:
galvanized pipe, cement pipe, PVC pipe, PE pipe, pig iron pipe.
The predetermined depth includes:
the preset depth is the preset buried depth of the water pipe;
the predetermined depths include a first predetermined depth of 0.35 meters, a second predetermined depth of 0.4 meters, and a third predetermined depth of 0.45 meters.
As a preferred example, the vector determination module 201 is further configured to determine the standard frequency domain feature vector of the predetermined material at the predetermined depth according to the following:
collecting sound signals when a water pipe made of a predetermined material and arranged at a predetermined burying depth does not leak water, wherein the time length of each section of collected sound signals is
Figure 813783DEST_PATH_IMAGE001
；
Processing each section of sound signal to obtain frequency domain information of each section of sound signal, wherein the frequency interval of the frequency domain information is
Figure 515023DEST_PATH_IMAGE002
；
Dividing said frequency interval into equal length
Figure 552249DEST_PATH_IMAGE003
Obtaining the maximum amplitude value according to the amplitude value in each frequency subinterval, and dividing the maximum amplitude value into a plurality of frequency subintervals
Figure 971729DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 57497DEST_PATH_IMAGE004
Wherein i is 1 or more and 1 or less
Figure 675560DEST_PATH_IMAGE003
，
Figure 86949DEST_PATH_IMAGE005
The maximum value of the amplitude value in the ith frequency subinterval is shown as x, and the number x is the number of the standard frequency domain feature vector and represents the number of the standard frequency domain feature vector of a specific material at a specific depth;
obtaining a second frequency feature vector according to the frequency feature vector, wherein the second frequency feature vector is
Figure 728146DEST_PATH_IMAGE006
And is made of
Figure 883184DEST_PATH_IMAGE007
，
Figure 559016DEST_PATH_IMAGE008
Is a set first judgment threshold value;
determining a set of spatial feature coordinates of the second frequency feature vector
Figure 938045DEST_PATH_IMAGE009
；
The spatial characteristic coordinate sets of all frequency domain information form a full data characteristic coordinate set
Figure 332117DEST_PATH_IMAGE010
；
For the full data characteristic coordinate set
Figure 759687DEST_PATH_IMAGE011
Clustering the inner elements to obtain a corresponding cluster center coordinate set
Figure 555605DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 839956DEST_PATH_IMAGE013
；
Determining standard frequency domain characteristic vectors of the preset materials at the preset depth according to the cluster center coordinate set
Figure 721324DEST_PATH_IMAGE014
；
wherein
Figure 952585DEST_PATH_IMAGE102
Int () is a rounding function;
Figure 603010DEST_PATH_IMAGE103
is the number of frequency subintervals, is greater than or equal to 1 and less than or equal to n 1 Is an integer of (1).
The number x of the standard frequency domain feature vector includes:
x is equal to 1 and represents the standard frequency domain feature vector of the PE pipe at the buried depth of 0.35m;
x is equal to 2 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.4m;
x is equal to 3 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.45 m;
x is equal to 4 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.35 meter;
x is equal to 5 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.4m;
x is equal to 6 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.45 m;
x is equal to 7 and represents the standard frequency domain feature vector of the cement pipe at the buried depth of 0.35m;
x is equal to 8 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.4m;
x is equal to 9 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.45 meter;
x is equal to 10 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.35m;
x is equal to 11 and represents the standard frequency domain characteristic vector of the PVC pipe at the buried depth of 0.4m;
x is equal to 12 and represents the standard frequency domain characteristic vector of the PVC pipe at the buried depth of 0.45 meter;
x is equal to 13 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.35m;
x is equal to 14 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.4m;
x equals 15 representing the standard frequency domain feature vector of the pig iron pipe at a buried depth of 0.45m.
As a preferred example, the depth determining module 202 is further configured to obtain corresponding frequency domain information according to the sound signal from the water pipe collected in the predetermined detection area, and according to the set frequency interval
Figure 323841DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 426926DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval constitutes the detection frequency domain vector
Figure 196299DEST_PATH_IMAGE017
；
wherein ,
Figure 966809DEST_PATH_IMAGE018
is the maximum value of the signal amplitude of the jth sub-interval.
As a preferred example, the depth determination module 202 is further configured to determine a feature extraction vector from the standard frequency domain feature vector:
the feature extraction vector is:
Figure 858542DEST_PATH_IMAGE019
)；
wherein ,
Figure 448923DEST_PATH_IMAGE020
。
as a preferred example, the depth determination module 202 is further configured to calculate matching scores of the detection frequency domain vector and the feature extraction vector:
the matching score is as follows:
Figure 21987DEST_PATH_IMAGE021
；
wherein ,
Figure 647003DEST_PATH_IMAGE022
,
Figure 709637DEST_PATH_IMAGE023
,
Figure 521735DEST_PATH_IMAGE024
,
q is a material number, 1 represents a PE pipe, 2 represents a galvanized pipe, 3 represents a cement pipe, 4 represents a PVC pipe, and 5 represents a pig iron pipe.
As a preferred example, the depth determination module 202 is further configured to determine the material of the detected water pipe and the depth of the buried pipe according to the matching score, including:
when in use
Figure 898490DEST_PATH_IMAGE025
Then, the water pipe is judged to be of the q-th material, wherein
Figure 378013DEST_PATH_IMAGE026
A threshold value is determined for a matching score range between the training real data and the standard vector according to the historical data;
if it is
Figure 611548DEST_PATH_IMAGE027
Judging that the buried pipe depth is a second preset depth;
if it is
Figure 176522DEST_PATH_IMAGE028
Judging that the depth of the buried pipe is a first preset depth;
if it is
Figure 91388DEST_PATH_IMAGE029
The buried pipe depth is determined to be a third predetermined depth.
As a preferred example, the determining module 203 is further configured to calculate a signal impact score according to the standard frequency domain feature vector corresponding to the depth of the buried pipe:
based on detected frequency domain vector
Figure 425417DEST_PATH_IMAGE017
And calculating a standard frequency domain feature vector corresponding to the corresponding buried pipe depth to obtain a signal impact score:
Figure 829854DEST_PATH_IMAGE030
；
wherein
Figure 616544DEST_PATH_IMAGE031
Is an index of the difference in the signal,
Figure 612400DEST_PATH_IMAGE032
is the peak impact index, and:
Figure 597673DEST_PATH_IMAGE033
；
when the buried pipe depth is a first preset depth:
Figure 376273DEST_PATH_IMAGE034
，
Figure 650260DEST_PATH_IMAGE035
;
Figure 172508DEST_PATH_IMAGE036
for buried depth influence index
When the buried pipe depth is a second preset depth:
Figure 277867DEST_PATH_IMAGE037
,
Figure 961789DEST_PATH_IMAGE038
,
Figure 988651DEST_PATH_IMAGE039
；
when the buried pipe depth is a third predetermined depth:
Figure 845749DEST_PATH_IMAGE037
，
Figure 8877DEST_PATH_IMAGE040
，
Figure 129280DEST_PATH_IMAGE041
。
as a preferred example, the determining module 203 is further configured to detect whether water leakage occurs in the water pipe according to the signal impact score:
when signal impact score
Figure 377858DEST_PATH_IMAGE042
Sometimes judging the abnormality of the water pipe at the detection position, wherein
Figure 38647DEST_PATH_IMAGE043
Is a set third judgment threshold;
when the abnormal water pipe at the detection position is judged, two signals are collected m meters before and after the abnormal water pipe position and are respectively calculated to obtain corresponding signal impact scores
Figure 56282DEST_PATH_IMAGE044
And
Figure 347586DEST_PATH_IMAGE045
when is coming into contact with
Figure 880198DEST_PATH_IMAGE046
and
Figure 547940DEST_PATH_IMAGE047
And judging that the water pipe at the detection position leaks water.
It should be noted that the vector determination module 201 provided in this embodiment can implement all functions included in the step S101, solve the same technical problem, and achieve the same technical effect, which is not described herein again;
it should be noted that, the depth determining module 202 provided in this embodiment can implement all the functions included in the steps S102 to S105, solve the same technical problem, and achieve the same technical effect, which is not described herein again;
it should be noted that, the determining module 203 provided in this embodiment can implement all functions included in the steps S106 and S107, solve the same technical problems, and achieve the same technical effects, which are not described herein again;
it should be noted that the apparatus and the method in the embodiment belong to the same inventive concept, solve the same technical problem, achieve the same technical effect, and the apparatus can implement all the methods, and the same parts are not described again.
Based on the same inventive concept, an embodiment of the present invention further provides a self-adaptive water pipe leakage detection device, as shown in fig. 3, the device includes:
comprising a memory 302, a processor 301 and a user interface 303;
the memory 302 for storing a computer program;
the user interface 303 is used for realizing interaction with a user;
the processor 301 is configured to read the computer program in the memory 302, and when the processor 301 executes the computer program, the processor implements:
determining a standard frequency domain feature vector of a predetermined material at a predetermined depth;
determining a detection frequency domain vector according to the sound signal transmitted from the water pipe collected in the preset area;
determining a feature extraction vector according to the standard frequency domain feature vector;
calculating matching scores of the detection frequency domain vector and the feature extraction vector;
determining the material of the detected water pipe and the depth of the buried pipe according to the matching score;
calculating according to the standard frequency domain feature vector corresponding to the buried pipe depth to obtain a signal impact score;
and detecting whether water leakage occurs in the water pipe or not according to the signal impact score.
Wherein in fig. 3 the bus architecture may comprise any number of interconnected buses and bridges, with one or more processors, represented by processor 301, and various circuits, represented by memory 302, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The processor 301 is responsible for managing the bus architecture and general processing, and the memory 302 may store data used by the processor 301 in performing operations.
The processor 301 may be a CPU, ASIC, FPGA or CPLD, and the processor 301 may also adopt a multi-core architecture.
The processor 301, when executing the computer program stored in the memory 302, implements any of the adaptive water line leak detection methods of the present invention.
It should be noted that the apparatus provided in this embodiment and the method embodiment belong to the same inventive concept, solve the same technical problem, achieve the same technical effect, and the same parts are not described again.
The present application also provides a processor-readable storage medium. The processor-readable storage medium stores a computer program, and the processor executes the computer program to implement any one of the above-mentioned adaptive water pipe leakage detection methods.
It should be noted that, in the embodiment of the present application, the division of the unit is schematic, and is only one logic function division, and when the actual implementation is realized, another division manner may be provided. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (14)

1. A self-adaptive water pipe leakage detection method is characterized by comprising the following steps:
determining a standard frequency domain feature vector of a predetermined material at a predetermined depth;
determining a detection frequency domain vector according to the sound signal transmitted from the water pipe collected in the preset area;
determining a feature extraction vector according to the standard frequency domain feature vector;
calculating matching scores of the detection frequency domain vector and the feature extraction vector;
determining the material of the detected water pipe and the depth of the buried pipe according to the matching score;
calculating according to the standard frequency domain feature vector corresponding to the buried pipe depth to obtain a signal impact score;
and detecting whether water leakage occurs in the water pipe or not according to the signal impact score.
2. The method of claim 1, wherein determining the predetermined material comprises one of:
galvanized pipe, cement pipe, PVC pipe, PE pipe, pig iron pipe.
3. The method of claim 1, wherein the predetermined depth comprises:
the preset depth is the preset buried depth of the water pipe;
the predetermined depths include a first predetermined depth of 0.35 meters, a second predetermined depth of 0.4 meters, and a third predetermined depth of 0.45 meters.
4. The method of claim 1, wherein determining the standard frequency domain feature vector of the predetermined material at the predetermined depth comprises:
collecting sound signals when a water pipe made of a predetermined material and arranged at a predetermined burying depth does not leak water, wherein the time length of each section of collected sound signals is
Figure 192410DEST_PATH_IMAGE001
；
Processing each section of sound signal to obtain frequency domain information of each section of sound signal, wherein the frequency interval of the frequency domain information is
Figure 781654DEST_PATH_IMAGE002
；
Dividing said frequency interval into equal length
Figure 295812DEST_PATH_IMAGE003
Obtaining the maximum value of the amplitude value according to the amplitude value in each frequency subinterval, and dividing the maximum value into a plurality of frequency subintervals
Figure 113858DEST_PATH_IMAGE003
The maximum value forms a frequency characteristic vector
Figure 662651DEST_PATH_IMAGE004
Wherein i is 1 or more and 1 or less
Figure 406484DEST_PATH_IMAGE003
，
Figure 407939DEST_PATH_IMAGE005
The maximum value of the amplitude value in the ith frequency subinterval is x, the number x is the number of the standard frequency domain feature vector, and the number x represents the number of the standard frequency domain feature vector of a specific material at a specific depth;
obtaining a second frequency feature vector according to the frequency feature vector, wherein the second frequency feature vector is
Figure 278943DEST_PATH_IMAGE006
And is and
Figure 421256DEST_PATH_IMAGE007
，
Figure 86723DEST_PATH_IMAGE008
is a set first judgment threshold value;
determining a set of spatial feature coordinates of the second frequency feature vector
Figure 575474DEST_PATH_IMAGE009
；
The spatial characteristic coordinate sets of all frequency domain information form a full data characteristic coordinate set
Figure 233857DEST_PATH_IMAGE010
；
For the full data characteristic coordinate set
Figure 491663DEST_PATH_IMAGE011
Clustering the inner elements to obtain corresponding cluster center coordinate set
Figure 344344DEST_PATH_IMAGE012
Where k is the number of the center coordinate and the number of the collection elements is
Figure 258073DEST_PATH_IMAGE013
；
Determining standard frequency domain characteristic vectors of the preset materials at the preset depth according to the cluster center coordinate set
Figure 454568DEST_PATH_IMAGE014
；
wherein
Figure 832460DEST_PATH_IMAGE016
Int () is a rounding function;
Figure 590462DEST_PATH_IMAGE018
is the number of frequency subintervals, is greater than or equal to 1 and less than or equal to n 1 Is an integer of (1).
5. The method of claim 4, wherein the number x of the standard frequency-domain feature vector comprises:
x is equal to 1 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.35m;
x is equal to 2 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.4m;
x is equal to 3 and represents the standard frequency domain characteristic vector of the PE pipe at the buried depth of 0.45 m;
x is equal to 4 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.35 meter;
x is equal to 5 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.4m;
x is equal to 6 and represents the standard frequency domain characteristic vector of the galvanized pipe at the buried depth of 0.45 meter;
x is equal to 7 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.35 meter;
x is equal to 8 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.4m;
x is equal to 9 and represents the standard frequency domain characteristic vector of the cement pipe at the buried depth of 0.45 m;
x is equal to 10 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.35m;
x is equal to 11 and represents the standard frequency domain characteristic vector of the PVC pipe at the buried depth of 0.4m;
x is equal to 12 and represents the standard frequency domain feature vector of the PVC pipe at the buried depth of 0.45 m;
x is equal to 13 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.35m;
x is equal to 14 and represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.4m;
x equals 15 represents the standard frequency domain feature vector of the pig iron pipe at the buried depth of 0.45 meter.
6. The method of claim 4, wherein the determining a detection frequency domain vector according to the sound signal from the water pipe collected in the predetermined area comprises:
obtaining corresponding frequency domain information according to the sound signal transmitted from the water pipe collected in the preset detection area, and according to the set frequency interval
Figure 53805DEST_PATH_IMAGE002
Extracting the frequency domain signal of the corresponding part and based on
Figure 804723DEST_PATH_IMAGE003
The maximum value of the signal amplitude of the subinterval forms the detection frequency domain vector
Figure 286389DEST_PATH_IMAGE019
；
wherein ,
Figure 730140DEST_PATH_IMAGE020
is the maximum value of the signal amplitude of the jth subinterval.
7. The method of claim 6, wherein determining the feature extraction vector from the standard frequency-domain feature vector comprises:
the feature extraction vector is:
Figure 415199DEST_PATH_IMAGE021
)；
wherein ,
Figure 720541DEST_PATH_IMAGE022
。
8. the method of claim 7, wherein the calculating the matching score of the detection frequency domain vector and the feature extraction vector comprises:
the matching score is:
Figure 541866DEST_PATH_IMAGE023
；
wherein ,
Figure 671365DEST_PATH_IMAGE024
,
Figure 843720DEST_PATH_IMAGE025
,
Figure 733179DEST_PATH_IMAGE026
,
q is a material number, 1 represents a PE pipe, 2 represents a galvanized pipe, 3 represents a cement pipe, 4 represents a PVC pipe, and 5 represents a pig iron pipe.
9. The method of claim 8, wherein determining the material of the detected water pipe and the depth of the buried pipe according to the matching score comprises:
when in use
Figure 894164DEST_PATH_IMAGE027
Then, the water pipe is judged to be of the q-th material, wherein
Figure 476455DEST_PATH_IMAGE028
A threshold value is determined for a matching score range between the training real data and the standard vector according to the historical data;
if it is
Figure 73790DEST_PATH_IMAGE029
Judging that the pipe burying depth is a second preset depth;
if it is
Figure 281786DEST_PATH_IMAGE030
Judging that the depth of the buried pipe is a first preset depth;
if it is
Figure 15387DEST_PATH_IMAGE031
The buried pipe depth is determined to be a third predetermined depth.
10. The method of claim 9, wherein the calculating a signal strike score according to the standard frequency domain feature vector corresponding to the borehole depth comprises:
based on the detected frequency domain vector
Figure 34158DEST_PATH_IMAGE019
And calculating a standard frequency domain feature vector corresponding to the corresponding buried pipe depth to obtain a signal impact score:
Figure 869521DEST_PATH_IMAGE032
；
wherein
Figure 631941DEST_PATH_IMAGE033
Is an index of the difference in the signal,
Figure 734895DEST_PATH_IMAGE034
is the peak impact index, and:
Figure 658989DEST_PATH_IMAGE035
；
when the buried pipe depth is a first preset depth:
Figure 230916DEST_PATH_IMAGE036
，
Figure 282179DEST_PATH_IMAGE037
;
Figure 255952DEST_PATH_IMAGE038
is a buried depth influence index;
when the buried pipe depth is a second preset depth:
Figure 350947DEST_PATH_IMAGE039
,
Figure 659437DEST_PATH_IMAGE040
,
Figure 763659DEST_PATH_IMAGE041
；
when the buried pipe depth is a third predetermined depth:
Figure 77091DEST_PATH_IMAGE039
，
Figure 608567DEST_PATH_IMAGE042
，
Figure 889506DEST_PATH_IMAGE043
。
11. the method of claim 9, wherein detecting whether a water leak occurs in a water pipe according to the signal impact score comprises:
when signal impact score
Figure 46687DEST_PATH_IMAGE044
Sometimes judging the abnormality of the water pipe at the detection position, wherein
Figure 526210DEST_PATH_IMAGE045
Is a set third judgment threshold;
when the abnormal water pipe at the detection position is judged, two signals are collected m meters before and after the abnormal water pipe position and are respectively calculated to obtain corresponding signal impact scores
Figure 166270DEST_PATH_IMAGE046
And
Figure DEST_PATH_IMAGE047
when is coming into contact with
Figure 431378DEST_PATH_IMAGE048
and
Figure DEST_PATH_IMAGE049
And judging that the water pipe at the detection position leaks water.
12. A self-adaptive water pipe leakage detection device is characterized by comprising:
a vector determination module configured to determine a standard frequency domain feature vector of a predetermined material at a predetermined depth;
the depth determination module is configured for determining a detection frequency domain vector according to a sound signal transmitted by the water pipe collected in a preset area, determining a feature extraction vector according to the standard frequency domain feature vector, calculating a matching score of the detection frequency domain vector and the feature extraction vector, and determining the material and the pipe burying depth of the detection water pipe according to the matching score;
and the judging module is configured for calculating to obtain a signal impact score according to the standard frequency domain feature vector corresponding to the buried pipe depth, and detecting whether the water pipe leaks according to the signal impact score.
13. A self-adaptive water pipe leakage detecting device is characterized by comprising a memory, a processor and a user interface;
the memory for storing a computer program;
the user interface is used for realizing interaction with a user;
the processor, configured to read the computer program in the memory, and when the processor executes the computer program, implement the adaptive water pipe leakage detecting method according to one of claims 1 to 11.
14. A processor-readable storage medium, characterized in that the processor-readable storage medium stores a computer program which, when executed by a processor, implements an adaptive water pipe leakage detection method according to one of claims 1 to 11.
CN202211576081.0A 2022-12-09 2022-12-09 Self-adaptive water pipe leakage detection method, device and storage medium Active CN115602194B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211576081.0A CN115602194B (en) 2022-12-09 2022-12-09 Self-adaptive water pipe leakage detection method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211576081.0A CN115602194B (en) 2022-12-09 2022-12-09 Self-adaptive water pipe leakage detection method, device and storage medium

Publications (2)

Publication Number Publication Date
CN115602194A true CN115602194A (en) 2023-01-13
CN115602194B CN115602194B (en) 2023-04-28

Family

ID=84852367

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211576081.0A Active CN115602194B (en) 2022-12-09 2022-12-09 Self-adaptive water pipe leakage detection method, device and storage medium

Country Status (1)

Country Link
CN (1) CN115602194B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115855070A (en) * 2023-03-01 2023-03-28 东莞先知大数据有限公司 Water pipe water leakage detection method and device, electronic equipment and storage medium
CN116245512A (en) * 2023-03-15 2023-06-09 东莞先知大数据有限公司 Method and device for recommending easily-leaked areas, electronic equipment and storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08210937A (en) * 1995-02-02 1996-08-20 Matsushita Electric Ind Co Ltd Piping leak detecting device
CN101063641A (en) * 2006-04-28 2007-10-31 孙盈军 Method for testing digital products and special equipment thereof
US20080234950A1 (en) * 2007-03-21 2008-09-25 Korea Atornic Energy Research Institute Water leakage-acoustic sensing method and apparatus in steam generator of sodium-cooled fast reactor using standard deviation by octave band analysis
CN102606891A (en) * 2012-04-11 2012-07-25 广州东芝白云自动化系统有限公司 Water leakage detector, water leakage detecting system and water leakage detecting method
US20140311245A1 (en) * 2013-04-19 2014-10-23 Acoustic Sensing Technology (Uk) Ltd Pipe inspection system and related methods
CN108679455A (en) * 2018-05-17 2018-10-19 中山市顺康塑料制品有限公司 Pipeline leakage monitor and line leakage method
RU2688903C1 (en) * 2018-05-18 2019-05-22 Государственное бюджетное образовательное учреждение высшего образования "Альметьевский государственный нефтяной институт" Method of determining leaks in pipelines and device for its implementation
CN110849936A (en) * 2019-11-27 2020-02-28 云南电网有限责任公司电力科学研究院 GIS pipeline defect online detection device and method
CN112857699A (en) * 2021-01-03 2021-05-28 陕西理工大学 Method for detecting and positioning leakage of long-distance oil and gas pipeline of acoustic vector sensor
CN113109435A (en) * 2021-03-14 2021-07-13 北京工业大学 Pipe damage phonon energy wave diagnosis system and positioning method
CN114594157A (en) * 2020-12-03 2022-06-07 中国石油天然气股份有限公司 Ultrasonic detection method and device for electric fusion joint of polyethylene steel skeleton pipe
CN114877262A (en) * 2022-04-20 2022-08-09 成都千嘉科技股份有限公司 Acoustic emission detection method based on AI chip gas pipeline leakage
CN115222934A (en) * 2022-07-18 2022-10-21 东莞先知大数据有限公司 Method, device and equipment for detecting abnormal operation of water pipe leakage detection and storage medium

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08210937A (en) * 1995-02-02 1996-08-20 Matsushita Electric Ind Co Ltd Piping leak detecting device
CN101063641A (en) * 2006-04-28 2007-10-31 孙盈军 Method for testing digital products and special equipment thereof
US20080234950A1 (en) * 2007-03-21 2008-09-25 Korea Atornic Energy Research Institute Water leakage-acoustic sensing method and apparatus in steam generator of sodium-cooled fast reactor using standard deviation by octave band analysis
CN102606891A (en) * 2012-04-11 2012-07-25 广州东芝白云自动化系统有限公司 Water leakage detector, water leakage detecting system and water leakage detecting method
US20140311245A1 (en) * 2013-04-19 2014-10-23 Acoustic Sensing Technology (Uk) Ltd Pipe inspection system and related methods
CN108679455A (en) * 2018-05-17 2018-10-19 中山市顺康塑料制品有限公司 Pipeline leakage monitor and line leakage method
RU2688903C1 (en) * 2018-05-18 2019-05-22 Государственное бюджетное образовательное учреждение высшего образования "Альметьевский государственный нефтяной институт" Method of determining leaks in pipelines and device for its implementation
CN110849936A (en) * 2019-11-27 2020-02-28 云南电网有限责任公司电力科学研究院 GIS pipeline defect online detection device and method
CN114594157A (en) * 2020-12-03 2022-06-07 中国石油天然气股份有限公司 Ultrasonic detection method and device for electric fusion joint of polyethylene steel skeleton pipe
CN112857699A (en) * 2021-01-03 2021-05-28 陕西理工大学 Method for detecting and positioning leakage of long-distance oil and gas pipeline of acoustic vector sensor
CN113109435A (en) * 2021-03-14 2021-07-13 北京工业大学 Pipe damage phonon energy wave diagnosis system and positioning method
CN114877262A (en) * 2022-04-20 2022-08-09 成都千嘉科技股份有限公司 Acoustic emission detection method based on AI chip gas pipeline leakage
CN115222934A (en) * 2022-07-18 2022-10-21 东莞先知大数据有限公司 Method, device and equipment for detecting abnormal operation of water pipe leakage detection and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陆松: "浅析给水管道检漏技术", 《水工业市场 》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115855070A (en) * 2023-03-01 2023-03-28 东莞先知大数据有限公司 Water pipe water leakage detection method and device, electronic equipment and storage medium
CN115855070B (en) * 2023-03-01 2023-04-28 东莞先知大数据有限公司 Water pipe water leakage detection method and device, electronic equipment and storage medium
CN116245512A (en) * 2023-03-15 2023-06-09 东莞先知大数据有限公司 Method and device for recommending easily-leaked areas, electronic equipment and storage medium
CN116245512B (en) * 2023-03-15 2023-09-26 东莞先知大数据有限公司 Method and device for recommending easily-leaked areas, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN115602194B (en) 2023-04-28

Similar Documents

Publication Publication Date Title
CN115602194A (en) Self-adaptive water pipe leakage detection method and device and storage medium
Casillas Ponce et al. Model-based leak detection and location in water distribution networks considering an extended-horizon analysis of pressure sensitivities
Sarrate et al. Sensor placement for leak detection and location in water distribution networks
CN103189725B (en) Leakage identification in supply system and leakage location
CN106195646B (en) Leak is distributed estimating device, deduction system and presumption method
EP1630635A2 (en) Method and apparatus for improved fault detection in power generation equipment
CN108052628A (en) Switch starting electric current detecting method, system and terminal device
CN109697333A (en) Detection method, device and the electronic equipment of pipeline detection database
CN107507330B (en) Detection method, detection device and the terminal device of banknote thickness abnormity
Wu et al. Data-driven and model-based framework for smart water grid anomaly detection and localization
CN115662469B (en) Water pipe leakage detection method, electronic equipment and storage medium
Ji et al. A novel method to identify the scaling region for chaotic time series correlation dimension calculation
CN114037219A (en) Data evaluation method and device and electronic equipment
JP2017002554A (en) Conduit failure detection device and method
CN100478650C (en) Method and apparatus for improved fault detection in power generation equipment
CN104133836B (en) A kind of method and device realizing change Data Detection
Srirangarajan et al. Water main burst event detection and localization
Okeya et al. Locating pipe bursts in a district metered area via online hydraulic modelling
JP2015137866A (en) Water leakage amount estimation device, method, and system
Salam et al. A leakage detection system on the Water Pipe Network through Support Vector Machine method
CN113343056A (en) Method and device for detecting abnormal gas consumption of user
CN107133328A (en) Pipeline buried depth accuracy checking method and device
KR20110083952A (en) Pipe vibration estimation method
CN101944142A (en) Method for determining optimal fusion of multi-source information of spacecraft flight parameters
Ferino et al. Development of Leak Detection System for PVC Pipeline Through Vibro-Acoustic Emission

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
CP03 Change of name, title or address

Address after: Building 7, No. 124 Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523015

Patentee after: Guangdong Prophet Big Data Co.,Ltd.

Country or region after: China

Address before: Room 102, Building 7, No. 124, Dongbao Road, Dongcheng Street, Dongguan City, Guangdong Province, 523015

Patentee before: Dongguan prophet big data Co.,Ltd.

Country or region before: China

CP03 Change of name, title or address