CN117607960A - Leakage source positioning method and device, computer equipment and storage medium - Google Patents
Leakage source positioning method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117607960A CN117607960A CN202311523977.7A CN202311523977A CN117607960A CN 117607960 A CN117607960 A CN 117607960A CN 202311523977 A CN202311523977 A CN 202311523977A CN 117607960 A CN117607960 A CN 117607960A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- sound source
- image
- leakage
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 239000011159 matrix material Substances 0.000 claims abstract description 71
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 53
- 238000001931 thermography Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 27
- 238000013528 artificial neural network Methods 0.000 claims description 20
- 230000004807 localization Effects 0.000 claims description 19
- 238000001228 spectrum Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 abstract description 7
- 238000012216 screening Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 238000009825 accumulation Methods 0.000 description 7
- 238000012937 correction Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 239000000523 sample Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 210000005069 ears Anatomy 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Geophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radar, Positioning & Navigation (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The application relates to the technical field of seismic data processing, in particular to a leakage source positioning method which comprises the following steps: acquiring sound wave information of a sound source; obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers; determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm; and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information. The method combines the sound source positioning and the infrared thermal imaging method to monitor the pipeline. And positioning a sound source according to the sound wave information to serve as preliminary screening, zooming and extracting an infrared thermal imaging image to be processed of the sound source position through a video camera, and further judging whether a leakage source exists or not and judging the position of the leakage source through temperature change of the periphery of the pipeline.
Description
Technical Field
The present disclosure relates to the field of seismic data processing technologies, and in particular, to a method and apparatus for positioning a leakage source, a computer device, and a storage medium.
Background
Pipeline transportation is the main transportation mode of petroleum, natural gas, water conservancy water delivery and urban water supply and drainage. With the wider and wider application of the pipeline, pipeline leakage accidents caused by defects of the pipeline, various natural (such as environmental corrosion, geological change, water flow flushing and the like) and artificial (such as construction damage, artificial damage and the like) factors are frequent and continuously increased, and the pipeline leakage accidents seriously threaten the safe operation of the pipeline. Thus, leak source localization is particularly important. In the related art, a gas sensor is used for monitoring a pipeline in most cases, only a fixed point is monitored, and the whole pipeline cannot be monitored. Infrared thermal imaging is used to regionalize the captured environment, but single monitoring cannot meet complex environments.
In the related art, the resolution of sound source localization needs to be achieved by technology, and a microphone array and a sound intensity probe are commonly used as sound source localization schemes. It can be approximately considered that both sound source localization is an extension of the mechanism of human ear sound localization, and is a bionic technology. The microphone array mimics two ears of a human, and the microphone array uses several to thousands of microphones, which is equivalent to a person with a plurality of ears, so that the positioning accuracy of the microphone array is far higher than that of the human ears. The sound intensity probe can be simply considered to simulate a single ear listening near a sound source, and the ear is wrapped by hand so that the ear is less disturbed by far sounds, and the moving head moves near the object to be listened to determine the sound source position. In short, the noise identification and sound source localization technology is a comprehensive application of technological advances of sensors, data acquisition, signal processing and the like.
As a non-contact and imaging temperature measurement technology, advanced and friendly infrared thermal imaging temperature measurement data extraction, visualization and diagnosis technologies are gradually paid attention to and paid attention to along with the continuous deepening of intellectualization and digitalization of operation and maintenance work. The thermal infrared imager itself does not emit infrared light but absorbs it passively. The infrared heat can be detected in a non-contact way and converted into a thermal image and a temperature value, and then the thermal image and the temperature value are displayed on a display, and the temperature value can be calculated. The thermal infrared imager can accurately quantify the detected heat, and can accurately identify and strictly analyze the heating fault area. In nature, all objects can radiate infrared rays, and different infrared images can be obtained by measuring the infrared ray difference between the object and the background by using a detector. In operation, a thermal infrared imager uses optics to focus infrared energy from objects in a scene onto an infrared detector, and then converts the infrared data from each detector element into a standard video format and displays it on a standard video monitor or records it on memory.
In the field related to leakage source positioning, how to superimpose two technologies of infrared thermal imaging and acoustic source positioning and present the two technologies in a video mode is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a leakage source positioning method, a leakage source positioning device, a computer device and a storage medium.
In a first aspect, the present application provides a leakage source positioning method, including:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In one embodiment, determining to use a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm includes:
When the distance is greater than zero and less than or equal to a preset value, obtaining the sound source position through a first algorithm according to the frequency;
and when the distance is larger than a preset value, obtaining the sound source position through a second algorithm according to the frequency.
In one embodiment, when the distance is greater than zero and less than or equal to a preset value, the sound source position is obtained according to the frequency through a first algorithm, including:
carrying out Fourier transform on the acoustic wave information to obtain a frequency domain signal;
performing matrix feature decomposition on the frequency domain signal to obtain a first feature vector;
arranging the first feature vectors according to the first feature values of the first feature vectors to obtain a first signal subspace and a first noise subspace;
the position corresponding to the peak of the average spatial spectrum of the first signal subspace and the first noise subspace is determined as the sound source position.
In one embodiment, when the distance is greater than a preset value, obtaining the sound source position according to the frequency through a second algorithm includes:
obtaining a covariance matrix according to the acoustic wave information;
performing matrix feature decomposition on the covariance matrix to obtain a second feature vector;
arranging the second feature vectors according to the second feature values of the second feature vectors to obtain a second signal subspace and a second noise subspace;
The sound source position is determined from the positions corresponding to the peaks of the orthogonal spatial spectrums of the second signal subspace and the second noise subspace.
In one embodiment, performing infrared thermal imaging analysis on an area corresponding to a sound source position to obtain leakage source information includes:
acquiring an image to be processed of a sound source position, wherein the image to be processed is infrared thermal imaging;
dividing an image to be processed according to the temperature value to obtain a sub-image;
and carrying out neural network identification on the sub-images to obtain leakage source information.
In one embodiment, segmenting an image to be processed according to a temperature value to obtain a sub-image includes:
determining a rectangular frame of a binarized image of the image to be processed by a pixel accumulation method;
determining a target area according to the bit rectangle frame;
and performing character segmentation on the target area by a vertical projection method to obtain a sub-image.
In one embodiment, performing neural network identification on the sub-images to obtain leakage source information includes:
pooling the sub-images and extracting image features;
and analyzing the image characteristics to obtain leakage source information.
In one embodiment, before dividing the image to be processed according to the temperature value to obtain the sub-image, the method further includes:
And carrying out binarization processing on the image to be processed.
In a second aspect, the present application further provides a leakage source positioning device, including:
the sound source acquisition unit is used for acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
the analysis unit is used for obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the receivers of the sound source and the array;
the sound source positioning unit is used for determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining a sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and the leakage source information unit is used for carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
Obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
And carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
According to the leakage source positioning method, the leakage source positioning device, the computer equipment and the storage medium, the sound wave information of the sound source is obtained, and the sound wave information comprises wavelength and frequency; obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers; determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm; and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information. The method combines the sound source positioning and the infrared thermal imaging method to monitor the pipeline. And positioning a sound source according to the sound wave information to serve as preliminary screening, zooming and extracting an infrared thermal imaging image to be processed of the sound source position through a video camera, further judging whether a leakage source exists or not and judging the position of the leakage source through temperature change of the periphery of the pipeline, and displaying videos.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or conventional techniques of the present application, the drawings required for the descriptions of the embodiments or conventional techniques will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flow diagram of a method of leak source localization in one embodiment;
FIG. 2 is a schematic diagram of a microphone array of a leakage source localization method in one embodiment;
FIG. 3 is a flow chart of a determination algorithm of a leakage source positioning method in one embodiment;
FIG. 4 is a first algorithm flow diagram of a leak source localization method in one embodiment;
FIG. 5 is a second algorithm flow diagram of a leak source localization method in one embodiment;
FIG. 6 is a schematic diagram of a leakage source information determination flow of a leakage source positioning method according to an embodiment;
FIG. 7 is a schematic diagram of a temperature identification flow of a leak source localization method in one embodiment;
FIG. 8 is a schematic diagram of an image preprocessing flow for a leakage source localization method in one embodiment;
FIG. 9 is a sub-image flow diagram of a leak source localization method in one embodiment;
FIG. 10 is a schematic diagram of a temperature localization flow of a leak source localization method in one embodiment;
FIG. 11 is a schematic diagram of a leakage source information analysis flow of a leakage source positioning method according to an embodiment;
FIG. 12 is a neural network identification schematic of a leak source localization method in one embodiment;
fig. 13 is an internal structural view of a computer device in one embodiment.
Detailed Description
In order to facilitate an understanding of the present application, a more complete description of the present application will now be provided with reference to the relevant figures. Examples of the present application are given in the accompanying drawings. This application may, however, be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all couplings of one or more of the associated listed items.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another element.
The leakage source positioning method can be applied to pipeline detection in the chemical industry. The leakage source positioning device acquires sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency; obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers; determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm; and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information. The method combines the sound source positioning and the infrared thermal imaging method to monitor the pipeline. And positioning a sound source according to the sound wave information to serve as preliminary screening, zooming and extracting an infrared thermal imaging image to be processed of the sound source position through a video camera, further judging whether a leakage source exists or not and judging the position of the leakage source through temperature change of the periphery of the pipeline, and displaying videos.
Embodiment 1,
As shown in fig. 1, in this embodiment, there is provided a leakage source positioning method, including the steps of:
s101: and acquiring sound wave information of the sound source, wherein the sound wave information comprises wavelength and frequency.
Specifically, the leakage source positioning device obtains acoustic information of the sound source through the microphone array receiver, wherein the acoustic information comprises wavelength and frequency. Because in a field environment, the signals received by the microphone array of the leakage source positioning device inevitably contain extraneous interference noise. The leakage source positioning device classifies noise received by the microphone array into four categories: additive noise, mutual interference between sounds, reverberation, and echo, wherein additive noise can be classified into coherent noise and incoherent noise.
S102: and obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the receivers of the sound source and the array.
Specifically, the leakage source positioning device obtains acoustic information of the sound source through the microphone array receiver, wherein the acoustic information comprises wavelength and frequency. Because the sound signal is a narrow-band signal and satisfies the far-field environmental formula as
Wherein r is the distance from the center of the microphone array to the sound source;
d is the distance between the linear array microphone arrays;
Lambda is the wavelength.
Assuming that the sound source direction forms an included angle of theta degrees with the array, microphone x 1 First received signal, then x m The signals are received in turn, and the signal received by the first microphone is x.e, because the path from one microphone to the mth microphone is d.m.sin theta j0 The signal received by the mth sensor is
S103: and determining to adopt a first algorithm or a second algorithm according to the preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm.
The first algorithm is a matrix characteristic space decomposition algorithm focusing on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm.
Specifically, the leakage source positioning device obtains the distance from the sound source to the center of the array, and then determines a matrix characteristic space decomposition algorithm focused on the formant frequency domain according to a preset interval to which the distance belongs, or calculates the position of the sound source by adopting a matrix characteristic space decomposition algorithm different from the first algorithm.
S104: and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
Wherein the leakage source information includes a specific shape of the leakage source whose leakage position has been leaked.
Specifically, the leakage source positioning device receives sound source information through the microphone array, performs preliminary judgment on the position of the sound source to obtain the specific position of the sound source, and performs infrared thermal imaging analysis on the corresponding region to obtain the leakage source information.
In the embodiment, the leakage source positioning method is provided, and the leakage source positioning device obtains the sound wave information of the sound source, wherein the sound wave information comprises wavelength and frequency; obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers; determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm; and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information. The method combines the sound source positioning and the infrared thermal imaging method to monitor the pipeline. And positioning a sound source according to the sound wave information to serve as preliminary screening, zooming and extracting an infrared thermal imaging image to be processed of the sound source position through a video camera, further judging whether a leakage source exists or not and judging the position of the leakage source through temperature change of the periphery of the pipeline, and displaying videos.
Embodiment II,
As shown in fig. 2 and 3, in the present embodiment, step S103 is provided: determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm, and the method comprises the following steps:
s1031: and when the distance is greater than zero and less than or equal to a preset value, obtaining the sound source position through a first algorithm according to the frequency.
Specifically, the leakage source positioning device determines to adopt a first algorithm or a second algorithm according to the preset interval to which the obtained distance belongs. When the distance is greater than zero and less than or equal to a preset value, the leakage source positioning device obtains the sound source position according to the frequency through a matrix characteristic space decomposition algorithm focused on the formant frequency domain.
S1032: and when the distance is larger than a preset value, obtaining the sound source position through a second algorithm according to the frequency.
Specifically, the leakage source positioning device determines to adopt a first algorithm or a second algorithm according to the preset interval to which the obtained distance belongs. When the distance is greater than zero and less than or equal to a preset value, the leakage source positioning device obtains the sound source position according to the frequency through a matrix characteristic space decomposition algorithm different from the first algorithm.
In this embodiment, when the distance from the center of the microphone array to the sound source is greater than zero and less than or equal to a preset value, the leakage source positioning device obtains the sound source position according to the frequency through a first algorithm, and when the distance is greater than the preset value, the leakage source positioning device obtains the sound source position according to the frequency through a second algorithm. According to different distances from the center of the microphone array to the sound source, different algorithms are adopted, so that data processing is more accurate, and accurate positioning is realized.
Third embodiment,
As shown in fig. 4, in the present embodiment, step S1031 is provided: when the distance is greater than zero and less than or equal to a preset value, the sound source position is obtained through a first algorithm according to the frequency, and the method comprises the following steps:
s10311: and carrying out Fourier transform on the acoustic wave information to obtain a frequency domain signal.
Specifically, the leakage source positioning device takes the acoustic wave information received by the microphone array as X i (n), i=1, 2,3 … M, i represents the number of the array element, fourier transform is performed on the acoustic information, and the acoustic information is converted from the time domain signal to the frequency domain, where the formula is as follows:
wherein R is x (f i ) For frequency domain f i Is a cross-spectral density of (2);
X k (f i ) For each signal frequency f i A snapshot of amplitude phase composition;
k is the number of frequency domain segments taken.
S10312: and performing matrix characteristic decomposition on the frequency domain signal to obtain a first characteristic vector.
In particular, the leakage source localization means localize the frequency domain signal Rx (f i ) And (3) performing matrix characteristic decomposition, wherein the formula is as follows:
s10313: and arranging the first eigenvectors according to the first eigenvalues of the first eigenvectors to obtain a first signal subspace and a first noise subspace.
Specifically, the leakage source positioning device arranges the feature vectors according to the magnitude of the feature values, arranges the first feature vectors according to the first feature values of the first feature vectors, and forms first signal subspaces us= [ u ] by the first P first feature vectors with the largest first feature values 1 ,u 2 ,u 3 …u p ]The remaining first eigenvectors form a first noise subspace Us (f i )＝[u p+1 ,u p+2 ,u p+3 …u m ]。
S10314: the position corresponding to the peak of the average spatial spectrum of the first signal subspace and the first noise subspace is determined as the sound source position.
Specifically, the leakage source positioning device focuses the first signal subspace and the first noise subspace on the matrix characteristic space average spatial spectrum formula of the formant frequency domain as follows:
different θ values correspond to different P (θ) values, wherein the position corresponding to the peak is determined as the sound source position.
In the embodiment, the leakage source positioning device performs Fourier transform on the acoustic wave information to obtain a frequency domain signal; performing matrix feature decomposition on the frequency domain signal to obtain a first feature vector; arranging the first feature vectors according to the first feature values of the first feature vectors to obtain a first signal subspace and a first noise subspace; the position corresponding to the peak of the average spatial spectrum of the first signal subspace and the first noise subspace is determined as the sound source position. The method has higher signal-to-noise ratio in the frequency domain, and shorter wavelength means that under the same wave path difference, shorter wavelength can generate more obvious signal phase difference, so that the positioning resolution can be improved, and the peak value is more obvious.
As shown in fig. 5, in the present embodiment, step S1032 is also provided: when the distance is larger than a preset value, the sound source position is obtained through a second algorithm according to the frequency, and the method comprises the following steps:
s10321: and obtaining a covariance matrix according to the acoustic wave information.
Specifically, the leakage source positioning device receives a uniform linear microphone array, the array number is M, and the array pitch is d. There are D sound source targets in space, which are labeled S 1 (t)，S 2 (t)…S D (t), the acoustic information received in far field mode is:
in the method, in the process of the invention,an array formed as an array manifold;
signals received for each array element;
n and (t) is a noise signal received by the array element.
Wherein,the signals received by each array element areThe covariance matrix of the array is obtained according to the above formula:
R x (t)＝E{x(t)*x H (t)}。
s10322: and performing matrix characteristic decomposition on the covariance matrix to obtain a second characteristic vector.
Specifically, the leakage source positioning device is based onFormula, R is x And (t) performing matrix feature decomposition to obtain a second feature vector.
S10323: and arranging the second eigenvectors according to the second eigenvalues of the second eigenvectors to obtain a second signal subspace and a second noise subspace.
Specifically, the leakage source positioning device performs size arrangement on second eigenvalues of the second eigenvectors, and determines the second eigenvectors corresponding to the first D second eigenvalues as a signal subspace E; determining the rest of the second eigenvectors as noise subspaces, and obtaining:
S10324: the sound source position is determined from the positions corresponding to the peaks of the orthogonal spatial spectrums of the second signal subspace and the second noise subspace.
Specifically, the leakage source positioning device obtains, according to orthogonality between each column vector and noise subspace in the matrix A (θ):
G H a(θ i )＝0，i＝1,2…,M
due to orthogonality of the signal space and the noise space, the array space spectral functions are obtained as follows:
by changing θ, P corresponding thereto is obtained MUSIC (θ), the peak is the sound source position, i.e.:
θ target object ＝arg θ min(a H (θ)GG H a(θ))。
In this embodiment, the leakage source positioning device obtains a covariance matrix according to acoustic information; performing matrix feature decomposition on the covariance matrix to obtain a second feature vector; arranging the second feature vectors according to the second feature values of the second feature vectors to obtain a second signal subspace and a second noise subspace; the sound source position is determined from the positions corresponding to the peaks of the orthogonal spatial spectrums of the second signal subspace and the second noise subspace. And dividing the acoustic wave information into a signal subspace and a noise subspace by adopting a matrix characteristic space decomposition algorithm different from the first algorithm, and obtaining the sound source position information by utilizing orthogonality of the signal subspace and the noise subspace. The method is simple and easy to popularize, and the algorithm is accurate.
Fourth embodiment,
As shown in fig. 6 and 7, in the present embodiment, step S104 is provided: carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information, wherein the method comprises the following specific steps:
s1041: and acquiring an image to be processed of the sound source position, wherein the image to be processed is infrared thermal imaging.
Wherein the image to be processed is infrared thermal imaging.
Specifically, the leakage source positioning device acquires an image to be processed of a sound source position, contains complex backgrounds such as buildings and the like based on the image to be processed, usually contains time, equipment model watermarks and frames due to different acquisition equipment, and can influence accuracy rate if the image to be processed is directly identified, so that image preprocessing is needed.
As shown in fig. 8, specifically, the leakage source positioning device reads an image to be processed, and performs gray level conversion and Gamma correction on the image to be processed to obtain an initial image. Drawing a histogram of the infrared image to be identified on the initial image, and adaptively obtaining a side threshold value at the trough of the histogram; and performing binarization processing on the image by adopting the self-adaptive threshold value.
And carrying out gray level transformation by adopting a weighting method, and carrying out normalization processing on the gray level image by adopting a Gamma correction method in order to enhance detail information and improve contrast. According to the characteristics of the infrared image, the tested correction parameter gamma is 0.45, and the constant C is 0.85.L G (x, y) =c×l (x, y) γ: l (x, y) is the original image; l G (x, y) is a corrected image; gamma is a correction parameter; c is a constant.
Specifically, the method comprises the steps of dividing the image to be processed according to the temperature value, and before obtaining the sub-image, further comprising: and carrying out binarization processing on the image to be processed. Common binarization methods comprise a maximum inter-class variance method (Otsu) and a maximum entropy threshold method, and 100 infrared images and visible light images are randomly selected for comparison analysis in consideration of differences in image color composition of the infrared images and the visible light images. The infrared image pretreated by the improved binarization method is compared with the traditional binarization method. The binarization method for improving the self-adaptive threshold value can be used for completely storing the temperature value, the maximum value and minimum value areas have no salt-and-pepper noise points, the binarization processing requirement is met, different threshold values can be respectively determined according to different objects, and an ideal preprocessing result is obtained.
S1042: and dividing the image to be processed according to the temperature value to obtain a sub-image.
Specifically, after the leakage source positioning device preprocesses the image to be processed, the background information can be effectively removed, and the temperature value area is highlighted. The method is beneficial to dividing the image to be processed, the image to be processed is divided into two parts including temperature value region positioning and temperature value character division, and the sub-image is obtained after the image to be processed is divided.
S1043: and carrying out neural network identification on the sub-images to obtain leakage source information.
Specifically, the leakage source positioning device performs neural network identification on the sub-images to obtain leakage source information. In a specific neural network identification structure, C1 and C2 are convolution layers, P1 and P2 are pooling layers, and FC is a full connection layer.
In this embodiment, the leakage source positioning device uses a sound source positioning algorithm as a first to screening condition, zooms through a video camera when a sound source exists, extracts a high-frame picture of infrared thermal imaging of a sound source area, and further judges whether a leakage source exists or not through temperature change of the periphery of a pipeline.
Fifth embodiment (V),
As shown in fig. 9 and 10, in the present embodiment, step S1042 is provided: dividing an image to be processed according to a temperature value to obtain a sub-image, wherein the specific steps comprise:
s10421: and determining a rectangular frame of the binarized image of the image to be processed by a pixel accumulation method.
Specifically, the leakage source positioning device positions the temperature value region based on the profile information. Because the temperature measuring map rectangular frame of the binarized image to be processed remains intact, the rectangular frame can be positioned by adopting pixel accumulation.
S10422: the target area is determined from the bitrectangular box.
Specifically, the leakage source positioning device accumulates continuous pixels in columns of the whole image by taking the long side of the rectangular frame as the direction, and screens out columns with the continuous pixels equal to the length of the rectangular frame. The leakage source positioning device is used for positioning pixel coordinates of four corners of the rectangular frame by taking the short side of the rectangular frame as a reference, positioning a target area according to the relative position relation between the rectangular frame and the temperature value, and dividing the target area to obtain a determined target area.
S10423: and performing character segmentation on the target area by a vertical projection method to obtain a sub-image.
Specifically, the leakage source positioning device adopts a vertical integral projection method to carry out character segmentation on the temperature value, and the formula is as follows:
f(x,y),0≤x≤h
wherein: vx is the vertical projection integration result of the image x columns; f (x, y) is the gray value at the pixel point (x, y); n is the height of the target area; h is the length of the target area. The pixel accumulation value has mutation at the joint, which indicates that the region has two characters, and then the number and the positions of the characters are determined according to the characteristics, so that the segmentation of the temperature value is realized.
As shown in fig. 11 and 12, in the present embodiment, step S1043 is also provided: the neural network identification is carried out on the sub-images to obtain leakage source information, and the method specifically comprises the following steps:
S10431: and carrying out pooling operation on the sub-images, and extracting image features.
Specifically, the leakage source positioning device builds a neural network identification structure with depth of 7, determines network parameters, and divides a temperature value training set and a test set according to the proportion of 8:2; training and testing a CNN network, and analyzing each character recognition result; and designing an infrared image temperature value identification and recording system of the power equipment by combining with an App Designer module, and selecting a plurality of infrared image test temperature identification results.
S10432: and analyzing the image characteristics to obtain leakage source information.
Specifically, an image to be processed having a pixel size of 16×16 is input to the neural network identification structure of the leakage source positioning device. The convolution kernel size of two convolution layers of the neural network identification structure is 5 multiplied by 5, the step length is 1, the pooling layer P1 adopts the maximum pooling operation, the pooling kernel size is 1 multiplied by 1, and the step length is 1. The image features are further extracted by adopting a convolution kernel of 2×2 in the pooling layer P2, the step length is 2, the feature map size is 4×4×12, finally, a full-connection layer is input, the dropout value is 0.5, and the result is predicted by adopting a Softmax classifier and is divided into 11 categories including symbols "-" and numbers "0-9". The following table shows:
The predicted value and the true value of the loss function of the neural network identification structure deviate from each other, and the formula is as follows:
wherein:is the predicted value of the i-th sample; y is i Is the true value of the i-th sample; n is the number of samples.
In this embodiment, when receiving that the acoustic wave information has a leakage source, the leakage source positioning device zooms through the video camera to extract an image to be processed of an infrared imaging high frame of the acoustic wave information position, further judges whether the leakage source exists through temperature change of the periphery of the pipeline, and finally can directly observe whether the leakage source exists through the presentation of the video.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a leakage source positioning device for realizing the leakage source positioning method. The implementation of the solution provided by the leakage source positioning device is similar to that described in the above method, so the specific limitation in the embodiments of the leakage source positioning device provided below may be referred to the limitation of the leakage source positioning method hereinabove, and will not be repeated herein.
In one embodiment, there is provided a leakage source positioning device comprising:
the sound source acquisition unit is used for acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
the analysis unit is used for obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the receivers of the sound source and the array;
the sound source positioning unit is used for determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining a sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and the leakage source information unit is used for carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In one embodiment, determining to use a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm includes:
the first analysis unit is used for obtaining the sound source position through a first algorithm according to the frequency when the distance is greater than zero and smaller than or equal to a preset value;
and the second analysis unit is used for obtaining the sound source position through a second algorithm according to the frequency when the distance is larger than the preset value.
In one embodiment, when the distance is greater than zero and less than or equal to a preset value, the sound source position is obtained according to the frequency through a first algorithm, including:
the Fourier transform unit is used for carrying out Fourier transform on the acoustic wave information to obtain a frequency domain signal;
the matrix characteristic decomposition unit is used for performing matrix characteristic decomposition on the frequency domain signal to obtain a first characteristic vector;
the subspace unit is used for arranging the first eigenvectors according to the first eigenvalues of the first eigenvectors to obtain a first signal subspace and a first noise subspace;
and a sound source position unit for determining a position corresponding to a peak value of the average spatial spectrum of the first signal subspace and the first noise subspace as a sound source position.
In one embodiment, when the distance is greater than a preset value, obtaining the sound source position according to the frequency through a second algorithm includes:
the covariance matrix unit is used for obtaining a covariance matrix according to the acoustic wave information;
the matrix characteristic decomposition unit is used for performing matrix characteristic decomposition on the covariance matrix to obtain a second characteristic vector;
the subspace unit is used for arranging the second eigenvectors according to the second eigenvalues of the second eigenvectors to obtain a second signal subspace and a second noise subspace;
and a sound source position unit for determining a position corresponding to a peak value of the orthogonal spatial spectrum of the second signal subspace and the second noise subspace as a sound source position.
In one embodiment, performing infrared thermal imaging analysis on an area corresponding to a sound source position to obtain leakage source information includes:
the acquisition unit is used for acquiring an image to be processed of the sound source position, wherein the image to be processed is infrared thermal imaging;
the sub-image unit is used for dividing the image to be processed according to the temperature value to obtain a sub-image;
and the neural network identification unit is used for carrying out neural network identification on the sub-images to obtain leakage source information.
In one embodiment, segmenting an image to be processed according to a temperature value to obtain a sub-image includes:
The rectangular frame analysis unit is used for determining a rectangular frame of a binarized image of the image to be processed through a pixel accumulation method;
a target area determining unit for determining a target area according to the bit rectangle frame;
and the sub-image unit is used for carrying out character segmentation on the target area through a vertical projection method to obtain a sub-image.
In one embodiment, performing neural network identification on the sub-images to obtain leakage source information includes:
the image feature extraction unit is used for carrying out pooling operation on the sub-images and extracting image features;
and the analysis unit is used for analyzing the image characteristics to obtain leakage source information.
In one embodiment, before dividing the image to be processed according to the temperature value to obtain the sub-image, the method further includes:
and the preprocessing unit is used for binarizing the image to be processed.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 13. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store periodic task allocation data such as configuration files, theoretical operating parameters and theoretical deviation value ranges, task attribute information, and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a leakage source localization method.
It will be appreciated by those skilled in the art that the structure shown in fig. 13 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In one embodiment, when executing the computer program, the processor determines to use a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtains the sound source position according to the frequency through the first algorithm or the second algorithm, including:
when the distance is greater than zero and less than or equal to a preset value, obtaining the sound source position through a first algorithm according to the frequency;
and when the distance is larger than a preset value, obtaining the sound source position through a second algorithm according to the frequency.
In one embodiment, when the processor executes the computer program to realize that the distance is greater than zero and less than or equal to a preset value, the sound source position is obtained through a first algorithm according to the frequency, including:
carrying out Fourier transform on the acoustic wave information to obtain a frequency domain signal;
performing matrix feature decomposition on the frequency domain signal to obtain a first feature vector;
arranging the first feature vectors according to the first feature values of the first feature vectors to obtain a first signal subspace and a first noise subspace;
the position corresponding to the peak of the average spatial spectrum of the first signal subspace and the first noise subspace is determined as the sound source position.
In one embodiment, when the processor executes the computer program to achieve a distance greater than a preset value, the obtaining the sound source position according to the frequency through the second algorithm includes:
Obtaining a covariance matrix according to the acoustic wave information;
performing matrix feature decomposition on the covariance matrix to obtain a second feature vector;
arranging the second feature vectors according to the second feature values of the second feature vectors to obtain a second signal subspace and a second noise subspace;
the sound source position is determined from the positions corresponding to the peaks of the orthogonal spatial spectrums of the second signal subspace and the second noise subspace.
In one embodiment, the processor, when executing the computer program, performs an infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information, including:
acquiring an image to be processed of a sound source position, wherein the image to be processed is infrared thermal imaging;
dividing an image to be processed according to the temperature value to obtain a sub-image;
and carrying out neural network identification on the sub-images to obtain leakage source information.
In one embodiment, the processor, when executing the computer program, performs segmentation on an image to be processed according to a temperature value to obtain a sub-image, including:
determining a rectangular frame of a binarized image of the image to be processed by a pixel accumulation method;
determining a target area according to the bit rectangle frame;
and performing character segmentation on the target area by a vertical projection method to obtain a sub-image.
In one embodiment, the processor, when executing the computer program, implements neural network identification on the sub-images to obtain leakage source information, including:
pooling the sub-images and extracting image features;
and analyzing the image characteristics to obtain leakage source information.
In one embodiment, the processor when executing the computer program realizes the segmentation of the image to be processed according to the temperature value, and before obtaining the sub-image, the method further comprises:
and carrying out binarization processing on the image to be processed.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the receivers;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
And carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
In one embodiment, the computer program when executed by the processor implements determining to use a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm includes:
when the distance is greater than zero and less than or equal to a preset value, obtaining the sound source position through a first algorithm according to the frequency;
and when the distance is larger than a preset value, obtaining the sound source position through a second algorithm according to the frequency.
In one embodiment, when the computer program is executed by the processor, to obtain the sound source position according to the frequency through a first algorithm when the implementation distance is greater than zero and less than or equal to a preset value, including:
carrying out Fourier transform on the acoustic wave information to obtain a frequency domain signal;
performing matrix feature decomposition on the frequency domain signal to obtain a first feature vector;
arranging the first feature vectors according to the first feature values of the first feature vectors to obtain a first signal subspace and a first noise subspace;
the position corresponding to the peak of the average spatial spectrum of the first signal subspace and the first noise subspace is determined as the sound source position.
In one embodiment, when the computer program is executed by the processor to obtain the sound source position according to the frequency through the second algorithm when the implementation distance is greater than the preset value, the method includes:
obtaining a covariance matrix according to the acoustic wave information;
performing matrix feature decomposition on the covariance matrix to obtain a second feature vector;
arranging the second feature vectors according to the second feature values of the second feature vectors to obtain a second signal subspace and a second noise subspace;
the sound source position is determined from the positions corresponding to the peaks of the orthogonal spatial spectrums of the second signal subspace and the second noise subspace.
In one embodiment, the computer program, when executed by the processor, performs an infrared thermal imaging analysis on an area corresponding to a sound source position to obtain leakage source information, including:
acquiring an image to be processed of a sound source position, wherein the image to be processed is infrared thermal imaging;
dividing an image to be processed according to the temperature value to obtain a sub-image;
and carrying out neural network identification on the sub-images to obtain leakage source information.
In one embodiment, the computer program, when executed by the processor, performs segmentation of an image to be processed according to a temperature value to obtain a sub-image, comprising:
Determining a rectangular frame of a binarized image of the image to be processed by a pixel accumulation method;
determining a target area according to the bit rectangle frame;
and performing character segmentation on the target area by a vertical projection method to obtain a sub-image.
In one embodiment, the processor, when executing the computer program, implements neural network identification on the sub-images to obtain leakage source information, including:
pooling the sub-images and extracting image features;
and analyzing the image characteristics to obtain leakage source information.
In one embodiment, the processor when executing the computer program realizes the segmentation of the image to be processed according to the temperature value, and before obtaining the sub-image, the method further comprises:
and carrying out binarization processing on the image to be processed.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The various embodiments in this disclosure are described in a progressive manner, and identical and similar parts of the various embodiments are all referred to each other, and each embodiment is mainly described as different from other embodiments.
The scope of the present disclosure is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present disclosure by those skilled in the art without departing from the scope and spirit of the disclosure. Such modifications and variations are intended to be included herein within the scope of the following claims and their equivalents.
Claims (11)
1. A method of locating a leak source, the method comprising:
acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the sound source and the array of the sound source;
determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
And carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
2. The leakage source positioning method according to claim 1, wherein the determining, according to the preset interval to which the distance belongs, to use a first algorithm or a second algorithm, and obtaining the sound source position according to the frequency by using the first algorithm or the second algorithm includes:
when the distance is greater than zero and smaller than or equal to a preset value, the sound source position is obtained through a first algorithm according to the frequency;
and when the distance is larger than a preset value, obtaining the sound source position through a second algorithm according to the frequency.
3. The leakage source localization method according to claim 2, wherein when the distance is greater than zero and less than or equal to a preset value, the sound source position is obtained by a first algorithm according to the frequency, comprising:
performing Fourier transform on the acoustic wave information to obtain a frequency domain signal;
performing matrix feature decomposition on the frequency domain signal to obtain a first feature vector;
arranging the first feature vectors according to first feature values of the first feature vectors to obtain a first signal subspace and a first noise subspace;
And determining the position corresponding to the peak value of the average spatial spectrum of the first signal subspace and the first noise subspace as a sound source position.
4. The leakage source positioning method according to claim 2, wherein when the distance is greater than a preset value, the sound source position is obtained by a second algorithm according to the frequency, comprising:
obtaining a covariance matrix according to the acoustic wave information;
performing matrix feature decomposition on the covariance matrix to obtain a second feature vector;
arranging the second eigenvectors according to the second eigenvalues of the second eigenvectors to obtain a second signal subspace and a second noise subspace;
and determining the position corresponding to the peak value of the orthogonal space spectrum of the second signal subspace and the second noise subspace as the sound source position.
5. The leakage source positioning method according to claim 1, wherein the performing infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information includes:
acquiring an image to be processed of the sound source position, wherein the image to be processed is infrared thermal imaging;
dividing the image to be processed according to the temperature value to obtain a sub-image;
And carrying out neural network identification on the sub-images to obtain the leakage source information.
6. The leakage source positioning method according to claim 5, wherein the segmenting the image to be processed according to the temperature value to obtain the sub-image includes:
determining a rectangular frame of a binarized image of the image to be processed by a pixel addition method;
determining a target area according to the bit rectangle frame;
and performing character segmentation on the target area by a vertical projection method to obtain the sub-image.
7. The leakage source positioning method according to claim 5, wherein the performing neural network recognition on the sub-image to obtain the leakage source information includes:
pooling the sub-images to extract image features;
and analyzing the image characteristics to obtain the leakage source information.
8. The leakage source positioning method according to claim 5, wherein before dividing the image to be processed according to the temperature value to obtain the sub-image, further comprising:
and carrying out binarization processing on the image to be processed.
9. A leak source positioning apparatus, the apparatus comprising:
The sound source acquisition unit is used for acquiring sound wave information of a sound source, wherein the sound wave information comprises wavelength and frequency;
the analysis unit is used for obtaining the distance from the sound source to the center of the array according to the wavelength and the distance between the receivers of the sound source and the array;
the sound source positioning unit is used for determining to adopt a first algorithm or a second algorithm according to a preset interval to which the distance belongs, and obtaining the sound source position according to the frequency through the first algorithm or the second algorithm, wherein the first algorithm is a matrix characteristic space decomposition algorithm focused on a formant frequency domain, and the second algorithm is a matrix characteristic space decomposition algorithm different from the first algorithm;
and the leakage source information unit is used for carrying out infrared thermal imaging analysis on the region corresponding to the sound source position to obtain leakage source information.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.
11. A computer storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311523977.7A CN117607960A (en) | 2023-11-15 | 2023-11-15 | Leakage source positioning method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311523977.7A CN117607960A (en) | 2023-11-15 | 2023-11-15 | Leakage source positioning method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117607960A true CN117607960A (en) | 2024-02-27 |
Family
ID=89952683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311523977.7A Pending CN117607960A (en) | 2023-11-15 | 2023-11-15 | Leakage source positioning method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117607960A (en) |
-
2023
- 2023-11-15 CN CN202311523977.7A patent/CN117607960A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105865723B (en) | Leakage inspection non-uniform correction method and gas leak detection apparatus | |
| Yao et al. | Detecting image splicing based on noise level inconsistency | |
| Yuan et al. | Fast hyperspectral anomaly detection via high-order 2-D crossing filter | |
| JP2024509411A (en) | Defect detection method, device and system | |
| Uss et al. | Maximum likelihood estimation of spatially correlated signal-dependent noise in hyperspectral images | |
| CN111652098B (en) | Product surface defect detection method and device | |
| US9305239B2 (en) | Detecting and processing small text in digital media | |
| EP1958158B1 (en) | Method for detecting streaks in digital images | |
| WO2013020143A1 (en) | Image-based crack quantification | |
| CN111476159A (en) | Method and device for training and detecting detection model based on double-angle regression | |
| US20230056564A1 (en) | Image authenticity detection method and apparatus | |
| Yuan et al. | A method for the evaluation of image quality according to the recognition effectiveness of objects in the optical remote sensing image using machine learning algorithm | |
| CN111563408B (en) | High-resolution image landslide automatic detection method with multi-level perception characteristics and progressive self-learning | |
| Mamatov et al. | Methods for improving contrast of agricultural images | |
| CN116630327B (en) | Boiler state abnormity monitoring system based on thermodynamic diagram | |
| CN109584262A (en) | Cloud detection method of optic, device and electronic equipment based on remote sensing image | |
| CN109409285B (en) | Remote sensing video target detection method based on overlapped slices | |
| Gao et al. | A novel multi-model cascade framework for pipeline defects detection based on machine vision | |
| US20230306578A1 (en) | Ultrasonic defect detection and classification system using machine learning | |
| CN117607960A (en) | Leakage source positioning method and device, computer equipment and storage medium | |
| Zou et al. | YOLOv7‐EAS: A Small Target Detection of Camera Module Surface Based on Improved YOLOv7 | |
| Bin et al. | Foreground fusion-based liquefied natural gas leak detection framework from surveillance thermal imaging | |
| CN115389514A (en) | Material defect detection method and device | |
| Shen et al. | Seismic trace editing by applying machine learning | |
| CN111669575B (en) | Method, system, electronic device, medium and terminal for testing image processing effect |
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 |