CN113962266B - Improved BAS-VMD-based pipeline leakage signal denoising method - Google Patents
Improved BAS-VMD-based pipeline leakage signal denoising method Download PDFInfo
- Publication number
- CN113962266B CN113962266B CN202111243771.XA CN202111243771A CN113962266B CN 113962266 B CN113962266 B CN 113962266B CN 202111243771 A CN202111243771 A CN 202111243771A CN 113962266 B CN113962266 B CN 113962266B
- Authority
- CN
- China
- Prior art keywords
- leakage signal
- pipeline leakage
- components
- component
- vmd
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims abstract description 28
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 24
- 241000254173 Coleoptera Species 0.000 claims abstract description 21
- 239000003345 natural gas Substances 0.000 claims abstract description 14
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 15
- 241001481710 Cerambycidae Species 0.000 claims description 14
- 230000001149 cognitive effect Effects 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000001914 filtration Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- 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
- F17D5/005—Protection or supervision of installations of gas pipelines, e.g. alarm
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Examining Or Testing Airtightness (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The invention relates to a pipeline leakage signal denoising method based on an improved BAS-VMD, which comprises the following steps: acquiring a pipeline leakage signal of the natural gas pipeline under a leakage working condition by using an acoustic wave sensor; the BAS is improved, a single longhorn beetle is changed into a plurality of longhorn beetles, and the longhorn beetles learn group experiences in movement to improve algorithm accuracy; determining the parameter mode quantity K and bandwidth constraint alpha in the VMD by utilizing the improved BAS algorithm, and carrying out self-adaptive decomposition on the pipeline leakage signal by the VMD decomposition signal to obtain a plurality of mode components; and screening out an effective component by using the Euclidean distance ED, reconstructing the effective component, and removing a noise component to obtain a denoised leakage signal. The invention can obtain better effect by denoising the pipeline leakage signal, and retain effective characteristics in the pipeline leakage signal while filtering noise.
Description
Technical Field
The invention relates to a denoising method used for signal processing in a pipeline leakage detection technology, in particular to a pipeline leakage signal denoising method based on an improved BAS-VMD.
Background
In the natural gas pipeline system, due to various external sound interferences and random noise of the acquisition system, a great amount of noise is contained in the sound wave signals acquired by the sensor, and the noise in the signals can seriously influence the analysis of useful signals. Therefore, it is critical to perform denoising processing before signal analysis, which helps to improve accuracy of signal analysis.
The leakage signal acquired by the sensor has a large amount of noise, the pipeline signal needs to be subjected to denoising treatment, and the Variational Modal Decomposition (VMD) is an effective signal denoising method, so that the method has a solid theoretical basis, and the problem of modal aliasing of the EMD and the problem of difficulty in selecting wavelet basis functions in wavelet decomposition are effectively solved. Each mode decomposed by the VMD comprises a frequency modulation and amplitude modulation function, so that effective separation of components can be realized in a self-adaptive mode.
Based on analysis of a nonlinear signal processing method, however, the value of the modal number K and the bandwidth constraint alpha of VMD decomposition are required to be preset before VMD decomposition, and the values of parameters K and alpha can influence the effect of VMD decomposition. The determination method of the modal number K value and the bandwidth constraint alpha of VMD decomposition does not have a clear selection standard, and parameters K and alpha are often required to be set manually in the actual decomposition process, so that the method has great subjectivity.
Disclosure of Invention
The invention aims to provide a pipeline leakage signal denoising method based on an improved BAS-VMD, which is used for solving the problem that pipeline leakage detection accuracy is affected by noise in a natural gas pipeline leakage signal.
The technical scheme adopted for solving the technical problems is as follows: the improved BAS-VMD-based pipeline leakage signal denoising method comprises the following steps of:
Step one, acquiring a pipeline leakage signal of a natural gas pipeline under a leakage working condition by utilizing an acoustic wave sensor;
Step two, improving the BAS, changing a single longhorn beetle into a plurality of longhorn beetles, and allowing the longhorn beetles to learn group experiences in movement so as to improve algorithm accuracy; each movement of the longhorn beetles is guided by the self optimal position and the group optimal position, and the movement mode of the longhorn beetles is expressed as follows by a formula:
xnext＝x-A*step*dir*sign(fleft-fright)+S*(xbest-x)
Wherein: x is the position of the current generation longicorn; x next is the position of the next generation longicorn; a is a cognitive factor which increases with iteration number; s is a learning factor, and decreases with iteration times; step is the step size; fleft is the fitness function value of the longicorn left whisker; fright is the fitness function value of the right beard of the longicorn; xbest is the best position of the longicorn until now;
step three, determining the parameter mode quantity K and bandwidth constraint alpha in the VMD by utilizing the improved BAS algorithm, and carrying out self-adaptive decomposition on pipeline leakage signals by the VMD decomposition signals to obtain a plurality of mode components;
and step four, screening out an effective component by using the Euclidean distance ED, reconstructing the effective component, and removing a noise component to obtain a denoised leakage signal.
The specific method of the fourth step in the scheme is as follows: ED between each modal component and the probability density of the pipeline leakage signal is calculated, and a first local maximum value point after the ED of the adjacent component and the pipeline leakage signal starts to increase is used as a demarcation point of the effective component and the noise component; screening out effective components, and regarding the rest modal components as noise components; and reconstructing by using the effective component to obtain the denoised pipeline leakage signal.
The specific method of the fourth step in the scheme is as follows: the Euclidean distance ED between the probability density functions of each modal component and the pipeline leakage signal after decomposition is calculated, the similarity degree of the modal component and the pipeline leakage signal is represented by using the Euclidean distance ED between the probability density functions of each modal component and the pipeline leakage signal, effective components are selected by evaluating ED of each modal component and the pipeline leakage signal, the increment of ED of two adjacent modal components and the pipeline leakage signal is evaluated, two adjacent components with the largest ED increment are used as boundary points selected by the effective components, the components before the boundary points are used as the effective components, the components after the boundary points are used as noise components, and the noise components are removed to obtain the denoised leakage signal.
The invention has the following beneficial effects:
According to the invention, a pipeline leakage signal of the natural gas pipeline under a leakage working condition is acquired by using an acoustic wave sensor, and the pipeline leakage signal is decomposed by adopting a VMD algorithm according to the characteristic of non-stationarity of the pipeline leakage signal, wherein parameters K and alpha in the VMD are determined by using an improved BAS algorithm, so that the natural gas pipeline leakage signal is subjected to self-adaptive decomposition, and a plurality of components are obtained. And calculating the Euclidean Distance (ED) between each component after decomposition and the probability density function between the pipeline leakage signals, selecting effective components by evaluating the ED of each component and the pipeline leakage signals, reconstructing the effective components, removing noise components, and further obtaining the denoised pipeline leakage signals. The invention can obtain better effect by denoising the pipeline leakage signal, and retain effective characteristics in the pipeline leakage signal while filtering noise.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a time-frequency spectrum of an original acoustic signal for a pipeline leakage condition.
Fig. 3 is an iterative diagram of the improved BAS algorithm optimization for the K and α parameters.
Fig. 4 is a time domain diagram of modes after VMD decomposition.
Fig. 5 is a time-frequency spectrum diagram of the leaked signal after denoising.
Detailed Description
The invention is further described with reference to the accompanying drawings:
The improved BAS-VMD-based pipeline leakage signal denoising method comprises the following steps of:
And step 1, acquiring a pipeline leakage signal of the natural gas pipeline under a leakage working condition by adopting an acoustic wave sensor, and taking the pipeline leakage signal as an original natural gas pipeline leakage signal.
Step 2, improving the BAS, changing a single longhorn beetle into a plurality of longhorn beetles, and allowing the longhorn beetles to learn group experiences in movement so as to improve algorithm accuracy; each movement of the longhorn beetles is guided by the self optimal position and the group optimal position, and the movement mode of the longhorn beetles is expressed as follows by a formula:
xnext＝x-A*step*dir*sign(fleft-fright)+S*(xbest-x)
Wherein: x is the position of the current generation longicorn; x next is the position of the next generation longicorn; a is a cognitive factor which increases with iteration number; s is a learning factor, and decreases with iteration times; step is the step size; fleft and fright are fitness function values of the left whisker and the right whisker of the longicorn respectively; xbest is the best position of the longicorn until now.
Step 3, determining parameters K and alpha by utilizing an improved BAS algorithm, performing VMD decomposition on the acquired pipeline acoustic signals, namely performing self-adaptive decomposition on the natural gas pipeline leakage signals to obtain a plurality of modal components;
And 4, screening out an effective component by using an Euclidean Distance (ED), reconstructing the effective component, removing a noise component, and further obtaining a denoised leakage signal, wherein the method comprises the following steps of:
The Euclidean Distance (ED) between the probability density functions of each modal component and the pipeline leakage signal after decomposition is calculated, the Euclidean distance ED between the probability density functions of each modal component and the pipeline leakage signal is utilized to represent the similarity degree of the modal component and the pipeline leakage signal, the ED of each modal component and the pipeline leakage signal is evaluated to select effective components, the increment of ED of two adjacent modal components and the pipeline leakage signal is evaluated, two adjacent components with the largest ED increment are taken as turning points selected by the effective components, the component before the turning points is taken as the effective components, the component after the turning points is taken as noise components, and the noise components are removed to obtain the denoised leakage signal.
The beneficial effects of the present invention are illustrated by the following examples:
Example 1:
The experimental parameters were as follows: the experimental data of the invention are all derived from a simulation experiment platform for detecting the leakage of the natural gas pipeline in northeast petroleum university, the experiment platform simulates an actual field pipeline to be used as a high-pressure gas pipeline leakage detection device by means of an HD-II type pipeline leakage detection system, and the leakage effect of the natural gas pipeline under the real condition is simulated by controlling a 4-branch ball valve switch arranged on the pipeline. The pipeline pressure is 0.5MPa, the flow is 60m3/h, and the sampling frequency of the signal is set to be 1000Hz.
This improved BAS-VMD based pipeline leakage signal denoising method is shown in fig. 1: the method comprises the following steps:
s1, firstly, collecting a pipeline leakage signal of a laboratory pipeline under a leakage working condition by using an acoustic wave sensor, wherein the time domain waveform and the frequency spectrum of the leakage signal are shown in figure 2.
S2, improving the BAS algorithm, changing a single longhorn beetle into a plurality of longhorn beetles, and allowing the longhorn beetles to learn group experiences in motion so as to improve algorithm accuracy.
S3, determining parameters K and alpha in the VMD by using an improved BAS optimization algorithm method, wherein the obtained K is 6, the alpha is 2960, and an improved BAS optimization algorithm iteration chart is shown in FIG. 3; VMD decomposition is carried out on the collected pipeline acoustic wave signals.
S4, as shown in a VMD decomposition result diagram in FIG. 4, ED between each component and the probability density of the pipeline leakage signal is calculated, and the first local maximum point after ED of the adjacent component and the pipeline leakage signal starts to increase is used as the demarcation point of the effective component and the noise component. The effective components are screened out, and the remaining components are regarded as noise components. And reconstructing by using the effective component to obtain the denoised leakage signal.
As can be seen from a comparison between fig. 2 and fig. 5, the noise-containing pipeline leakage signal has a significant component distributed mainly in a low frequency region, and in the time domain, the noise-removed pipeline leakage signal is smoother; in the frequency domain, the denoised pipeline leakage signal is mainly distributed in the low frequency band. It can be derived from this that the effective characteristics in the pipeline leakage signal are preserved while noise is filtered out, verifying the feasibility of the invention.
In order to solve the problem that the pipeline leakage detection accuracy is affected by noise in a natural gas pipeline leakage signal, the invention provides an improved BAS-VMD pipeline leakage signal denoising method. Secondly, preprocessing leakage signals acquired by the acoustic wave sensor by adopting a VMD denoising method, wherein parameters K and alpha in the VMD are determined by utilizing an improved BAS optimization algorithm, so that the leakage signals of the natural gas pipeline are subjected to self-adaptive decomposition, and a plurality of modal components are obtained. And then, calculating the Euclidean Distance (ED) between each decomposed component and the probability density function of the original signal, selecting an effective component by evaluating the ED between each component and the original signal, reconstructing the effective component, removing the noise component, and further obtaining the denoised leakage signal. Finally, through analyzing the experimental result, the method verifies that the leakage signal can obtain a better effect after the denoising treatment of the method, the effective characteristics in the original leakage signal are reserved while the noise is filtered, and the method has a certain application value in the denoising treatment of the pipeline leakage signal.
Claims (3)
1. A method for denoising a pipeline leakage signal based on an improved BAS-VMD, comprising the steps of:
Step one, acquiring a pipeline leakage signal of a natural gas pipeline under a leakage working condition by utilizing an acoustic wave sensor;
Step two, improving the BAS, changing a single longhorn beetle into a plurality of longhorn beetles, and allowing the longhorn beetles to learn group experiences in movement so as to improve algorithm accuracy; each movement of the longhorn beetles is guided by the self optimal position and the group optimal position, and the movement mode of the longhorn beetles is expressed as follows by a formula:
xnext＝x-A*step*dir*sign(fleft-fright)+S*(xbest-x)
Wherein: x is the position of the current generation longicorn; x next is the position of the next generation longicorn; a is a cognitive factor which increases with iteration number; s is a learning factor, and decreases with iteration times; step is the step size; fleft is the fitness function value of the longicorn left whisker; fright is the fitness function value of the right beard of the longicorn; xbest is the best position of the longicorn until now;
step three, determining the parameter mode quantity K and bandwidth constraint alpha in the VMD by utilizing the improved BAS algorithm, and carrying out self-adaptive decomposition on pipeline leakage signals by the VMD decomposition signals to obtain a plurality of mode components;
and step four, screening out an effective component by using the Euclidean distance ED, reconstructing the effective component, and removing a noise component to obtain a denoised leakage signal.
2. The improved BAS-VMD based pipe leakage signal denoising method of claim 1, wherein: the specific method of the fourth step is as follows: calculating ED between each modal component and the probability density of the pipeline leakage signal, and taking the first local maximum value point after the ED of the adjacent component and the pipeline leakage signal begins to increase as the boundary point of the effective component and the noise component; screening out effective components, and regarding the rest modal components as noise components; and reconstructing by using the effective component to obtain the denoised pipeline leakage signal.
3. The improved BAS-VMD based pipe leakage signal denoising method of claim 2, wherein: the specific method of the fourth step is as follows: the Euclidean distance ED between the probability density functions of each modal component and the pipeline leakage signal after decomposition is calculated, the similarity degree of the modal component and the pipeline leakage signal is represented by using the Euclidean distance ED between the probability density functions of each modal component and the pipeline leakage signal, effective components are selected by evaluating ED of each modal component and the pipeline leakage signal, the increment of ED of two adjacent modal components and the pipeline leakage signal is evaluated, two adjacent components with the largest ED increment are used as boundary points selected by the effective components, the components before the boundary points are used as the effective components, the components after the boundary points are used as noise components, and the noise components are removed to obtain the denoised leakage signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111243771.XA CN113962266B (en) | 2021-10-25 | 2021-10-25 | Improved BAS-VMD-based pipeline leakage signal denoising method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111243771.XA CN113962266B (en) | 2021-10-25 | 2021-10-25 | Improved BAS-VMD-based pipeline leakage signal denoising method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113962266A CN113962266A (en) | 2022-01-21 |
| CN113962266B true CN113962266B (en) | 2024-06-14 |
Family
ID=79466978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111243771.XA Active CN113962266B (en) | 2021-10-25 | 2021-10-25 | Improved BAS-VMD-based pipeline leakage signal denoising method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113962266B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130064403A (en) * | 2011-12-08 | 2013-06-18 | 한국원자력연구원 | A method for reducing mechanical noise of cross-correlation method for leak detection of a buried pipe |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102007023559B3 (en) * | 2007-05-21 | 2008-12-04 | Continental Automotive Gmbh | Diagnostic method and device for diagnosing an intake tract of an internal combustion engine |
| CN109255490B (en) * | 2018-09-28 | 2022-03-22 | 西安建筑科技大学 | KPCA-BAS-GRNN-based buried pipeline external corrosion rate prediction method |
| CN110454687B (en) * | 2019-07-22 | 2020-09-22 | 常州大学 | Pipeline multipoint leakage positioning method based on improved VMD |
| CN113269082A (en) * | 2021-05-21 | 2021-08-17 | 合肥工业大学 | Partial discharge threshold denoising method based on improved variational modal decomposition |
-
2021
- 2021-10-25 CN CN202111243771.XA patent/CN113962266B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130064403A (en) * | 2011-12-08 | 2013-06-18 | 한국원자력연구원 | A method for reducing mechanical noise of cross-correlation method for leak detection of a buried pipe |
Non-Patent Citations (1)
| Title |
|---|
| 改进VMD算法在管道泄漏检测中的应用;杨丹迪;路敬祎;周怡娜;王闯;董宏丽;;吉林大学学报(信息科学版);20200715(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113962266A (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108107475B (en) | Borehole microseismic denoising method based on experience wavelet transformation and multi-threshold function | |
| CN107505652B (en) | A kind of mine microquake signal discrimination method based on energy-distributing feature | |
| CN102998706B (en) | Method and system for attenuating seismic data random noise | |
| CN104807534B (en) | Equipment eigentone self study recognition methods based on on-line vibration data | |
| CN105242309B (en) | The drawing method and device of rule interference in a kind of geological data | |
| CN103424183B (en) | Method for eliminating abnormal interference on detection for mechanical vibration signals | |
| CN106199532A (en) | Gpr Signal noise-reduction method based on mixing Fourier wavelet analysis | |
| CN111562597A (en) | Beidou satellite navigation interference source identification method based on BP neural network | |
| CN109374298B (en) | Bearing fault diagnosis method based on cross-correlation singular value | |
| CN112539887A (en) | WT-LCD-WD-based pipeline leakage signal denoising method | |
| CN114492538A (en) | Local discharge signal denoising method for urban medium-voltage distribution cable | |
| CN113723171A (en) | Electroencephalogram signal denoising method based on residual error generation countermeasure network | |
| CN103308829B (en) | A kind of GIS single Partial discharge signal extracts and trigger instants method of adjustment | |
| CN109630908B (en) | Pipeline leakage positioning method capable of reducing noise for multiple times | |
| CN113962266B (en) | Improved BAS-VMD-based pipeline leakage signal denoising method | |
| Du et al. | Study on optical fiber gas-holdup meter signal denoising using improved threshold wavelet transform | |
| CN117688369A (en) | DAS-based grouting pipeline data noise reduction method | |
| CN114441111B (en) | Pipeline leakage infrasonic wave signal analysis method and system | |
| CN115563480A (en) | Gear fault identification method for screening octave geometric modal decomposition based on kurtosis ratio coefficient | |
| CN112836583B (en) | Wind turbine fault diagnosis method | |
| CN105156901B (en) | A kind of optical fiber early warning system noise-reduction method and device based on wavelet analysis | |
| CN113567129A (en) | CEEMD-based noise reduction method for train bearing vibration signal | |
| CN113093282A (en) | Desert data denoising method based on geometric modal characteristic parallel network | |
| CN112764108B (en) | Novel seismic data noise suppression algorithm based on improved empirical wavelet transformation | |
| CN112213785A (en) | Seismic data desert noise suppression method based on feature-enhanced denoising network |
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 |