CN105927861A - Feature extraction method based on blind source separation algorithm of wavelet transform fusion for leakage acoustic wave - Google Patents
Feature extraction method based on blind source separation algorithm of wavelet transform fusion for leakage acoustic wave Download PDFInfo
- Publication number
- CN105927861A CN105927861A CN201610246962.4A CN201610246962A CN105927861A CN 105927861 A CN105927861 A CN 105927861A CN 201610246962 A CN201610246962 A CN 201610246962A CN 105927861 A CN105927861 A CN 105927861A
- Authority
- CN
- China
- Prior art keywords
- signal
- leakage
- source separation
- blind source
- separation algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/148—Wavelet transforms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Acoustics & Sound (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a feature extraction method based on a blind source separation algorithm of wavelet transform fusion for a leakage acoustic wave. The feature extraction method comprises the following steps: arranging a sensor on a detected pipeline, carrying out signal acquisition on a leakage point through the sensor, and obtaining a leakage acoustic wave acquisition signal; pre-processing the leakage acoustic wave acquisition signal by virtue of wavelet transform to obtain observation signals, and processing the observation signals by virtue of the blind source separation algorithm to obtain a target signal; and evaluating the target signal in step 2, and optimizing the composition of the observation signals. The feature extraction method based on the blind source separation algorithm of wavelet transform fusion for the leakage acoustic wave, which is provided by the invention, has the following beneficial effects: the target processing signal is evaluated through two evaluation parameters, that is, leakage time sampling point deviation and amplitude loss; and the method is capable of accurately locating a leakage time, and obvious in compensation action on the leakage amplitude of the weak signal.
Description
Technical field
The present invention relates to pipeline inspection technology field, especially a kind of based on the calculation of Wavelet Transform Fusion blind source separating
The leakage acoustic characteristic extracting method of method.
Background technology
The leakage monitoring method that can apply to oil and gas pipes at present has many kinds, wherein, sonic method and tradition
Mass balance approach, negative pressure wave method, transient model method etc. is compared has plurality of advantages: highly sensitive, location
Precision is high, rate of false alarm is low, the detection time is short, strong adaptability；Measure be in pipeline fluid faint dynamically
Pressure variety, unrelated with the absolute value of pipeline performance pressure；Response frequency is wider, and detection range is wider.
Gas pipeline occurs to produce acoustic signals during leakage, declines along with the increase leakage signal of propagation distance produces
Subtracting, wave character is covered by noise, effectively leaks feature for extracting, and Chinese scholars has carried out substantial amounts of
Research, according to finding, relates to the special of gas pipeline leakage acoustic characteristic extracting method outside Current Domestic
Profit mainly has:
United States Patent (USP) US6389881 discloses a kind of technology utilizing sound wave technology to carry out pipeline leakage testing,
This technology utilizes dynamic pressure in sensor acquisition pipe, uses pattern match filtering technique to be filtered signal
Process, get rid of noise, reduce interference, improve positioning precision；
Chinese patent 200710177617.0 discloses a kind of leakage based on pressure and sound wave information fusion inspection
Survey method, the method gathers pipeline upstream and downstream pressure and acoustic signals (in 0.2-20Hz) respectively, through number
Obtain final detection result according to the process of filtering, feature-based fusion and three levels of decision level fusion, and utilize
The localization method merged based on correlation analysis, wavelet analysis etc. carries out leakage location, improves Leak Detection
Accuracy and positioning precision.
Chinese patent 201510020155.6 discloses a kind of gas oil pipe leakage based on magnitudes of acoustic waves location
Method, the method use through wavelet analysis process after obtain low-frequency range magnitudes of acoustic waves to carry out Leak Detection and
Location, it is proposed that a kind of leakage locating method not considering the velocity of sound and time difference.
Chinese patent CN104614069A discloses a kind of based on joint approximate diagonalization blind source separation algorithm
Electrical equipment fault sound detection method, step includes: use microphone array；It is right to use based on combining approximation
Keratinization blind source separation algorithm separates each individual sources letter for the acoustical signal using microphone array collection
Number；The Mel frequency cepstral coefficient MFCC of extraction individual sources signal, as sound characteristic parameter, passes through pattern
Matching algorithm identification acoustical signal, after sound pattern to be tested is mated with all of sample for reference template,
The sample for reference template of matching distance minimum is exactly the result of power equipment work sound identification.
Existing patent is wavelet transformation or the application of blind source separation algorithm single treatment method, to two kinds
The integration technology of method does not describe, and is embodied in:
(1) wavelet transformation can extract the signal characteristic of low-frequency range, is to apply the most universal signal processing side
Method, but wavelet transformation there is also more significantly defect when signal extraction simultaneously, in actual applications, low
The acquisition of frequency band signals feature needs primary signal is carried out deep layer decomposition, is leaking the location in moment and is letting out
In the acquisition of leakage amplitude, relatively large deviation easily occurs, easily cause the calculating error of time difference so that location is by mistake
Difference is bigger；Leakage amplitude loss easily causes the distortion of leakage waveform, easily causes failing to judge and judging by accident of leakage.
(2) for solving this problem, use blind source separation algorithm that signal is processed, it has been investigated that blind
Source separates and can be accurately positioned the leakage moment, and does not the most lose in terms of leakage amplitude, has mended
Repay, especially compensate when signal is the faintest and become apparent from, but in use, blind source separating equally exists
More significantly defect: echo signal order, kind that blind source separating obtains not can determine that.
Summary of the invention
It is an object of the invention to as overcoming above-mentioned the deficiencies in the prior art, it is provided that a kind of based on Wavelet Transform Fusion
The leakage acoustic characteristic extracting method of blind source separation algorithm.
For achieving the above object, the present invention uses following technical proposals:
The leakage acoustic characteristic extracting method of blind source separation algorithm is merged based on wavelet character approximate signal, including
Following steps:
Step one: arrange sensor on tested pipeline, carries out signals collecting by sensor to leakage point,
Obtain leakage sound collecting signal；
Step 2: utilize wavelet transformation that leakage sound collecting signal is carried out pretreatment, obtain multiple details letter
Number, will leak out sound collecting signal and multiple detail signal as observation signal and blind to observation signal employing
Source separation algorithm processes, and obtains echo signal；
Step 3, is evaluated the echo signal in step 2, and carries out observation signal composition preferably.
Preferably, in described step one, sonic sensor uses dynamic pressure transducer.
Preferably, in described step 2, the wavelet basis that wavelet transformation uses is sym8, and Decomposition order is according to biography
The signal kinds contained in the leakage sound collecting signal of sensor collection determines, described signal kinds includes leakage
Acoustic signals, background noise and hydrodynamic noise.
Preferably, described background noise includes the operating of power-equipment, the noise of pipeline external environment and hard
The noise that part equipment, circuit produce；Described hydrodynamic noise includes the turbulence noise that fluid flowing produces.
Preferably, in described step 2, observation signal acquisition methods specifically comprises the following steps that
Step S201: will leak out sound collecting signal as primary signal, determine wavelet decomposition number of plies N, N
More than or equal to 2, using primary signal as signal to be decomposed, carry out wavelet decomposition, decompose and obtain the most respectively
One layer of detail signal and ground floor approximate signal；
Step S202: using ground floor approximate signal as signal to be decomposed, treats decomposed signal and carries out little wavelength-division
Solve, obtain second layer detail signal corresponding to signal to be decomposed and second layer approximate signal respectively；
Step S203: using N-1 layer approximate signal as signal to be decomposed, repeated execution of steps S202, directly
To reaching Decomposition order N, N-1 layer approximate signal wavelet decomposition correspondence n-th layer detail signal and n-th layer
Approximate signal；
Step S204: choose ground floor to each layer detail signal corresponding to n-th layer and n-th layer approximate signal
As observation signal.
It is further preferred that the described method according to signal kinds confirmation Decomposition order is: Decomposition order is equal to
The signal kinds contained in the leakage acoustic signals of sensor acquisition subtracts 1.
Preferably, in described step 2, blind source separation algorithm is used to carry out processing the number obtaining echo signal
Mode have two kinds: one be the sum of echo signal equal to the sum of observation signal, i.e. have m when observation signal
Individual, then echo signal also has m；Two is that directly definition echo signal number is one, i.e. works as observation signal
Having m, echo signal has and only one of which.
Preferably, in described step 3, utilize leakage instance sample point deviation and amplitude loss as evaluating ginseng
Number.
Described leakage instance sample point deviation refers to the leakage instance sample point of echo signal and the leakage of primary signal
The difference of instance sample point.Described leakage instance sample point deviation the least representative leakage moment location is more accurate.
Described amplitude loses the leakage amplitude the referring to echo signal difference with the leakage amplitude of primary signal with original
The ratio of the absolute value of signals leakiness amplitude.Amplitude loss is negative value, and this value absolute value is the biggest, represents amplitude
Compensate the most notable.
The invention has the beneficial effects as follows:
1. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm that the present invention provides
Lose two evaluatings by leakage instance sample point deviation and amplitude target process signal is evaluated,
The leakage moment can be accurately positioned by the method, and small-signal leaks the compensating action of amplitude simultaneously
Substantially；
2. the present invention solves present stage wavelet transformation and in leakage moment location and leaks amplitude offset error relatively
Greatly, blind source separating echo signal order, the unascertainable problem of kind, improve sonic method Leak Detection with
The suitability of location technology；
3. the inventive method is simple, easy to operate, to extracting oil and gas pipes sonic method leakage detection and localization side
The leakage acoustic characteristic suitability in method is strong.
Accompanying drawing explanation
Fig. 1 is that the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides is special
Levy the schematic diagram of extracting method；
Fig. 2 is that the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides is special
Levy extracting method implementing procedure schematic diagram；
Fig. 3 is that the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides is special
Levy extracting method primary signal before treatment schematic diagram；
Fig. 4 a is the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides
The first aim signal schematic representation that feature extracting method obtains after processing；
Fig. 4 b is the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides
The second target signal schematic representation that feature extracting method obtains after processing；
Fig. 4 c is the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides
The 3rd the echo signal schematic diagram that feature extracting method obtains after processing；
Fig. 5 is that the leakage sound wave based on Wavelet Transform Fusion blind source separation algorithm that the embodiment of the present invention provides is special
Levy the echo signal schematic diagram obtained after extracting method processes.
Detailed description of the invention
The present invention is further described with embodiment below in conjunction with the accompanying drawings.
As it is shown in figure 1, leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm
Flow chart uses following experiment parameter to this with reference to Fig. 1, the present invention according to the technical scheme that summary of the invention provides
Invent and carry out experimental verification:
Experiment parameter is as follows: distance leakage point 109m when primary signal is that under 2MPa, 0.6mm leaks aperture
The signal of sensor acquisition, be 2 with reference to Fig. 3, Decomposition order N, sample frequency f is 3000Hz, little
Wave conversion analytic function is sym8 or db4.
Embodiment 1: in this embodiment, the blind source separation algorithm of employing carries out processing the number obtaining echo signal
Purpose mode is that the sum of echo signal is equal to observation signal.Primary signal is A0, and wavelet transformation obtains after decomposing
To ground floor observation signal be D1, second layer observation signal is D2 and A2, i.e. blind source in the step 2
The observation signal of separation algorithm is A2, D2, D1, more respectively to A2, D2, D1 carry out blind source separating,
To echo signal.
As shown in Fig. 3, Fig. 4 a, Fig. 4 b, Fig. 4 c, Fig. 4 represents that the method using the present invention to provide obtains
Three echo signals.
Embodiment 2: in this embodiment, uses blind source separation algorithm to carry out processing the number obtaining echo signal
Mode for definition echo signal have and only one of which.Fig. 5 represents what the method using the present invention to provide obtained
One echo signal.
With reference to Fig. 4 a, Fig. 4 b and Fig. 4 c, according to the experiment accompanying drawing of embodiment 1 it can be seen that primary signal
Amplitude is-5.06159kPa, and primary signal leakage moment correspondence sampled point is 46441；Can be seen by Fig. 4 a
Going out, leakage acoustic signals amplitude is-9.53160kPa, and leakage acoustic signals leakage moment correspondence sampled point is
46441.Echo signal close with primary signal in 3 signals that invention obtains is leakage sound wave letter
Number, remaining 2 are respectively background noise and hydrodynamic noise, and leakage acoustic signals, background noise and flowing
The sequence of noise is followed successively by 1,2,3, so, the present invention will leak out the signal kinds contained in acoustic signals
Classify, and the order of echo signal is confirmed.The determination mode of this echo signal number is
Optimal way, because the present invention lets out in view of not only to obtain from leakage sound collecting signal in experimentation
Leakage acoustic signals, also to enter the background noise and the hydrodynamic noise that obtain from leakage sound collecting signal
The research of one step, to this end, preferred above-mentioned echo signal number validation testing.
With reference to Fig. 5, according to the experiment accompanying drawing of embodiment 1 it can be seen that leakage acoustic signals amplitude is
-9.53160kPa, leakage acoustic signals leakage sampled point corresponding to moment is 46441.Can according to above-mentioned data
To find out, the leakage instance sample point of the echo signal that the method that the present invention provides obtains and the width of primary signal
Value deviation is 0, and the leakage magnitudes of acoustic waves of echo signal that obtains of the present invention is more than the amplitude of primary signal,
Therefore the method that the present invention provides is more accurate to leakage moment location, and amplitude loss is for-88.31%, i.e. lets out
Leakage amplitude compensation effect is obvious.If the present invention only obtains leakage acoustic signals from leakage sound collecting signal,
The echo signal number that embodiment 2 can be used to use determines that mode, echo signal have been defined as and only one of which,
So the problem that the sequence of echo signal, kind are distinguished need not be considered.
In sum, the method that the present invention provides is lost two by leakage instance sample point deviation and amplitude and is commented
Valency parameters on target signal is evaluated, and the leakage moment of leakage sound wave can be accurately positioned by the method,
The compensating action that small-signal leaks amplitude simultaneously is obvious, therefore, effectively reduces present stage small echo and becomes
Change and leaking the problem that moment error is bigger.
Therefore, echo signal effectively can be classified after blind source separating of the present invention, and then improve sound
The practicality of ripple method leakage detection and localization.
Although the detailed description of the invention of the present invention is described by the above-mentioned accompanying drawing that combines, but not to the present invention
The restriction of protection domain, one of ordinary skill in the art should be understood that on the basis of technical scheme,
Those skilled in the art need not to pay various amendments or deformation that creative work can make still in the present invention
Protection domain within.
Claims (10)
1. leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm, is characterized in that,
Comprise the following steps:
Step one: arrange sensor on tested pipeline, carries out signals collecting by sensor to leakage point,
Obtain leakage sound collecting signal；
Step 2: utilize wavelet transformation that leakage sound collecting signal is carried out pretreatment, obtain multiple details letter
Number, will leak out sound collecting signal and multiple detail signal as observation signal and blind to observation signal employing
Source separation algorithm processes, and obtains echo signal；
Step 3, is evaluated the echo signal in step 2, and carries out observation signal composition preferably.
2. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 1 carries
Access method, is characterized in that, in described step one, sonic sensor uses dynamic pressure transducer.
3. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 1 carries
Access method, is characterized in that, in described step 2, the wavelet basis that wavelet transformation uses is sym8, Decomposition order
Being determined by the signal kinds contained in the leakage sound collecting signal of sensor acquisition, described signal kinds includes
Leakage acoustic signals, background noise and hydrodynamic noise.
4. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 3 carries
Access method, described background noise includes the operating of power-equipment, and noise and the hardware of pipeline external environment set
The noise that standby, circuit produces；Described hydrodynamic noise includes the turbulence noise that fluid flowing produces.
5. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 3 carries
Access method, in described step 2, observation signal acquisition methods specifically comprises the following steps that
Step S201: will leak out sound collecting signal as primary signal, determine wavelet decomposition number of plies N, N
More than or equal to 2, using primary signal as signal to be decomposed, carry out wavelet decomposition, decompose and obtain the most respectively
One layer of detail signal and ground floor approximate signal；
Step S202: using ground floor approximate signal as signal to be decomposed, treats decomposed signal and carries out little wavelength-division
Solve, obtain second layer detail signal corresponding to signal to be decomposed and second layer approximate signal respectively；
Step S203: using N-1 layer approximate signal as signal to be decomposed, repeated execution of steps S202, directly
To reaching Decomposition order N, N-1 layer approximate signal wavelet decomposition correspondence n-th layer detail signal and n-th layer
Approximate signal；
Step S204: choose ground floor to each layer detail signal corresponding to n-th layer and n-th layer approximate signal
As observation signal.
6. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 5 carries
Access method, the described method according to signal kinds confirmation Decomposition order is: Decomposition order is equal to leakage sound wave letter
Number kind subtracts 1.
7. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 5 carries
Access method, described echo signal quantity definition mode is the sum sum equal to observation signal of echo signal.
8. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 5 carries
Access method, described echo signal quantity definition mode be echo signal number be one.
9. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 1 carries
Access method, in described step 3, utilizes leakage instance sample point deviation and amplitude to lose as evaluating.
10. leakage acoustic characteristic based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 8
Extracting method, described leakage instance sample point deviation refers to leakage instance sample point and the primary signal of echo signal
The difference of leakage instance sample point；The loss of described amplitude refers to the leakage amplitude of echo signal and letting out of primary signal
The difference of leakage amplitude leaks the ratio of the absolute value of amplitude with primary signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610246962.4A CN105927861B (en) | 2016-04-20 | 2016-04-20 | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610246962.4A CN105927861B (en) | 2016-04-20 | 2016-04-20 | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105927861A true CN105927861A (en) | 2016-09-07 |
| CN105927861B CN105927861B (en) | 2018-12-07 |
Family
ID=56838568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610246962.4A Active CN105927861B (en) | 2016-04-20 | 2016-04-20 | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105927861B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107907279A (en) * | 2017-11-20 | 2018-04-13 | 中国石油大学(华东) | Multiphase flow pipeline leakage acoustic signals analysis method based on wavelet coefficient amplitude |
| CN110778922A (en) * | 2019-10-26 | 2020-02-11 | 山东佑安消防***有限公司 | Pipe network leakage point searching method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006146484A (en) * | 2004-11-18 | 2006-06-08 | Institute Of Physical & Chemical Research | Signal separation system, signal separation method, and signal separation program |
| US7603401B2 (en) * | 1998-11-12 | 2009-10-13 | Sarnoff Corporation | Method and system for on-line blind source separation |
| CN104595730A (en) * | 2015-01-15 | 2015-05-06 | 中国石油大学(华东) | Oil and gas pipeline leakage positioning method based on sound wave amplitude attenuation model |
-
2016
- 2016-04-20 CN CN201610246962.4A patent/CN105927861B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7603401B2 (en) * | 1998-11-12 | 2009-10-13 | Sarnoff Corporation | Method and system for on-line blind source separation |
| JP2006146484A (en) * | 2004-11-18 | 2006-06-08 | Institute Of Physical & Chemical Research | Signal separation system, signal separation method, and signal separation program |
| CN104595730A (en) * | 2015-01-15 | 2015-05-06 | 中国石油大学(华东) | Oil and gas pipeline leakage positioning method based on sound wave amplitude attenuation model |
| CN104595730B (en) * | 2015-01-15 | 2015-08-12 | 中国石油大学(华东) | A kind of oil and gas pipeline leakage localization method based on magnitudes of acoustic waves attenuation model |
Non-Patent Citations (1)
| Title |
|---|
| 吴晓，刘瑞林，董素荣，周广猛，许翔，刘刚: "基于小波变换的盲分离技术在管道内检测器地面标记", 《国际会议论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107907279A (en) * | 2017-11-20 | 2018-04-13 | 中国石油大学(华东) | Multiphase flow pipeline leakage acoustic signals analysis method based on wavelet coefficient amplitude |
| CN110778922A (en) * | 2019-10-26 | 2020-02-11 | 山东佑安消防***有限公司 | Pipe network leakage point searching method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105927861B (en) | 2018-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110454687B (en) | Pipeline multipoint leakage positioning method based on improved VMD | |
| CN101592288B (en) | Method for identifying pipeline leakage | |
| CN106287240B (en) | A kind of pipeline leakage testing device and single-sensor localization method based on sound emission | |
| CN110762398B (en) | Oil and gas pipeline leakage detection method and system based on excitation response | |
| Meng et al. | Leak localization of gas pipeline based on the combination of EEMD and cross-spectrum analysis | |
| CN105909979A (en) | Leakage acoustic wave feature extraction method based on fusion of wavelet transform and blind source separation algorithm | |
| CN104595729A (en) | Oil and gas pipeline leakage positioning method based on sound wave amplitude | |
| Sheng et al. | Applications in bearing fault diagnosis of an improved Kurtogram algorithm based on flexible frequency slice wavelet transform filter bank | |
| CN103033567A (en) | Pipeline defect signal identification method based on guided wave | |
| CN109063762A (en) | A kind of line clogging fault recognition method based on DT-CWT and S4VM | |
| Mei et al. | Adaptive signal enhancement based on improved VMD-SVD for leak location in water-supply pipeline | |
| CN105928666A (en) | Leakage acoustic characteristic extraction method based on Hilbert-Huang transform and blind source separation | |
| Han et al. | Plastic pipeline leak localization based on wavelet packet decomposition and higher order cumulants | |
| CN105927861A (en) | Feature extraction method based on blind source separation algorithm of wavelet transform fusion for leakage acoustic wave | |
| CN109630908B (en) | Pipeline leakage positioning method capable of reducing noise for multiple times | |
| CN116304638A (en) | Pipeline leakage aperture identification method based on improved LCD | |
| Jiang et al. | Denoising method of pipeline leakage signal based on VMD and Hilbert transform | |
| Nicola et al. | Pipeline leakage detection by means of acoustic emission technique using cross-correlation function | |
| CN114722856A (en) | Pipeline damage monitoring method and device | |
| Hao et al. | Research on gas pipeline multi-point leak signal processing and source locating using VMD, BSS and relative entropy | |
| Wu et al. | Novel signal denoising approach for acoustic leak detection | |
| Zhengjie et al. | Pressure vessel leakage detection method based on online acoustic emission signals | |
| Ye et al. | Multi-variable classification model for valve internal leakage based on acoustic emission time–frequency domain characteristics and random forest | |
| Gao et al. | Acoustic Emission‐Based Small Leak Detection of Propulsion System Pipeline of Sounding Rocket | |
| CN106482912A (en) | A kind of vacuum equipment Leak Detection and localization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |