CN105927861B - Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm - Google Patents
Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm Download PDFInfo
- Publication number
- CN105927861B CN105927861B CN201610246962.4A CN201610246962A CN105927861B CN 105927861 B CN105927861 B CN 105927861B CN 201610246962 A CN201610246962 A CN 201610246962A CN 105927861 B CN105927861 B CN 105927861B
- Authority
- CN
- China
- Prior art keywords
- signal
- leakage
- blind source
- source separation
- 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.)
- Active
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 leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm that the invention discloses a kind of, comprising the following steps: sensor is set on tested pipeline, signal acquisition is carried out to leakage point by sensor, obtains leakage sound collecting signal;Leakage sound collecting signal is pre-processed using wavelet transformation, observation signal is obtained, and handled using blind source separation algorithm observation signal, obtains echo signal;Echo signal in step 2 is evaluated, and observation signal composition is carried out preferred.The beneficial effects of the present invention are: provided by the invention evaluate target processing signal by leakage instance sample point deviation and amplitude two evaluation parameters of loss based on the leakage acoustic characteristic extracting method of Wavelet Transform Fusion blind source separation algorithm, the leakage moment can be accurately positioned in this method, while obvious to the compensating action of the leakage amplitude of small-signal.
Description
Technical field
The present invention relates to pipeline inspection technology field, especially a kind of letting out based on Wavelet Transform Fusion blind source separation algorithm
Leak acoustic characteristic extracting method.
Background technique
There are many kinds for the current leakage monitoring method that can be applied to oil-gas pipeline, wherein sonic method and traditional quality
Balancing method, negative pressure wave method, transient model method etc., which are compared, to be had many advantages, such as: high sensitivity, positioning accuracy are high, rate of false alarm is low, inspection
It is short, adaptable to survey the time;What is measured is the faint dynamic pressure variable quantity in pipeline fluid, absolute with pipeline performance pressure
It is worth unrelated;Response frequency is wider, and detection range is wider etc..
Acoustic signals are generated when gas pipeline leaks, as the increase leakage signal of propagation distance generates decaying, wave
Shape feature is covered by noise, and to extract effective leakage feature, domestic and foreign scholars have carried out a large amount of research, tied according to investigation
Fruit, the patent that Current Domestic is related to gas pipeline leakage acoustic characteristic extracting method outside mainly have:
United States Patent (USP) US6389881 discloses a kind of technology that pipeline leakage testing is carried out using sound wave technology, the technology
Using dynamic pressure in sensor collection tube, signal is filtered using pattern match filtering technique, excludes noise, drop
Low interference, improves positioning accuracy;
Chinese patent 200710177617.0 discloses a kind of leakage detection method merged based on pressure and information of acoustic wave,
This method acquires pipeline upstream and downstream pressure and acoustic signals (in 0.2-20Hz) respectively, by data filtering, feature-based fusion and
The processing of three levels of decision level fusion obtains final detection result, and using based on fusions such as correlation analysis, wavelet analysis
Localization method carries out leakage positioning, improves the accuracy and positioning accuracy of leak detection.
Chinese patent 201510020155.6 discloses a kind of gas oil pipe leakage localization method based on magnitudes of acoustic waves, should
Method carries out leakage detection and location using low-frequency range magnitudes of acoustic waves is obtained after wavelet analysis is handled, and proposes one kind not
Consider the velocity of sound and the leakage locating method of time difference.
Chinese patent CN104614069A discloses a kind of electric power based on joint approximate diagonalization blind source separation algorithm and sets
Standby failure sound detection method, step includes: using microphone array;Using based on joint approximate diagonalization blind source separation algorithm needle
Each individual sources signal is separated to the voice signal using microphone array acquisition;Extract the Mel frequency of individual sources signal
Cepstrum coefficient MFCC identifies voice signal as sound characteristic parameter, by pattern matching algorithm, by sound pattern to be tested with
After all reference sample templates are matched, the smallest reference sample template of matching distance is exactly power equipment work sound identification
Result.
Existing patent is the application of wavelet transformation or blind source separation algorithm single treatment method, to two methods
Integration technology does not describe, specific manifestation are as follows:
(1) wavelet transformation can extract the signal characteristic of low-frequency range, be using signal processing method the most universal, but it is same
When wavelet transformation in signal extraction, there is also more apparent defects, in practical applications, the acquisition of low-band signal feature
It needs to carry out deep layer decomposition to original signal, be easy to appear in the positioning at leakage moment and the acquisition of leakage amplitude larger inclined
Difference be easy to cause the calculating error of time difference, so that position error is larger;Leakage amplitude loss be easy to cause the mistake of leakage waveform
Very, it be easy to cause failing to judge and judging by accident for leakage.
(2) to solve this problem, signal is handled using blind source separation algorithm, it has been investigated that blind source separating energy
It is enough that the leakage moment is accurately positioned, and do not lost not only in terms of leaking amplitude, compensated instead, especially signal more
Compensation becomes apparent when faint, but in use, blind source separating equally exists more apparent defect: the mesh that blind source separating obtains
Mark signal sequence, type not can determine that.
Summary of the invention
It is a kind of based on the blind source of Wavelet Transform Fusion point the purpose of the present invention is to overcome above-mentioned the deficiencies in the prior art, providing
Leakage acoustic characteristic extracting method from algorithm.
To achieve the above object, the present invention adopts the following technical solutions:
Based on the leakage acoustic characteristic extracting method of wavelet character approximate signal fusion blind source separation algorithm, including following step
It is rapid:
Step 1: being arranged sensor on tested pipeline, carries out signal acquisition to leakage point by sensor, obtains leakage
Sound collecting signal;
Step 2: leakage sound collecting signal is pre-processed using wavelet transformation, multiple detail signals is obtained, will let out
Sound collecting signal and multiple detail signals are leaked as observation signal, and to observation signal using at blind source separation algorithm
Reason obtains echo signal;
Step 3 evaluates the echo signal in step 2, and carries out to observation signal composition preferred.
Preferably, in the step 1, sonic sensor uses dynamic pressure transducer.
Preferably, in the step 2, for sym8, Decomposition order acquires the wavelet basis that wavelet transformation uses according to sensor
Leakage sound collecting signal in the signal kinds that contain determine that the signal kinds include leakage acoustic signals, ambient noise
And hydrodynamic noise.
Preferably, the ambient noise includes the operating of power-equipment, the noise and hardware device of pipeline external environment,
The noise that circuit generates;The hydrodynamic noise includes the turbulence noise that fluid flowing generates.
Preferably, in the step 2, specific step is as follows for observation signal acquisition methods:
Step S201: using leakage sound collecting signal as original signal, determining that wavelet decomposition number of plies N, N are more than or equal to 2,
Using original signal as signal to be decomposed, wavelet decomposition is carried out, decomposes and obtains first layer detail signal and first layer respectively for the first time
Approximate signal;
Step S202: it using first layer approximate signal as signal to be decomposed, treats decomposed signal and carries out wavelet decomposition, respectively
Obtain the corresponding second layer detail signal of signal to be decomposed and second layer approximate signal;
Step S203: using N-1 layers of approximate signal as signal to be decomposed, repeating step S202, until reaching point
Number of plies N is solved, N-1 layers of approximate signal wavelet decomposition correspond to n-th layer detail signal and n-th layer approximate signal;
Step S204: first layer is chosen to the corresponding each layer detail signal of n-th layer and n-th layer approximate signal as observation
Signal.
It is further preferred that the method for confirming Decomposition order according to signal kinds are as follows: Decomposition order is equal to sensor
The signal kinds contained in the leakage acoustic signals of acquisition subtract 1.
Preferably, in the step 2, in such a way that blind source separation algorithm carries out the number that processing obtains echo signal
There are two types of: first is that the sum of echo signal is equal to the sum of observation signal, i.e., when observation signal has m, then echo signal also has m
It is a;Second is that directly defining echo signal number is one, i.e., when observation signal has m, echo signal has and only one.
Preferably, in the step 3, using leakage instance sample point deviation and amplitude loss as evaluation parameter.
The leakage instance sample point deviation refers to the leakage moment of leakage the instance sample point and original signal of echo signal
The difference of sampled point.The smaller representative leakage moment positioning of leakage instance sample point deviation is more acurrate.
The amplitude loss refers to the difference and original signal of the leakage amplitude of echo signal and the leakage amplitude of original signal
Leak the ratio between the absolute value of amplitude.Amplitude loss is negative value, and the value absolute value is bigger, and it is more significant to represent amplitude compensation.
The beneficial effects of the present invention are:
1. the leakage acoustic characteristic extracting method provided by the invention based on Wavelet Transform Fusion blind source separation algorithm passes through
Leakage instance sample point deviation and amplitude are lost two evaluation parameters and are evaluated target processing signal, and this method can be to letting out
The leakage moment is accurately positioned, while obvious to the compensating action of the leakage amplitude of small-signal;
2. the present invention solves at this stage, wavelet transformation is larger in the positioning of leakage moment and leakage amplitude offset error, blind
Source separates echo signal sequence, the unascertainable problem of type, improves the applicability of sonic method leakage detection and localization technology;
3. the method for the present invention is simple, easy to operate, in extraction oil-gas pipeline sonic method leakage detection and localization method
Leak acoustic characteristic strong applicability.
Detailed description of the invention
Fig. 1 is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm extracts
The schematic diagram of method;
Fig. 2 is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm extracts
Method implementation process diagram;
Fig. 3 is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm extracts
Original signal schematic diagram before method processing;
Fig. 4 a is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm mentions
The first aim signal schematic representation obtained after taking method to handle;
Fig. 4 b is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm mentions
The second target signal schematic representation obtained after taking method to handle;
Fig. 4 c is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm mentions
The third echo signal schematic diagram obtained after taking method to handle;
Fig. 5 is that the leakage acoustic characteristic provided in an embodiment of the present invention based on Wavelet Transform Fusion blind source separation algorithm extracts
The echo signal schematic diagram obtained after method processing.
Specific embodiment
Present invention will be further explained below with reference to the attached drawings and examples.
As shown in Figure 1, the flow chart of the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm
With reference to Fig. 1, the technical solution that the present invention is provided according to summary of the invention carries out experimental verification to the present invention using following experiment parameters:
Experiment parameter is as follows: original signal is that sensor when 0.6mm leaks aperture under 2MPa apart from leakage point 109m is adopted
The signal of collection, with reference to Fig. 3, Decomposition order N is 2, and sample frequency f is 3000Hz, wavelet transformation analytic function be sym8 or
db4。
Embodiment 1: in the embodiment, using blind source separation algorithm carry out processing obtain echo signal number by the way of
It is equal to observation signal for the sum of echo signal.Original signal is A0, the first layer observation signal that wavelet transformation obtains after decomposing
For D1, second layer observation signal is D2 and A2, that is, is used for the observation signal of blind source separation algorithm in step 2 as A2, D2, D1, then
Are carried out by blind source separating, obtains echo signal by A2, D2, D1 respectively.
As shown in Fig. 3, Fig. 4 a, Fig. 4 b, Fig. 4 c, Fig. 4 indicates the three targets letter obtained using method provided by the invention
Number.
Embodiment 2: in the embodiment, use blind source separation algorithm carry out processing obtain echo signal number mode for
Definition echo signal has and only one.Fig. 5 indicates the echo signal obtained using method provided by the invention.
With reference to Fig. 4 a, Fig. 4 b and Fig. 4 c, according to the experiment attached drawing of embodiment 1 can be seen that original signal amplitude be-
5.06159kPa, it is 46441 that the original signal leakage moment, which corresponds to sampled point,;Acoustic signals amplitude is leaked it can be seen from Fig. 4 a
For -9.53160kPa, it is 46441 that the leakage acoustic signals leakage moment, which corresponds to sampled point,.In 3 signals obtained by invention with
The close echo signal of original signal is leakage acoustic signals, remaining 2 respectively ambient noise and hydrodynamic noises, and leakage sound
The sequence of wave signal, ambient noise and hydrodynamic noise is followed successively by 1,2,3, so, the present invention, which will leak in acoustic signals, to be contained
Signal kinds are classified, and are confirmed to the sequence of echo signal.The method of determination of the echo signal number is excellent
Mode is selected, because the present invention leaks acoustic signals in view of not only to obtain from leakage sound collecting signal in experimentation,
Also the ambient noise and hydrodynamic noise obtained from leakage sound collecting signal is conducted further research, for this purpose, it is preferred that
Above-mentioned echo signal number validation testing.
With reference to Fig. 5, can be seen that leakage acoustic signals amplitude according to the experiment attached drawing of embodiment 1 is -9.53160kPa,
Leaking acoustic signals leakage moment corresponding sampled point is 46441.It can be seen that method provided by the invention according to above-mentioned data
The leakage instance sample point of obtained echo signal and the amplitude deviation of original signal are 0, and the echo signal that the present invention obtains
Leakage magnitudes of acoustic waves be greater than original signal amplitude, therefore method provided by the invention to leakage the moment positioning it is more accurate,
And amplitude loss is -88.31%, i.e. leakage amplitude compensation effect is obvious.If the present invention is only from leakage sound collecting signal
Leakage acoustic signals are obtained, the echo signal number method of determination of the use of embodiment 2 can be used, echo signal has been defined as and only
There is one, so not having to consider the problems of that the sequence of echo signal, type are distinguished.
In conclusion method provided by the invention loses two evaluation parameters by leakage instance sample point deviation and amplitude
Echo signal is evaluated, the leakage moment of leakage sound wave can be accurately positioned in this method, while to small-signal
Leakage amplitude compensating action it is obvious, therefore, effectively reduce at this stage Wavelet transformation in leakage moment error is biggish asks
Topic.
Therefore, echo signal can effectively be classified after blind source separating of the present invention, and then improves sonic method and lets out
The practicability of leak detection and positioning.
Above-mentioned, although the foregoing specific embodiments of the present invention is described with reference to the accompanying drawings, not protects model to the present invention
The limitation enclosed, those skilled in the art should understand that, based on the technical solutions of the present invention, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within protection scope of the present invention.
Claims (8)
1. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm, characterized in that including following step
It is rapid:
Step 1: being arranged sensor on tested pipeline, carries out signal acquisition to leakage point by sensor, obtains leakage sound wave
Acquire signal;
Step 2: leakage sound collecting signal is pre-processed using wavelet transformation, multiple detail signals is obtained, sound will be leaked
Wave acquires signal and multiple detail signals as observation signal, and is handled using blind source separation algorithm observation signal, obtains
Take echo signal;
In the step 2, the wavelet basis that wavelet transformation uses for sym8, adopt by the leakage sound wave that Decomposition order is acquired by sensor
The signal kinds contained in collection signal determine that the signal kinds include leakage acoustic signals, ambient noise and hydrodynamic noise;
In the step 2, specific step is as follows for observation signal acquisition methods:
Step S201: using leakage sound collecting signal as original signal, determining that wavelet decomposition number of plies N, N are more than or equal to 2, will
Original signal carries out wavelet decomposition, decomposition obtains first layer detail signal respectively for the first time and first layer is close as signal to be decomposed
Likelihood signal;
Step S202: it using first layer approximate signal as signal to be decomposed, treats decomposed signal and carries out wavelet decomposition, obtain respectively
The corresponding second layer detail signal of signal to be decomposed and second layer approximate signal;
Step S203: using N-1 layers of approximate signal as signal to be decomposed, repeating step S202, until reaching decomposition layer
Number N, N-1 layers of approximate signal wavelet decomposition correspond to n-th layer detail signal and n-th layer approximate signal;
Step S204: first layer is chosen to the corresponding each layer detail signal of n-th layer and n-th layer approximate signal as observation letter
Number;
Step 3 evaluates the echo signal in step 2, and carries out to observation signal composition preferred.
2. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, in the step 1, sonic sensor uses dynamic pressure transducer.
3. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, the ambient noise includes the operating of power-equipment, and noise and hardware device, the circuit of pipeline external environment generate
Noise;The hydrodynamic noise includes the turbulence noise that fluid flowing generates.
4. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, the method that Decomposition order is confirmed according to signal kinds are as follows: Decomposition order is equal to leakage acoustic signals type and subtracts 1.
5. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, the echo signal quantity definition mode is that the sum of echo signal is equal to the sum of observation signal.
6. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, the echo signal quantity definition mode is that echo signal number is one.
7. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as described in claim 1,
It is characterized in, in the step 3, using leakage instance sample point deviation and amplitude loss as evaluation parameter.
8. the leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm as claimed in claim 7,
It is characterized in, the leakage instance sample point deviation refers to that the leakage instance sample point of echo signal and the leakage moment of original signal are adopted
The difference of sampling point;The amplitude loss refers to the difference and original signal of the leakage amplitude of echo signal and the leakage amplitude of original signal
Leak the ratio between the absolute value of amplitude.
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 CN105927861A (en) | 2016-09-07 |
CN105927861B true 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) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107907279B (en) * | 2017-11-20 | 2020-09-22 | 中国石油大学(华东) | Multi-phase flow pipeline leakage sound wave signal analysis method based on wavelet coefficient amplitude |
CN110778922B (en) * | 2019-10-26 | 2021-06-08 | 山东佑安消防***有限公司 | Pipe network leakage point searching method and system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6898612B1 (en) * | 1998-11-12 | 2005-05-24 | Sarnoff Corporation | Method and system for on-line blind source separation |
JP4354387B2 (en) * | 2004-11-18 | 2009-10-28 | 独立行政法人理化学研究所 | Signal separation system, signal separation method, and signal separation program |
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 |
-
2016
- 2016-04-20 CN CN201610246962.4A patent/CN105927861B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN105927861A (en) | 2016-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021012986A1 (en) | Pipeline multi-point leakage positioning method based on improved vmd | |
Xu et al. | Pipeline leak detection based on variational mode decomposition and support vector machine using an interior spherical detector | |
CN105909979B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
CN107435817B (en) | A kind of pressure pipeline two o'clock leak detection accurate positioning method | |
Song et al. | Gas leak detection in galvanised steel pipe with internal flow noise using convolutional neural network | |
CN110762398A (en) | Oil and gas pipeline leakage detection method and system based on excitation response | |
CN105928666B (en) | Leakage acoustic characteristic extracting method based on Hilbert-Huang transform and blind source separating | |
CN107328528A (en) | A kind of ultrasonic wave air tightness detection system and method based on multisensor | |
CN103742794A (en) | Simulating device and simulating method for pipeline leakage acoustic emission signals | |
CN109063762A (en) | A kind of line clogging fault recognition method based on DT-CWT and S4VM | |
CN105927861B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
CN116304638A (en) | Pipeline leakage aperture identification method based on improved LCD | |
CN106770668B (en) | Method for detecting quality of single-hole foundation pile by acoustic transmission method | |
Bakhti et al. | Experimental validation of hybrid EMD-correlation acoustic digital leaks detector in water distribution network system | |
CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
CN210920975U (en) | Deep sea oil gas field oil gas production leakage point positioning and alarming experiment system | |
CN112198232A (en) | Drainage pipeline working condition detection and identification method | |
Chi et al. | Novel leakage detection method by improved adaptive filtering and pattern recognition based on acoustic waves | |
Hao et al. | Research on gas pipeline multi-point leak signal processing and source locating using VMD, BSS and relative entropy | |
CN106650951A (en) | Multichannel measurement data automatic screening method based on time domain global similarity | |
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 | |
CN113484417B (en) | Pipeline corrosion detection method based on wavelet transformation | |
CN115854269A (en) | Leakage hole jet flow noise identification method and device, electronic equipment and storage medium | |
CN115345193A (en) | Multi-channel ultrasonic gas leakage positioning method based on decision tree and neural network |
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 |