CN109556797A - The pipeline leakage detection and location method with convolutional neural networks is decomposed based on spline local mean value - Google Patents
The pipeline leakage detection and location method with convolutional neural networks is decomposed based on spline local mean value Download PDFInfo
- Publication number
- CN109556797A CN109556797A CN201811375623.1A CN201811375623A CN109556797A CN 109556797 A CN109556797 A CN 109556797A CN 201811375623 A CN201811375623 A CN 201811375623A CN 109556797 A CN109556797 A CN 109556797A
- Authority
- CN
- China
- Prior art keywords
- signal
- leakage
- convolutional neural
- neural networks
- mean value
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Examining Or Testing Airtightness (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of pipeline leakage testing and localization method decomposed based on spline interpolation local mean value with convolutional neural networks, comprising: decomposes the suction wave noise reduction generated to leakage by using modified spline local mean value first;On this basis, picture signal being converted as the input of convolutional neural networks model using the negative pressure wave signal that leakage generates, the detection to different leak sizes is realized by the training to convolutional neural networks;Leakage time delay is determined finally by the generalized related function for calculating leakage point upstream and downstream pressure signal, so that it is determined that leak position.Compared with current local mean value noise-reduction method, the present invention not only higher computational efficiency, but also there is better Decomposition Accuracy, reduction pressure signal that can be more accurate;There is good accuracy and model generalization ability by the leakage detection method based on convolutional neural networks of proposition.
Description
Technical field
The present invention relates to a kind of pipeline leakage testing and localization methods.
Background technique
Pipeline has a very important effect as the infrastructure in city, factory, however pipeline is vulnerable to environment, outer
The influence of the factors such as power, corrosion leaks, and leakage not only causes the waste of resource but also causes the pollution of environment, and leaks letter
Number noise reduction be the key that leak detection.
There is experience Mode Decomposition (Empirical mode for noise-reduction method common in pipe detection and positioning at present
Decomposition, EMD) and local mean value decomposition (Local mean decomposition, LMD).Empirical mode decomposition is
A kind of adaptive signal Time-Frequency Analysis Method, signal decomposition have the characteristics that adaptive, and original signal is decomposed into multiple by it
The superposition of intrinsic mode functions (Intrinsic mode function, IMF).EMD does not need basic function, according only to signal itself
Scale feature carry out signal decomposition, can be used for the decomposition of any type signal, especially non-linear, non-stationary signal
There is apparent advantage in decomposition, thus widely applied in engineering.But EMD comes with some shortcomings, and such as modal overlap is crossed and wrapped
Network owes envelope, and especially decomposing accuracy to sophisticated signal can reduce.
Part mean decomposition method is a kind of novel non-linear, unstable state signal processing method, it is original by one
Several instantaneous frequencys of signal decomposition have the multiplicative function PFs (Product Functions, PFs) of physical significance.LMD and EMD
It is small compared to its operation the number of iterations, end effect in therefore decomposable process can be reduced, and can solve envelope and owed packet
Network problem, furthermore PF component ratio IMF component can save more frequencies and envelope information, therefore LMD ratio EMD is more suitable for handling
Non-stationary, nonlinear properties.But LMD comes with some shortcomings in practical applications.For example, LMD calculates local mean value function and packet
The accuracy of network estimation function is low and there are Boundary Distortions.Spline local mean value decomposition method can overcome accuracy low and boundary
Distortion, spline local mean value is decomposed replaces moving average process to calculate corresponding local mean value function using cubic spline interpolation
With envelope estimation function;Meanwhile calculating is overcome using original signal is properly extended based on adaptive Waveform Matching technology up and down
Boundary Distortion during envelope.Although SLMD has high accuracy and efficiency, can not accurately select containing information
PF component.Routine be according to frequency select PF component, but in pipeline noise and leakage signal frequency be it is unknown, and frequency with
Operating condition and environment and change.The improvement spline local mean value invented is decomposed according to cross correlation measure between PF component and reference signal
Determine whether the PF component is noise, completes progress signal filter and make an uproar.
Summary of the invention
The present invention will overcome the disadvantages mentioned above of the prior art, provide a kind of based on the decomposition of modified spline local mean value and volume
The pipeline leakage detection and location method of product neural network.
For more acurrate detection leak sizes, the present invention is using convolutional neural networks model to the tonogram in different leakage apertures
As classifying.First using the pressure image of different leak sizes as convolutional neural networks mode input, and to the network into
Row training, obtained convolutional neural networks model can be realized the leak detection to different leakage apertures.With other detection methods
Compared to convolutional neural networks with higher accuracy and generalization ability
The purpose of the present invention is: the negative pressure wave signal noise reduction difficult point generated for leakage, using spline interpolation local mean value
Former negative pressure wave signal is decomposed, spline local mean value, which is decomposed, has better accuracy and efficiency.In order to select reasonable PF component,
By cross correlation measure between reference signal and PF component, the cross-correlation factor is calculated.By setting critical correlation factor number, selection
PF component containing leakage information is reconstructed.Simultaneously for there are similar between de-noising signal different location and different size
Property, classified using convolutional neural networks to suction wave pressure signal image, realizes and different leak sizes are detected.
Technical solution of the invention are as follows: decompose first by using modified spline local mean value to leakage generation
Suction wave noise reduction;On this basis, picture signal is converted by the negative pressure wave signal that pipe leakage generates;It is rolled up secondly by building
Product neural network model is completed to detect different leak sizes;Finally by calculating leakage point upstream and downstream pressure signal broad sense phase
It closes function and determines leakage time delay, so that it is determined that leak position.Compared with current local mean value noise-reduction method, the present invention is not only more
High computational efficiency, but also there is better Decomposition Accuracy, reduction pressure signal that can be more accurate is realized more accurate
Positioning accuracy.In addition what is proposed has higher accuracy and general based on convolutional neural networks detection method and conventional method
Change ability.
The pipeline leakage detection and location method with convolutional neural networks is decomposed based on modified spline local mean value, specifically
Steps are as follows:
Step 1, leakage point upstream pressure signal is decomposed by the decomposition of spline local mean value, obtains multiplicative function
(Product Functions, PFs).
Wherein PF represents multiplicative function, rk(t) residual error is represented.
Step 2, leakage point downstream signal (reference signal) is introduced, calculates cross-correlation between each PF component and reference signal
Degree selects correlation factor to be greater than critical PF component always and carries out signal reconstruction.
Concrete foundation is as follows: coefficient Ri(τ) can are as follows:
According to coefficient Ri(τ) calculates related coefficient factor, definition are as follows:
The PF component of δ >=0.75 is selected to carry out signal reconstruction, reconstruction signalIt may be expressed as:
Step 3, db4 small echo is used to reconstruction signal, 7 layers of decompositions carry out wavelet decompositions, set 1,7 and 8 layer coefficients as
0, then reconstruct obtains reconstruction signal.
Step 4, image is converted by reconstruction signal, wherein all image line colors, size are identical, and remove and press
The unrelated any mark of power, pixel value set 227*227, and pressure change is full of whole image.
Step 5, No leakage, this 5 kinds leakage apertures 2mm, 3mm, 5mm and 10mm are amounted to 400*5=2000 group data to make
Step 1-4 processing generates 2000 total, the image of 5 kinds of different leak sizes.
Step 6, images above is inputted into training in convolutional neural networks, constructs convolutional neural networks detection model.
Step 7, it will need to detect signal, handle in the same way.After processing, convolutional neural networks are inputted, are completed
Different leak sizes detections.
Step 8, after convolutional neural networks detect leakage, with modified part mean decomposition method and Wavelet Denoising Method
To the processing of leakage point downstream pressure signal, wherein processed leakage point stream signal is reference signal.
Step 9, upstream and downstream pressure signal generalized related function is crossed in calculation processing, determines leakage time delay, and then realize leakage
Point location.
The invention has the advantages that not only higher computational efficiency, but also there is better Decomposition Accuracy, can more subject to
True reduction pressure signal;There is good accuracy and mould by the leakage detection method based on convolutional neural networks of proposition
Type generalization ability
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example and is used together to explain the present invention, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is experiment pipeline design drawing of the invention.
Fig. 2 is flow chart of the present invention.
Fig. 3 is to leak the noise reduction figure that bore is 3mm apart from upstream 1000m.
Fig. 4 is the downstream noise reduction result figure that leakage bore is 10mm at the 1000m of upstream.
Fig. 5 is the downstream noise reduction result figure that leakage bore is 5mm at the 1000m of upstream.
Fig. 6 is the downstream noise reduction result figure that leakage bore is 3mm at the 1000m of upstream.
Fig. 7 is the downstream noise reduction result figure that leakage bore is 2mm at the 1000m of upstream.
Fig. 8 is the structure chart of convolutional neural networks.
Fig. 9 a~9e be respectively away from the 1000m of upstream at 0,2,3,5, the training of 10mm and detection input scheme.
Fig. 9 f~9j be respectively away from the 500m of upstream at 0,2,3,5, the training of 10mm and detection input scheme.
Specific embodiment
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and examples, how to apply to the present invention whereby
Technological means solves technical problem, and the realization process for reaching technical effect can fully understand and implement accordingly.
The suction wave that the leakage of different location different size generates is collected, concrete operations condition is as follows: medium is water, pipe range L
=1510m, internal diameter 0.05m manage interior opposite wall roughness 0.025, upstream and downstream drop 120m, negative pressure velocity of wave propagation 1000m/s,
20 degrees Celsius of temperature.For the leakage for simulating different location and different pore size, stream ball is being installed at upstream 500m and 1010m
Valve, the aperture of ball valve are respectively 0mm, 2mm, 3mm, 5mm and 10mm.Upstream and downstream pressure tap is node1, node2, and pressure gauge is adopted
Sample frequency 100HZ, duration 40s open pipeline valve in 2s, and 20s opens leakage valve.
The above different location, big Small leak pressure acquire 400 groups respectively.It will first be adopted apart from upstream 1000m pressure signal
It is decomposed with SLMD, calculates the PF component and downstream signal (reference signal) cross correlation measure after each decomposition, select cross correlation measure
PF component greater than 0.75 carries out signal reconstruction.Db4 small echo is used to reconstruction signal, 7 layers of decomposition carry out wavelet decomposition, setting ground
1,7 and 8 layer coefficients are 0, and then reconstruct obtains reconstruction signal.Image is converted by reconstruction signal, wherein all image lines face
Color, size are identical, and pressure-independent any mark of erasing, and pixel value sets 227*227, and pressure change is full of whole figure
Picture.No leakage, this 5 kinds leakage apertures 2mm, 3mm, 5mm and 10mm are amounted into 400*5=2000 group data and make the above processing, it is raw
At 2000 total, the image of 5 kinds of different leak sizes.Images above is allocated as trained and test data set with the ratio of 8:2,
And test its accuracy.
In a practical situation, leak position has randomness, and convolutional neural networks model has good generalization ability.For inspection
The generalization ability for surveying training pattern, upstream pressure signal will be handled at the 500m of upstream with identical processing method, be used
The convolutional neural networks model of 1000m training is to images above classification and Detection.Its specific accuracy is as shown in table 1 below:
Table 1: the accurate table of leak detection
After convolutional neural networks detect that leakage occurs, downstream signal is handled with identical noise-reduction method, wherein joining
It is the stream signal after noise reduction than signal, other parameters are consistent with upstream noise reduction parameters.Leakage signal time delay Δ t by it is upper,
Broad sense cross-correlation function calculating in downstream acquires, leak position LxIt is calculated according to the following formula.
Lx=(L+v × Δ t)/2
LxLeakage point is apart from upstream position, L pipe range, v negative pressure velocity of wave propagation, Δ v time difference.Specific position error is random
It extracts 20 groups of data at 1000m to be calculated, position error, concrete outcome the following table 2 is obtained to the average value of accidentally absolute value of the difference
It is shown:
Table 2: leak detection errors table
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
Range should not be construed as being limited to the specific forms stated in the embodiments, and protection scope of the present invention is also and in art technology
Personnel conceive according to the present invention it is conceivable that equivalent technologies mean.
Claims (2)
1. a kind of pipeline leakage testing and positioning system based on spline interpolation and convolutional neural networks, comprising the following steps:
Step 1, upstream pressure signal is decomposed by the decomposition of spline local mean value, obtains multiplicative function PFs;
Step 2, leakage point downstream pressure wave signal, that is, reference signal is introduced, is calculated between each PF component and reference signal mutually
Guan Du selects the PF component containing leakage information to be reconstructed by setting critical correlation factor number;Spline local is decomposed
Improving is: introducing reference signal, determines whether the PF component contains using the cross correlation measure between reference signal and PF and let out
Information is leaked, and then realizes that filter is made an uproar;The specific steps of which are as follows:
(1) for non-linear, non-stationary signal downstream pressure xu(t), spline local mean value decomposition result may be expressed as:
Wherein, k represents the number of PF component, rk(t) residual error is represented;
(2) by each PF and rk(t) with downstream signal xd(t) make correlation analysis;
(3) the related coefficient factor is calculated:
(4) the suitable threshold values δ of PF pertinency factor is chosen0=0.75, as δ >=δ0, it is believed that the PF component is leakage signal;As δ < δ0,
Think that the PF component is not leakage signal;According to related coefficient selecting predictors PF, and to the PF signal reconstruction of selection;
(5) PF is selectedi signalReconstruct, reconstruction signalIt may be expressed as:
Step 3, further pass through wavelet decomposition to reconstruction signal and carry out noise reduction process;
Step 4, de-noising signal step 3 obtained is converted into picture signal, wherein the color of all images and lines, size phase
Together, and pressure-independent any mark is removed, and sets pixel value, pressure suction wave change procedure is full of whole image;
Step 5,5 kinds of leakage apertures of No leakage, 2mm, 3mm, 5mm, 10mm are amounted into 400*5=2000 group data and makees step 1-
4 processing, generate and amount to 2000 images;
Step 6, images above is inputted and carries out model training and verifying in convolutional neural networks, building convolutional neural networks detection
Model;
Step 7, will the obtained convolutional neural networks model of training, it can be achieved that different leak sizes detection;
Step 8, leakage point downstream pressure signal is handled with modified part mean decomposition method and Wavelet Denoising Method, and with
Leakage point stream signal is reference signal;
Step 9, the leakage point upstream and downstream pressure signal generalized related function after reconstruct is calculated, determines leakage time delay, and then realize
Leak point positioning.
2. according to claim 1 based on convolutional neural networks to pipeline leakage testing, which is characterized in that the step 6 and 7
In, convolutional neural networks are introduced into the detection to pipe leakage;Using convolutional neural networks in the excellent of processing 2-D image data
Gesture realizes the training of one leakage point of training, the detection of multiple place leak sizes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811375623.1A CN109556797B (en) | 2018-11-19 | 2018-11-19 | Pipeline leakage detection and positioning method based on spline local mean decomposition and convolutional neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811375623.1A CN109556797B (en) | 2018-11-19 | 2018-11-19 | Pipeline leakage detection and positioning method based on spline local mean decomposition and convolutional neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109556797A true CN109556797A (en) | 2019-04-02 |
CN109556797B CN109556797B (en) | 2020-10-09 |
Family
ID=65866766
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811375623.1A Active CN109556797B (en) | 2018-11-19 | 2018-11-19 | Pipeline leakage detection and positioning method based on spline local mean decomposition and convolutional neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109556797B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110440148A (en) * | 2019-07-15 | 2019-11-12 | 清华大学 | A kind of leakage loss acoustical signal classifying identification method, apparatus and system |
CN114486128A (en) * | 2022-02-18 | 2022-05-13 | 汉威科技集团股份有限公司 | Gas leakage detection device and method integrating ultrasonic wave and passive infrared imaging |
CN115824519A (en) * | 2023-02-14 | 2023-03-21 | 中国海洋大学 | Valve leakage fault comprehensive diagnosis method based on multi-sensor information fusion |
CN115993268A (en) * | 2023-03-22 | 2023-04-21 | 福建天甫电子材料有限公司 | Sampling system and method for anhydrous hydrogen fluoride |
US20230332976A1 (en) * | 2022-04-14 | 2023-10-19 | Professional Flexible Technologies Inc. | Systems and methods for improved pipeline leak detection |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103216731A (en) * | 2013-05-08 | 2013-07-24 | 西安理工大学 | Pipeline leakage judgment method and system thereof |
CN104390781A (en) * | 2014-11-26 | 2015-03-04 | 中国矿业大学 | Gear fault diagnosis method based on LMD and BP neural network |
CN105424057A (en) * | 2015-10-30 | 2016-03-23 | 东南大学 | Fiber-optic gyroscope vibration signal analysis method based on improved LMD |
US20170082518A1 (en) * | 2012-11-16 | 2017-03-23 | International Business Machines Corporation | Method and apparatus of estimating wave velocity of negative pressure wave in a fluid transportation pipeline |
US20170219454A1 (en) * | 2016-01-28 | 2017-08-03 | International Business Machines Corporation | Leak identification in a mass transport network |
CN107228282A (en) * | 2017-07-06 | 2017-10-03 | 东北石油大学 | A kind of gas pipeline leakage localization method and device |
CN108052989A (en) * | 2018-02-07 | 2018-05-18 | 深圳市唯特视科技有限公司 | A kind of image classification method based on Spline convolution neutral net |
CN108444653A (en) * | 2018-03-09 | 2018-08-24 | 北京理工大学 | A kind of face formation ultrasonic gas leak point positioning detection device and method |
CN108488638A (en) * | 2018-03-28 | 2018-09-04 | 东北大学 | Line leakage system and method based on sound wave suction wave hybrid monitoring |
CN108664901A (en) * | 2018-04-20 | 2018-10-16 | 三峡大学 | Based on the micro-capacitance sensor power quality disturbance signal detection method for improving LMD |
-
2018
- 2018-11-19 CN CN201811375623.1A patent/CN109556797B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170082518A1 (en) * | 2012-11-16 | 2017-03-23 | International Business Machines Corporation | Method and apparatus of estimating wave velocity of negative pressure wave in a fluid transportation pipeline |
CN103216731A (en) * | 2013-05-08 | 2013-07-24 | 西安理工大学 | Pipeline leakage judgment method and system thereof |
CN104390781A (en) * | 2014-11-26 | 2015-03-04 | 中国矿业大学 | Gear fault diagnosis method based on LMD and BP neural network |
CN105424057A (en) * | 2015-10-30 | 2016-03-23 | 东南大学 | Fiber-optic gyroscope vibration signal analysis method based on improved LMD |
US20170219454A1 (en) * | 2016-01-28 | 2017-08-03 | International Business Machines Corporation | Leak identification in a mass transport network |
CN107228282A (en) * | 2017-07-06 | 2017-10-03 | 东北石油大学 | A kind of gas pipeline leakage localization method and device |
CN108052989A (en) * | 2018-02-07 | 2018-05-18 | 深圳市唯特视科技有限公司 | A kind of image classification method based on Spline convolution neutral net |
CN108444653A (en) * | 2018-03-09 | 2018-08-24 | 北京理工大学 | A kind of face formation ultrasonic gas leak point positioning detection device and method |
CN108488638A (en) * | 2018-03-28 | 2018-09-04 | 东北大学 | Line leakage system and method based on sound wave suction wave hybrid monitoring |
CN108664901A (en) * | 2018-04-20 | 2018-10-16 | 三峡大学 | Based on the micro-capacitance sensor power quality disturbance signal detection method for improving LMD |
Non-Patent Citations (1)
Title |
---|
王少峰 等: "立体管网微泄漏实时监测系统研究概述", 《河北科技大学学报》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110440148A (en) * | 2019-07-15 | 2019-11-12 | 清华大学 | A kind of leakage loss acoustical signal classifying identification method, apparatus and system |
CN114486128A (en) * | 2022-02-18 | 2022-05-13 | 汉威科技集团股份有限公司 | Gas leakage detection device and method integrating ultrasonic wave and passive infrared imaging |
CN114486128B (en) * | 2022-02-18 | 2024-05-03 | 汉威科技集团股份有限公司 | Gas leakage detection device and method integrating ultrasonic wave and passive infrared imaging |
US20230332976A1 (en) * | 2022-04-14 | 2023-10-19 | Professional Flexible Technologies Inc. | Systems and methods for improved pipeline leak detection |
CN115824519A (en) * | 2023-02-14 | 2023-03-21 | 中国海洋大学 | Valve leakage fault comprehensive diagnosis method based on multi-sensor information fusion |
CN115824519B (en) * | 2023-02-14 | 2023-05-12 | 中国海洋大学 | Comprehensive diagnosis method for valve leakage faults based on multi-sensor information fusion |
CN115993268A (en) * | 2023-03-22 | 2023-04-21 | 福建天甫电子材料有限公司 | Sampling system and method for anhydrous hydrogen fluoride |
Also Published As
Publication number | Publication date |
---|---|
CN109556797B (en) | 2020-10-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109556797A (en) | The pipeline leakage detection and location method with convolutional neural networks is decomposed based on spline local mean value | |
Zhou et al. | Leak detection and location based on ISLMD and CNN in a pipeline | |
Wang et al. | Pipeline leak detection using the matched-field processing method | |
CN110185939B (en) | Gas pipeline leakage identification method based on convolutional neural network | |
CN106950276B (en) | Pipeline defect depth inversion method based on convolutional neural network | |
Yu et al. | Dual-tree complex wavelet transform and SVD based acoustic noise reduction and its application in leak detection for natural gas pipeline | |
CN110345392B (en) | Positioning method and device for oil pipeline leakage point | |
CN112013286B (en) | Method and device for positioning pipeline leakage point, storage medium and terminal | |
CN103488906A (en) | Valve inner leakage defect type recognition and inner leakage rate calculation method | |
Feng et al. | Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology | |
CN111947045A (en) | GVMD parameter optimization and singular value decomposition-based fluid pipeline leakage positioning method | |
CN108954020A (en) | A kind of pipeline location method | |
CN111503527B (en) | Fluid pipeline leakage positioning method based on self-adaptive multivariate variational modal decomposition | |
CN103176946A (en) | Sparse decomposition and denoising method facing block sparse signals | |
CN105674065A (en) | Acoustic emission pipeline leakage point positioning method based on variable mode decomposition | |
CN104456089A (en) | Fluid pipeline multi-leakage-point locating method | |
CN113343402B (en) | Pipeline corrosion grade evaluation method based on multilayer convolution sparse coding | |
CN113111923A (en) | Water supply network leakage detection and positioning method based on one-dimensional migration learning convolutional neural network integrated model | |
Jiao et al. | Sparse representation of acoustic emission signals and its application in pipeline leak location | |
Zhengjie et al. | Pressure vessel leakage detection method based on online acoustic emission signals | |
CN108195932B (en) | Ultrasonic guided wave quantitative assessment method for aircraft pipeline damage | |
Jiao et al. | Lifting wavelet denoising algorithm for acoustic emission signal | |
CN109340587B (en) | Empirical mode decomposition-based fluid pipeline leakage acoustic emission coherent positioning method | |
Rashid et al. | Performance analysis of wavelet transforms for leakage detection in long range pipeline networks | |
An et al. | Constant false alarm rate detection of pipeline leakage based on acoustic sensors |
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 |