CN109063762A - A kind of line clogging fault recognition method based on DT-CWT and S4VM - Google Patents
A kind of line clogging fault recognition method based on DT-CWT and S4VM Download PDFInfo
- Publication number
- CN109063762A CN109063762A CN201810812279.1A CN201810812279A CN109063762A CN 109063762 A CN109063762 A CN 109063762A CN 201810812279 A CN201810812279 A CN 201810812279A CN 109063762 A CN109063762 A CN 109063762A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- frequency range
- component
- sound
- s4vm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 15
- 230000000903 blocking effect Effects 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 6
- 230000006854 communication Effects 0.000 claims description 4
- 230000007547 defect Effects 0.000 claims description 3
- 230000006378 damage Effects 0.000 abstract description 3
- 238000009434 installation Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 abstract 1
- 238000000354 decomposition reaction Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 239000000470 constituent Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of line clogging fault recognition methods based on DT-CWT and S4VM, belong to fault detection technique field, the present invention detects the sound pressure signal data that pipeline obtains pipeline first, then it is carried out using acoustic signal data of the dual-tree complex wavelet transform algorithm to acquisition decomposed and reconstituted, obtain the component of each frequency range, effective frequency range component is selected from the component of each frequency range, and sound pressure level transformation is carried out to effective frequency range component, then the pulse factor of effective frequency range component and average sound energy density after converting are extracted, the pulse factor and average sound energy density as the feature vector for being used to classify and will be trained to obtain training aids model in feature vector input S4VM classifier, the different degrees of blocking of pipeline is identified using training aids model and excludes the interference of three-way piece, this method overcomes existing pipeline inspection It surveys signal and is difficult to the problem of being effectively treated, it is small to pipe damage, it is at low cost, it is easy for installation, it is practical.
Description
Technical field
The present invention relates to a kind of line clogging fault recognition methods based on DT-CWT and S4VM, belong to fault detection technique
Field.
Background technique
About 710,000 kilometers of China's water supply line total length in 2015, and it is annual in rising trend, but China and developed country
It compares, the pipeline leak rate height that is averaged wherein the greasy filth, rust deposite caused by blocking in pipe can solidify causes former caliber to become smaller;Mud
It can be precipitated in pipeline, be easy to produce the flammable explosive gas such as hydrogen sulfide, cause environmental pollution and easily cause booster.If too late
When remove foreign matter in pipeline, will cause line clogging, gently then endanger water safety, it is heavy then cause to leak, booster, to resource,
Environment and China's economy bring about great losses and endanger.So timely detect line clogging, control line clogging quantitative change is generated
Harm is dangerous, and to saving, water resource, guarantee urban water, the promotion economic sustainable and healthy development in China are significant.
The detection in buried drain pipe road at present is concentrated mainly on subsequent detection, exists in method and excavates damage, relies on artificial
Operation, the main problems such as equipment valuableness.Detection method based on acoustics has the characteristics that inexpensive, easy for installation.Guided waves
Belong to one of acoustics field of non destructive testing fresh approach, can be used to line clogging and leakage detection and localization, this method
It is propagated using mechanical stress wave along pipeline extending direction, propagation distance is long and decays small, and sometimes single position detection can
Up to hundreds of meters, it is only necessary to handle the pipeline external surface of sensor mounting location, the pipe for being difficult to closely detect can be detected
Road position.When pipeline blocks, conduit cross-sectional area is caused to become smaller, when medium changes, acoustic characteristic can be sent out guided wave
Raw corresponding variation, guided wave also will receive the influence of pipeline conventional components such as three-way piece in communication process.
Summary of the invention
The purpose of the present invention is to provide a kind of line clogging fault recognition method based on DT-CWT and S4VM, DT-CWT
As dual-tree complex wavelet transform, S4VM are safe semisupervised support vector machines, and the present invention overcomes existing pipe detections
Signal is difficult to the problem of being effectively treated, and present invention guided wave obtains the echo in pipeline to line clogging and leak detection, obtains
Echo-signal be non-linear, non-stationary signal, from blocking acoustical signal mechanism, analysis blocking acoustical signal feature and is utilized
The feature extracting method that dual-tree complex wavelet transform and sound pressure level combine is to Signal Pretreatment, according to the propagation of sound wave in the duct
Mechanism, extracts sound energy density and the pulse factor is characterized, using safe semisupervised support vector machines, that is, S4VM to different blockings
Situation and three-way piece have carried out more classification annotations.
The technical scheme is that the sound pressure signal data of detection pipeline acquisition pipeline first, then multiple using double trees
Wavelet Transformation Algorithm is decomposed and reconstituted to the acoustic signal data progress of acquisition, the component of each frequency range is obtained, from the component of each frequency range
The middle effective frequency range component of selection, and sound pressure level transformation is carried out to effective frequency range component, then extract effective frequency range component after transformation
The pulse factor and average sound energy density, using the pulse factor and average sound energy density as being used for the feature vector of classification simultaneously
Feature vector is inputted in S4VM classifier and is trained to obtain training aids model, identifies pipeline difference journey using training aids model
The blocking of degree and the interference for excluding three-way piece.
The specific steps of the present invention are as follows:
(1) acoustic instrument is placed in pipeline first, pipeline is externally provided with data signal sampling and processing equipment, the tail of pipeline
Hold semiclosed, sound encounters pipeline tail end and reflection, refraction, scattering occurs in the communication process of pipeline, generates and a large amount of carries pipe
Road fault of construction information reflection echo, the echo of data signal sampling and processing equipment acquisition reflection obtain the acoustic pressure letter of pipeline
Number;
(2) data signal sampling and processing equipment handles signal data, using dual-tree complex wavelet transform algorithm pair
Sound pressure signal data are decomposed, are reconstructed, and the component of each frequency range is obtained, and the component of each frequency range is indicated with time domain figure respectively, are seen
Time-domain diagram is examined, the frequency range component that the big time-domain diagram of signals and associated noises indicates is removed, using the component of other frequency ranges as effective frequency range
Component, and sound pressure level transformation is carried out to effective frequency range component, obtain the sound pressure level signal of each effective frequency range component;
(3) the pulse factor of the sound pressure level signal of each effective frequency range component of extraction step (2) and average sound energy density,
In each effective frequency range component average acoustic energy metric density formulas Extraction it is as follows:
Wherein,Indicate average acoustic energy metric density, peIndicate effective acoustic pressure, andpaIndicate original acoustic pressure, ρ0
Indicate density, c0Indicate sound spread speed in the duct,For the time average of sound energy density, V0For pipeline body
Product;
(4) the pulse factor and average sound energy density extracted step (3) be used as classification feature vector and by
Classification based training, which is carried out, in feature vector input S4VM classifier obtains the model of each classification results;
(5) step (1)~(3) are repeated when testing other pipeline, obtain the pulse factor for testing pipeline data and average sound
Energy density, then calculates the Euclidean distance between test data and the model of step (4) each classification results, and by the Europe of calculating
Formula distance is test result of the representative classification results of minimum value as the test pipeline, completes the failure to test pipeline
Identification.
The model of four kinds of classification results is obtained in the step (4), respectively normally, slight to block, middle severe blocking, three
Parts interference.
Acoustic instrument includes more than one hydrophone and a loudspeaker in the step (1), and data acquire and signal
Processing equipment includes PC machine, sound card, filter, preamplifier and power amplifier;More than one hydrophone respectively with filter
The connection of wave device, filter are connect with power amplifier, and power amplifier is connect with sound card, and loudspeaker passes through preamplifier and sound
Card connection, sound card are connect with PC machine.
Compared with prior art, beneficial effects of the present invention are as follows:
(1) present invention is using sound wave as detection means, active detecting defect of pipeline, destroys in practical application to pipe-line system
Property it is small, detecting distance is long, and cost is relatively low for other opposite detection modes.
(2) present invention uses dual-tree complex wavelet transform algorithm, and it is mixed which can overcome Traditional Wavelet to decompose the frequency occurred
Folded phenomenon obtains accurately each frequency component.
(3) present invention identifies that semi-supervised learning can also effectively identify difference to different degrees of blocking using S4VM
Pipeline fault, and reduce the problem of mass data can not mark in practical pipe detection.
Detailed description of the invention
Fig. 1 is detection schematic diagram of the invention;
Fig. 2 (a) is the time-domain diagram that 1 dual-tree complex wavelet of the embodiment of the present invention decomposes sound pressure signal;
Fig. 2 (b) is the transformed time-domain diagram of 1 sound pressure level of the embodiment of the present invention;
Fig. 3 is that 1 liang of category feature of the embodiment of the present invention clusters visualization result.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, the invention will be further described.
Embodiment 1:(1) pipe detection schematic illustration as shown in Figure 1, pipeline head end place acoustic instrument, acoustics instrument
Device includes four hydrophones and a loudspeaker, and pipeline is externally provided with data signal sampling and processing equipment, data acquisition and signal
Processing equipment includes PC machine, sound card, filter, preamplifier and power amplifier;4 hydrophones connect with filter respectively
It connects, filter is connect with power amplifier, and power amplifier is connect with sound card, and loudspeaker is connected by preamplifier and sound card
It connects, sound card is connect with PC machine, and the sinusoidal signal that frequency of use range is 50 to 7000Hz is as pumping signal, the tail end half of pipeline
Closing, sound encounter pipeline tail end and occur to reflect, refraction, scatter, generate a large amount of carrying pipeline knots in the communication process of pipeline
Structure defect information reflection echo, the echo of data signal sampling and processing equipment acquisition reflection, every 0.1s acquire 4410 points, adopt
Sample frequency is 44100Hz, obtains the sound pressure signal data of pipeline;
(2) data signal sampling and processing equipment handles signal data, using dual-tree complex wavelet transform algorithm pair
Sound pressure signal data carry out 8 layers and decompose and reconstruct, and obtain the component of each frequency range, the component of each frequency range is used time domain chart respectively
Show, as shown in Fig. 2, by Fig. 2 (a) dual-tree complex wavelet decomposition result figure as it can be seen that d1, d2, d3 frequency are higher, fault characteristic information compared with
Less and contain noise information, so not handling d1, d2, d3 of high frequency section, remove the component of d1, d2, d3 frequency range,
According to the number of plies of decomposition, every layer of decomposition frequency becomes upper one layer of fs/2n, and Decomposition order is higher, and frequency is lower, selects remaining
D4, d5, d6, d7, d8, a8 carry out sound pressure level transformation as active constituent, by active constituent respectively, as shown in Fig. 2 (b);
(3) the pulse factor of the sound pressure level signal of each effective frequency range component of extraction step (2) and average sound energy density,
In each effective frequency range component average acoustic energy metric density formulas Extraction it is as follows:
Wherein,Indicate average acoustic energy metric density, peIndicate effective acoustic pressure, andpaIndicate original acoustic pressure, ρ0
Indicate density, c0Indicate sound spread speed in the duct,For the time average of sound energy density, V0For pipeline body
Product;The pulse factor P of extractionjWith average sound energy density PiMatrix it is as follows:
(4) the pulse factor and average sound energy density extracted step (3) be used as classification feature vector and by
Classification based training is carried out in feature vector input S4VM classifier and obtains the model of each classification results, obtains the mould of four kinds of classification results
Type, respectively normally, slight to block, middle severe blocking, three-way piece interference specially carries out the set of the feature vector of extraction
Singular value decomposition dimensionality reduction, by 6 dimension sign vectors drop to 3 dimensions carry out classification and 3 dimension coordinates under visualize, as shown in figure 3,
Four kinds of operating mode feature distribution characteristics vector aggregations are obvious, there is good separability, so feature set can be used to fault type
Classify.
(5) step (1)~(3) are repeated when testing other pipeline, obtain the pulse factor for testing pipeline data and average sound
Energy density, then calculates the Euclidean distance between test data and the model of step (4) each classification results, and by the Europe of calculating
Formula distance is test result of the representative classification results of minimum value as the test pipeline, completes the failure to test pipeline
Identification.
Specific embodiments of the present invention are explained in detail above in conjunction with attached drawing, but the present invention is not limited to above-mentioned realities
Example is applied, it within the knowledge of a person skilled in the art, can also be without departing from the purpose of the present invention
Various changes can be made.
Claims (4)
1. a kind of line clogging fault recognition method based on DT-CWT and S4VM, which is characterized in that detection pipeline first obtains
Then the sound pressure signal data of pipeline carry out the sound pressure signal data of acquisition using dual-tree complex wavelet transform algorithm decomposing weight
Structure obtains the component of each frequency range, effective frequency range component is selected from the component of each frequency range, and carry out acoustic pressure to effective frequency range component
Grade converts, and the pulse factor of effective frequency range component and average sound energy density after converting then is extracted, by the pulse factor and averagely
Sound energy density is classified as the feature vector for classification and by being trained in feature vector input S4VM classifier
As a result model identifies the different degrees of blocking of pipeline using the model of classification results and excludes the interference of three-way piece.
2. the line clogging fault recognition method according to claim 1 based on DT-CWT and S4VM, it is characterised in that: tool
Steps are as follows for body:
(1) acoustic instrument is placed in pipeline first, pipeline is externally provided with data signal sampling and processing equipment, the tail end half of pipeline
Closing, sound encounter pipeline tail end and occur to reflect, refraction, scatter, generate a large amount of carrying pipeline knots in the communication process of pipeline
Structure defect information reflection echo, the echo of data signal sampling and processing equipment acquisition reflection, obtains the sound pressure signal number of pipeline
According to;
(2) data signal sampling and processing equipment handles signal data, using dual-tree complex wavelet transform algorithm to acoustic pressure
Signal data is decomposed, is reconstructed, and the component of each frequency range is obtained, and the component of each frequency range is indicated with time domain figure respectively, when observation
Domain figure removes the frequency range component that the big time-domain diagram of signals and associated noises indicates, using the component of other frequency ranges as effective frequency range component,
And sound pressure level transformation is carried out to effective frequency range component, obtain the sound pressure level signal of each effective frequency range component;
(3) the pulse factor of the sound pressure level signal of each effective frequency range component of extraction step (2) and average sound energy density, wherein respectively
The formulas Extraction of the average acoustic energy metric density of effective frequency range component is as follows:
Wherein,Indicate average acoustic energy metric density, peIndicate effective acoustic pressure, andpaIndicate original acoustic pressure, ρ0It indicates
Density, c0Indicate sound spread speed in the duct,For the time average of sound energy density, V0For conduit volume;
(4) the pulse factor and average sound energy density extracted step (3) are used as the feature vector for classifying and by features
Classification based training, which is carried out, in vector input S4VM classifier obtains the model of each classification results;
(5) step (1)~(3) are repeated when testing other pipeline, obtain the pulse factor for testing pipeline data and average acoustic energy
Density, then calculates the Euclidean distance between test data and the model of step (4) each classification results, and by calculating it is European away from
From test result of the representative classification results as the test pipeline for minimum value, complete to know the failure of test pipeline
Not.
3. the line clogging fault recognition method according to claim 2 based on DT-CWT and S4VM, it is characterised in that: institute
It states in step (4) and obtains the model of four kinds of classification results, respectively normally, slight to block, middle severe blocking, three-way piece interference.
4. the line clogging fault recognition method according to claim 2 based on DT-CWT and S4VM, it is characterised in that: institute
Stating acoustic instrument in step (1) includes more than one hydrophone and a loudspeaker, data signal sampling and processing equipment packet
Include PC machine, sound card, filter, preamplifier and power amplifier;More than one hydrophone is connect with filter respectively, filter
Wave device is connect with power amplifier, and power amplifier is connect with sound card, and loudspeaker is connect by preamplifier with sound card, sound card
It is connect with PC machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810812279.1A CN109063762B (en) | 2018-07-23 | 2018-07-23 | Pipeline blockage fault identification method based on DT-CWT and S4VM |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810812279.1A CN109063762B (en) | 2018-07-23 | 2018-07-23 | Pipeline blockage fault identification method based on DT-CWT and S4VM |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109063762A true CN109063762A (en) | 2018-12-21 |
CN109063762B CN109063762B (en) | 2021-11-16 |
Family
ID=64836040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810812279.1A Active CN109063762B (en) | 2018-07-23 | 2018-07-23 | Pipeline blockage fault identification method based on DT-CWT and S4VM |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109063762B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109827081A (en) * | 2019-02-28 | 2019-05-31 | 昆明理工大学 | A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting |
CN110673199A (en) * | 2019-08-30 | 2020-01-10 | 昆明理工大学 | U-shaped tube blockage state assessment method based on low-frequency sound pressure signal analysis |
CN110940889A (en) * | 2019-12-06 | 2020-03-31 | 西安锐驰电器有限公司 | Fault detection method for high-voltage power equipment |
CN111815561A (en) * | 2020-06-09 | 2020-10-23 | 中海石油(中国)有限公司 | Pipeline defect and pipeline assembly detection method based on depth space-time characteristics |
CN112908356A (en) * | 2021-01-19 | 2021-06-04 | 昆明理工大学 | Buried drainage pipeline voiceprint recognition method based on BSE and GMM-HMM |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003106929A (en) * | 2001-09-28 | 2003-04-09 | Hokuriku Gas Co Ltd | Leak test method for gas supply inner pipe and tool for leak test |
CN103758511A (en) * | 2013-11-25 | 2014-04-30 | 中国石油天然气股份有限公司 | Method and device for identifying hidden reservoir through underground reverse time migration imaging |
US20150269494A1 (en) * | 2014-03-19 | 2015-09-24 | Intelius Inc. | Graph-based organization entity resolution |
CN107218518A (en) * | 2017-04-17 | 2017-09-29 | 昆明理工大学 | A kind of detection method of detection means for drain line blockage failure |
CN107314251A (en) * | 2017-06-09 | 2017-11-03 | 昆明理工大学 | A kind of detection means and detection method of sewer pipe leakage failure |
-
2018
- 2018-07-23 CN CN201810812279.1A patent/CN109063762B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003106929A (en) * | 2001-09-28 | 2003-04-09 | Hokuriku Gas Co Ltd | Leak test method for gas supply inner pipe and tool for leak test |
CN103758511A (en) * | 2013-11-25 | 2014-04-30 | 中国石油天然气股份有限公司 | Method and device for identifying hidden reservoir through underground reverse time migration imaging |
US20150269494A1 (en) * | 2014-03-19 | 2015-09-24 | Intelius Inc. | Graph-based organization entity resolution |
CN107218518A (en) * | 2017-04-17 | 2017-09-29 | 昆明理工大学 | A kind of detection method of detection means for drain line blockage failure |
CN107314251A (en) * | 2017-06-09 | 2017-11-03 | 昆明理工大学 | A kind of detection means and detection method of sewer pipe leakage failure |
Non-Patent Citations (7)
Title |
---|
JING YAN 等: "Research on Identifying Drainage Pipeline Blockage based on Multi-Feature Fusion", 《第29届中国控制与决策会议》 * |
NURUL FATIEHAH ADNAN 等: "Leak Detection in MDPE Gas Pipeline using Dual-Tree Complex Wavelet Transform", 《AUSTRALIAN JOURNAL OF BASIC AND APPLIED SCIENCES》 * |
徐章遂等著: "《故障信息诊断原理及应用》", 31 July 2000 * |
朱雪峰 等: "基于声学特征的埋地管道堵塞故障的聚类识别方法", 《云南大学学报( 自然科学版)》 * |
王惠新 等: "基于双树复小波及递归图的管道泄漏定位方法", 《计量学报》 * |
虞和济等编著: "《设备故障诊断工程》", 30 June 2001 * |
闫菁 等: "LMD 特征融合与 SVM 的供水管道堵塞识别", 《传感器与微***》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109827081A (en) * | 2019-02-28 | 2019-05-31 | 昆明理工大学 | A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting |
CN109827081B (en) * | 2019-02-28 | 2020-12-11 | 昆明理工大学 | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection |
CN110673199A (en) * | 2019-08-30 | 2020-01-10 | 昆明理工大学 | U-shaped tube blockage state assessment method based on low-frequency sound pressure signal analysis |
CN110673199B (en) * | 2019-08-30 | 2022-05-13 | 昆明理工大学 | U-shaped tube blockage state assessment method based on low-frequency sound pressure signal analysis |
CN110940889A (en) * | 2019-12-06 | 2020-03-31 | 西安锐驰电器有限公司 | Fault detection method for high-voltage power equipment |
CN111815561A (en) * | 2020-06-09 | 2020-10-23 | 中海石油(中国)有限公司 | Pipeline defect and pipeline assembly detection method based on depth space-time characteristics |
CN111815561B (en) * | 2020-06-09 | 2024-04-16 | 中海石油(中国)有限公司 | Pipeline defect and pipeline assembly detection method based on depth space-time characteristics |
CN112908356A (en) * | 2021-01-19 | 2021-06-04 | 昆明理工大学 | Buried drainage pipeline voiceprint recognition method based on BSE and GMM-HMM |
CN112908356B (en) * | 2021-01-19 | 2022-08-05 | 昆明理工大学 | Buried drainage pipeline voiceprint recognition method based on BSE and GMM-HMM |
Also Published As
Publication number | Publication date |
---|---|
CN109063762B (en) | 2021-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109063762A (en) | A kind of line clogging fault recognition method based on DT-CWT and S4VM | |
CN109654384B (en) | Pipeline leakage detection device and detection method based on PSO-VMD algorithm | |
Zhang et al. | Deep convolutional neural network probability imaging for plate structural health monitoring using guided waves | |
CN112858473B (en) | Turnout switch blade damage state monitoring method based on feature fusion | |
CN110762398B (en) | Oil and gas pipeline leakage detection method and system based on excitation response | |
Song et al. | Gas leak detection in galvanised steel pipe with internal flow noise using convolutional neural network | |
CN109827081B (en) | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection | |
CN101592288B (en) | Method for identifying pipeline leakage | |
CN106864477B (en) | A kind of rail flaw ultrasonic detection intelligent detecting method based on time-frequency do-nothing function | |
CN114062490B (en) | GAN-based rail weld Lamb wave modal decomposition and crack damage monitoring method | |
CN111695465B (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
CN107132760A (en) | The underwater robot state monitoring method described based on fuzzy support vector domain | |
CN105909979B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
CN106769734A (en) | A kind of focusing ultrasonic wave formula river load concentration On-line Measuring Method | |
CN112198232A (en) | Drainage pipeline working condition detection and identification method | |
CN105928666B (en) | Leakage acoustic characteristic extracting method based on Hilbert-Huang transform and blind source separating | |
CN116773654A (en) | Intelligent pipeline defect detection device and detection method based on circumferential guided waves | |
Liu et al. | Speech enhancement based on Hilbert-Huang transform | |
CN116025856A (en) | Pipeline leakage detection device and detection method | |
Sun et al. | An ultrasonic signal denoising method for EMU wheel trackside fault diagnosis system based on improved threshold function | |
CN107907279A (en) | Multiphase flow pipeline leakage acoustic signals analysis method based on wavelet coefficient amplitude | |
Zhao et al. | Pipeline leak fault feature extraction based on wavelet packet analysis and application | |
CN105927861A (en) | Feature extraction method based on blind source separation algorithm of wavelet transform fusion for leakage acoustic wave | |
Yang et al. | Research on pattern recognition method of blockage signal in pipeline based on LMD information entropy and ELM | |
Zhang et al. | Flaw classification in ultrasonic guided waves signal using Wavelet Transform and PNN classifier |
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 |