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 band
- sound
- sound pressure
- energy density
- 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 21
- 239000013598 vector Substances 0.000 claims abstract description 15
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 238000002592 echocardiography Methods 0.000 claims description 7
- 230000007547 defect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000009434 installation Methods 0.000 abstract description 3
- 230000000903 blocking effect Effects 0.000 abstract 1
- 238000007689 inspection Methods 0.000 abstract 1
- 238000000354 decomposition reaction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004880 explosion Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000010802 sludge Substances 0.000 description 2
- 230000005236 sound signal 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
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 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
- 238000002372 labelling Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 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 invention relates to a pipeline blockage fault identification method based on DT-CWT and S4VM, and belongs to the technical field of fault detection.
Background
In 2015, the total length of a water supply pipeline in China is about 71 kilometers, and the pipeline tends to rise every year, but compared with the developed country, the average leakage rate of the pipeline in China is high, oil sludge and rust scale in the pipeline caused by blockage can be solidified, and the original pipeline diameter is reduced; the sludge can be precipitated in the pipeline, easily generates inflammable and explosive gases such as hydrogen sulfide and the like, causes environmental pollution and easily causes pipe explosion. If the foreign matters in the pipeline are not removed in time, the pipeline can be blocked, the water safety is damaged if the foreign matters are not removed in time, and leakage and pipe explosion are caused if the foreign matters are not removed in time, so that huge losses and damages are caused to resources, environment and economy of China. Therefore, the method and the device can detect the pipeline blockage in time and control the danger caused by the quantity of the pipeline blockage, and have important significance for saving water resources, guaranteeing urban water and promoting the sustainable and healthy development of the economy of China.
At present, detection of buried drainage pipelines is mainly focused on post detection, and the method has the main problems of excavation damage, dependence on manual operation, expensive equipment and the like. The detection method based on acoustics has the characteristics of low cost, convenience in installation and the like. The guided wave detection belongs to one of the latest methods in the field of acoustic nondestructive detection, can be used for detecting and positioning pipeline blockage and leakage, adopts mechanical stress waves to propagate along the extension direction of a pipeline, has long propagation distance and small attenuation, can detect a single position by hundreds of meters in some cases, only needs to process the outer surface of the pipeline at the installation position of a sensor, and can detect the pipeline part which is difficult to detect in a short distance. When the pipeline is blocked, the cross section area of the pipeline is reduced, when the medium of the guided wave is changed, the acoustic characteristic can be correspondingly changed, and the guided wave can be influenced by conventional parts of the pipeline, such as a tee joint, in the propagation process.
Disclosure of Invention
The invention aims to provide a pipeline blockage fault identification method based on DT-CWT and S4VM, wherein DT-CWT is double-tree complex wavelet transform, S4VM is a safe semi-supervised support vector machine, the method solves the problem that the existing pipeline detection signals are difficult to effectively process, echoes in a pipeline are obtained by detecting pipeline blockage and leakage through guided waves, the obtained echo signals are nonlinear and non-stationary signals, the characteristics of the blockage sound signals are analyzed from the mechanism of the blockage sound signals, the signals are preprocessed by using a characteristic extraction method combining double-tree complex wavelet transform and sound pressure level, sound energy density and pulse factors are extracted as characteristics according to the propagation mechanism of sound waves in the pipeline, and the safe semi-supervised support vector machine, namely S4VM, is used for multi-classification labeling of different blockage conditions and three-way parts.
The technical scheme of the invention is as follows: the method comprises the steps of firstly detecting a pipeline to obtain sound pressure signal data of the pipeline, then decomposing and reconstructing the obtained acoustic signal data by adopting a dual-tree complex wavelet transform algorithm to obtain components of each frequency band, selecting effective frequency band components from the components of each frequency band, carrying out sound pressure level transformation on the effective frequency band components, then extracting pulse factors and average sound energy density of the transformed effective frequency band components, inputting the pulse factors and the average sound energy density into an S4VM classifier as feature vectors for classification to train to obtain a trainer model, identifying blockage of the pipeline at different degrees by using the trainer model, and eliminating interference of a three-way part.
The method comprises the following specific steps:
(1) firstly, placing an acoustic instrument in a pipeline, arranging a data acquisition and signal processing device outside the pipeline, enabling the tail end of the pipeline to be semi-closed, generating a large number of reflected echoes carrying pipeline structure defect information when sound is reflected, refracted and scattered at the tail end of the pipeline in the transmission process of the pipeline, and acquiring the reflected echoes by the data acquisition and signal processing device to obtain sound pressure signal data of the pipeline;
(2) processing the signal data by the data acquisition and signal processing equipment, decomposing and reconstructing the sound pressure signal data by adopting a dual-tree complex wavelet transform algorithm to obtain components of each frequency band, respectively representing the components of each frequency band by using a time domain diagram, observing the time domain diagram, removing the frequency band component represented by the time domain diagram with large noise signals, taking the components of other frequency bands as effective frequency band components, and carrying out sound pressure level transformation on the effective frequency band components to obtain sound pressure level signals of each effective frequency band component;
(3) extracting the pulse factor and the average sound energy density of the sound pressure level signal of each effective frequency band component in the step (2), wherein the formula of the average sound energy density of each effective frequency band component is extracted as follows:
wherein,denotes the mean acoustic energy density, peRepresents an effective sound pressure, andparepresenting the original sound pressure, p0Denotes the medium density, c0Which is indicative of the speed of sound propagation in the pipe,is the time average of the acoustic energy density, V0Is the volume of the pipeline;
(4) taking the pulse factor and the average acoustic energy density extracted in the step (3) as feature vectors for classification, and inputting the feature vectors into an S4VM classifier for classification training to obtain models of each classification result;
(5) and (3) repeating the steps (1) to (3) when testing another pipeline to obtain the pulse factor and the average sound energy density of the data of the tested pipeline, then calculating the Euclidean distance between the data of the test and the model of each classification result in the step (4), and taking the classification result represented by the minimum Euclidean distance as the test result of the tested pipeline to finish the fault identification of the tested pipeline.
And (4) obtaining four classification result models, namely normal, slight blockage, medium and heavy blockage and three-way interference.
The acoustic instrument in the step (1) comprises more than one hydrophone and a loudspeaker, and the data acquisition and signal processing equipment comprises a PC (personal computer), a sound card, a filter, a preamplifier and a power amplifier; more than one hydrophone is respectively connected with the filter, the filter is connected with the power amplifier, the power amplifier is connected with the sound card, the loudspeaker is connected with the sound card through the preamplifier, and the sound card is connected with the PC.
Compared with the prior art, the invention has the following beneficial effects:
(1) the invention takes sound wave as a detection means to actively detect the defects of the pipeline, has small destructiveness to the pipeline system in practical application, long detection distance and lower cost compared with other detection modes.
(2) The invention adopts a dual-tree complex wavelet transform algorithm, which can overcome the frequency aliasing phenomenon of the traditional wavelet decomposition and obtain accurate frequency components.
(3) According to the invention, the S4VM is adopted to identify the blockage in different degrees, and the semi-supervised learning can also effectively identify different pipeline faults, and the problem that a large amount of data cannot be labeled in actual pipeline detection is reduced.
Drawings
FIG. 1 is a schematic view of the detection principle of the present invention;
fig. 2(a) is a time domain diagram of a dual-tree complex wavelet decomposition sound pressure signal according to embodiment 1 of the present invention;
fig. 2(b) is a time domain diagram after sound pressure level transformation according to embodiment 1 of the present invention;
fig. 3 shows the two types of feature clustering visualization results in embodiment 1 of the present invention.
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
Example 1: (1) fig. 1 shows a schematic diagram of a pipeline detection principle, where an acoustic instrument is placed at a head end of a pipeline, the acoustic instrument includes four hydrophones and a loudspeaker, a data acquisition and signal processing device is arranged outside the pipeline, and the data acquisition and signal processing device includes a PC, a sound card, a filter, a preamplifier and a power amplifier; the 4 hydrophones are respectively connected with a filter, the filter is connected with a power amplifier, the power amplifier is connected with a sound card, a loudspeaker is connected with the sound card through a preamplifier, the sound card is connected with a PC (personal computer), a sine signal with the frequency range of 50-7000 Hz is used as an excitation signal, the tail end of the pipeline is semi-closed, sound is reflected, refracted and scattered when encountering the tail end of the pipeline in the transmission process of the pipeline, a large amount of reflected echoes carrying pipeline structure defect information are generated, data acquisition and signal processing equipment acquires the reflected echoes, 4410 points are acquired every 0.1s, and the sampling frequency is 44100Hz, so that sound pressure signal data of the pipeline is obtained;
(2) the data acquisition and signal processing equipment processes the signal data, 8-layer decomposition and reconstruction are carried out on the sound pressure signal data by adopting a dual-tree complex wavelet transform algorithm to obtain components of each frequency band, the components of each frequency band are respectively represented by a time domain diagram, as shown in fig. 2, as can be seen from a diagram of a result of the dual-tree complex wavelet decomposition of fig. 2(a), d1, d2 and d3 are high in frequency, less in fault characteristic information and contain noise information, so d1, d2 and d3 of a high-frequency part are not processed, the components of d1, d2 and d3 frequency bands are removed, according to the number of decomposed layers, the decomposition frequency of each layer is changed into fs/2n of a previous layer, the higher the number of decomposed layers is, the lower the frequency is, the rest of d4, d5, d6, d7, d8 and a8 are selected as effective components, and the effective components are respectively subjected to sound pressure level transformation, as shown in fig. 2;
(3) extracting the pulse factor and the average sound energy density of the sound pressure level signal of each effective frequency band component in the step (2), wherein the formula of the average sound energy density of each effective frequency band component is extracted as follows:
wherein,denotes the mean acoustic energy density, peRepresents an effective sound pressure, andparepresenting the original sound pressure, p0Denotes the medium density, c0Which is indicative of the speed of sound propagation in the pipe,is the time average of the acoustic energy density, V0Is the volume of the pipeline; extracted pulse factor PjAnd the mean acoustic energy density PiThe matrix of (a) is as follows:
(4) and (3) taking the pulse factor and the average acoustic energy density extracted in the step (3) as feature vectors for classification, inputting the feature vectors into an S4VM classifier for classification training to obtain models of each classification result, and obtaining models of four classification results, namely normal models, slight blockage models, moderate and severe blockage models and three-way part interference models, specifically, performing singular value decomposition and dimension reduction on a set of the extracted feature vectors, reducing 6-dimensional sign vectors to 3-dimensional vectors for classification, and visualizing under 3-dimensional coordinates, as shown in FIG. 3, the feature vectors of feature distribution of four working conditions are obviously aggregated and have good separability, so that the feature set can be used for classifying fault types.
(5) And (3) repeating the steps (1) to (3) when testing another pipeline to obtain the pulse factor and the average sound energy density of the data of the tested pipeline, then calculating the Euclidean distance between the data of the test and the model of each classification result in the step (4), and taking the classification result represented by the minimum Euclidean distance as the test result of the tested pipeline to finish the fault identification of the tested pipeline.
While the present invention has been described in detail with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, and various changes and modifications can be made within the knowledge of those skilled in the art without departing from the spirit of the present invention.
Claims (4)
1. A pipeline blockage fault identification method based on DT-CWT and S4VM is characterized in that a pipeline is detected to obtain sound pressure signal data of the pipeline, then a dual-tree complex wavelet transform algorithm is adopted to decompose and reconstruct the obtained sound pressure signal data to obtain components of each frequency band, effective frequency band components are selected from the components of each frequency band, sound pressure level transformation is carried out on the effective frequency band components, then pulse factors and average sound energy density of the transformed effective frequency band components are extracted, the pulse factors and the average sound energy density are used as feature vectors for classification, the feature vectors are input into an S4VM classifier to be trained to obtain a model of a classification result, the model of the classification result is used for identifying blockage of the pipeline in different degrees, and interference of a tee joint is eliminated.
2. The DT-CWT and S4 VM-based pipe blockage fault identification method according to claim 1, wherein: the method comprises the following specific steps:
(1) firstly, placing an acoustic instrument in a pipeline, arranging a data acquisition and signal processing device outside the pipeline, enabling the tail end of the pipeline to be semi-closed, generating a large number of reflected echoes carrying pipeline structure defect information when sound is reflected, refracted and scattered at the tail end of the pipeline in the transmission process of the pipeline, and acquiring the reflected echoes by the data acquisition and signal processing device to obtain sound pressure signal data of the pipeline;
(2) processing the signal data by the data acquisition and signal processing equipment, decomposing and reconstructing the sound pressure signal data by adopting a dual-tree complex wavelet transform algorithm to obtain components of each frequency band, respectively representing the components of each frequency band by using a time domain diagram, observing the time domain diagram, removing the frequency band component represented by the time domain diagram with large noise signals, taking the components of other frequency bands as effective frequency band components, and carrying out sound pressure level transformation on the effective frequency band components to obtain sound pressure level signals of each effective frequency band component;
(3) extracting the pulse factor and the average sound energy density of the sound pressure level signal of each effective frequency band component in the step (2), wherein the formula of the average sound energy density of each effective frequency band component is extracted as follows:
wherein,denotes the mean acoustic energy density, peRepresents an effective sound pressure, andparepresenting the original sound pressure, p0Denotes the medium density, c0Which is indicative of the speed of sound propagation in the pipe,is the time average of the acoustic energy density, V0Is the volume of the pipeline;
(4) taking the pulse factor and the average acoustic energy density extracted in the step (3) as feature vectors for classification, and inputting the feature vectors into an S4VM classifier for classification training to obtain models of each classification result;
(5) and (3) repeating the steps (1) to (3) when testing another pipeline to obtain the pulse factor and the average sound energy density of the data of the tested pipeline, then calculating the Euclidean distance between the data of the test and the model of each classification result in the step (4), and taking the classification result represented by the minimum Euclidean distance as the test result of the tested pipeline to finish the fault identification of the tested pipeline.
3. The DT-CWT and S4 VM-based pipe blockage fault identification method according to claim 2, wherein: and (4) obtaining four classification result models, namely normal, slight blockage, medium and heavy blockage and three-way interference.
4. The DT-CWT and S4 VM-based pipe blockage fault identification method according to claim 2, wherein: the acoustic instrument in the step (1) comprises more than one hydrophone and a loudspeaker, and the data acquisition and signal processing equipment comprises a PC (personal computer), a sound card, a filter, a preamplifier and a power amplifier; more than one hydrophone is respectively connected with the filter, the filter is connected with the power amplifier, the power amplifier is connected with the sound card, the loudspeaker is connected with the sound card through the preamplifier, and the sound card is connected with the PC.
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", 《传感器与微系统》 * |
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 |
---|---|---|
CN109063762B (en) | Pipeline blockage fault identification method based on DT-CWT and S4VM | |
CN109654384B (en) | Pipeline leakage detection device and detection method based on PSO-VMD algorithm | |
Chuang et al. | Leak detection in water distribution pipes based on CNN with mel frequency cepstral coefficients | |
CN110762398B (en) | Oil and gas pipeline leakage detection method and system based on excitation response | |
Davoodi et al. | Gas leak locating in steel pipe using wavelet transform and cross-correlation method | |
CN109827081B (en) | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection | |
CN104089699A (en) | Substation equipment sound reconstruction algorithm | |
Yao et al. | Multiband weights-induced periodic sparse representation for bearing incipient fault diagnosis | |
Han et al. | A novel rolling bearing fault diagnosis method based on generalized nonlinear spectral sparsity | |
CN105909979B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
Tao et al. | Data compression and damage evaluation of underground pipeline with musicalized sonar GMM | |
Lee et al. | Deepaup: A deep neural network framework for abnormal underground heat transport pipelines | |
Xie et al. | Research on vibration fatigue damage identification of oil and gas pipeline under the condition of measured noise injection | |
Liu et al. | A non-contacting leak fault diagnosis method for subsea Christmas tree valve based on deep neural network with skip connections | |
CN117609860A (en) | Training method of pipeline leakage detection model, pipeline leakage detection method and device | |
CN105928666B (en) | Leakage acoustic characteristic extracting method based on Hilbert-Huang transform and blind source separating | |
CN112198232A (en) | Drainage pipeline working condition detection and identification method | |
CN116773654A (en) | Intelligent pipeline defect detection device and detection method based on circumferential guided waves | |
CN117214294A (en) | Ultrasonic guided wave detection device for pipeline damage and three-dimensional reconstruction method for damage signal of ultrasonic guided wave detection device | |
Feng | Condition Classification in Underground Pipes Based on Acoustical Characteristics. Acoustical characteristics are used to classify the structural and operational conditions in underground pipes with advanced signal classification methods | |
CN115078538B (en) | High-voltage cable aluminum sheath corrosion ultrasonic guided wave detection method, system and medium based on SWT-AE | |
PiRemli et al. | Transient-based leak detection and monitoring of water pipes using complementary ensemble empirical mode decomposition (CEEMD) method | |
CN114972898A (en) | Drainage pipeline online detection method based on low-frequency sound waves | |
CN105927861A (en) | Feature extraction method based on blind source separation algorithm of wavelet transform fusion for leakage acoustic wave | |
Shi et al. | Wavelet de-noising method analysis of pipeline magnetic flux leakage in-line inspection based on coefficient of variation |
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 |