CN109827081A - A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting - Google Patents
A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting Download PDFInfo
- Publication number
- CN109827081A CN109827081A CN201910150736.XA CN201910150736A CN109827081A CN 109827081 A CN109827081 A CN 109827081A CN 201910150736 A CN201910150736 A CN 201910150736A CN 109827081 A CN109827081 A CN 109827081A
- Authority
- CN
- China
- Prior art keywords
- signal
- pipeline
- acoustic signals
- sample
- connection part
- 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
- 238000002405 diagnostic procedure Methods 0.000 title claims abstract description 7
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000000903 blocking effect Effects 0.000 claims abstract description 15
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 8
- 239000004020 conductor Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 239000010865 sewage Substances 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of buried drain pipe road plugging fault based on acoustics active detecting and branch pipe tee connection part diagnostic methods, belong to pipeline fault diagnostic field.The present invention selects corresponding pipeline to detect with detection device, and computer obtains the signal under four kinds of operating conditions from receiving end;WAVELET PACKET DECOMPOSITION is carried out to acoustic signal is obtained;Various features are cascaded constitutive characteristic vector to characterize the signal of different operating conditions by energy-distributing feature, Sample Entropy and the wave character for extracting each frequency range component;Super complete dictionary is constructed with the feature vector of the training sample first gathered;Reconstruction signal of the detection signal in different classes of is acquired on the basis of super complete dictionary using sparse representation method, is passed through and is calculated the residual values of test sample and its reconstruction signal and realize the identification of line clogging degree and three-way piece.The present invention can identify blocking and branch pipe tee connection part different degrees of in pipeline and the accuracy for improving recognition result, have certain robustness to extraneous environmental change.
Description
Technical field
The present invention relates to a kind of buried drain pipe road plugging faults based on acoustics active detecting and branch pipe tee connection part to diagnose
Method belongs to pipeline fault diagnostic field.
Background technique
With urbanization process, the underground utility drainage pipeline network for serving our cities and towns and city becomes basis and sets
Apply one of most important component part, but it be on the ground it is invisible, therefore, unless the failures such as blocking, leakage occur in it,
Otherwise this network will not be paid attention to by people.Drainage pipeline is long using the time, is easy to cause that plugging fault occurs in pipeline.Blocking
Failure is showing as different degrees of Partial Blocking in early days, therefore is easy to be ignored.Last blocked area constantly expands, and not only can
Influence drain function, it is also possible to bring security risk.Therefore the monitoring and detection to drainage pipeline, causes to avoid equipment
Life accident and reduce to the greatest extent overflow fluid caused by environmental pollution, become most important.The event of buried drain pipe road blocking at present
The detection of barrier is main in practical applications or detects afterwards, exists in method and excavates damage, and dependence manual operation wastes man power and money
Etc. main problems;There are vibration analysis, pulse echo analysis, sound reflecting, resistance in the common detection method of research field line clogging
Anti- method etc..Acoustic detection method has unique advantage in pipeline fault detection, does not need to excavate pipeline, sound is in pipe
When propagating in road the information abundant about pipeline internal state, detection method letter are not influenced and carried by pipeline operation conditions
It is single and low in cost.The design introduces buried drain pipe road plugging fault and the diagnosis of branch pipe tee connection part based on acoustics active detecting
Method, it is intended to solve the problems, such as that line clogging degree and branch pipe tee connection part signal are difficult to differentiate between in line clogging detection process,
Become effective solution.
Summary of the invention
It is difficult to solve line clogging degree and branch pipe tee connection part signal during buried drain pipe road jam detection
The problem of differentiation, the present invention provides a kind of buried drain pipe road plugging fault and branch pipe tee connection part based on acoustics active detecting
Diagnostic method.
The technical scheme is that a kind of buried drain pipe road plugging fault and pipeline three based on acoustics active detecting
Parts diagnostic method, specific step is as follows for the method:
For S1 using the acoustic signals in detection device collection phase buried drain pipe road as training sample, acoustic signals include just
Acoustic signals under Chang Guandao, the normal pipeline containing three-way piece, slight blocking pipeline and severe blocking four kinds of operating conditions of pipeline;
Wherein detection device includes two telescope supports, sound card, signal amplifier, loudspeaker, acoustic receiver, filters
Be equipped with WinLMS computer;Two telescope supports are stretched into shaft bottom from same Sewage well cover, one is fixed therein and stretches
The loudspeaker of pedestal lower end emits acoustic signals in buried drain pipe road, and acoustic signals are that computer controls what sound card generated
Signal is transferred to loudspeaker via the inner conductors of telescope support through the amplified signal of signal amplifier;Another flexible branch
Acoustic receiver is placed in the bottom end of frame, receives reflected sound wave, the inner conductors that sound wave passes through this telescope support again reach
Filter is filtered, and filtered signal is input in computer and carries out data processing.It will pipe when using detection device
The collection for reflected acoustic wave is blocked in road tail portion.
Wherein severe blocking pipeline refers to that the shared height of tamper has been more than the 1/3 of pipe diameter, and the slight pipeline that blocks is
Refer to that the shared height of tamper is less than the 1/3 of pipe diameter.
S2 carries out WAVELET PACKET DECOMPOSITION to four kinds of acoustic signals in training sample and obtains each frequency range component under four kinds of operating conditions,
Each frequency range component chooses the frequency range component comprising frequency 100-6000Hz, gives up other frequency range components;Again by each frequency range component
Energy-distributing feature, Sample Entropy and wave character are extracted respectively, and the cascade of multiple features is characterized four as feature vector set
The different acoustic signals of kind;Energy-distributing feature includes that energy, energy accounting and Energy-Entropy, wave character refer to comprising degree of skewness
Mark, kurtosis index, peak-to-peak value, peak index, pulse index, margin index and root amplitude.
S3 constructs super complete dictionary using the feature vector of training sample;
By the feature connection one column feature vector set of composition of each frequency range component, V indicates the feature of whole training samples
Vector matrix,K is pipeline acoustic signals
Total classification number i.e. 4 classes, niIndicate the number of samples of the i-th class acoustic signals, i=1,2 ..., k.
S4 acquires detection signal i.e. test sample different classes of using sparse representation method on the basis of super complete dictionary
In reconstruction signal, pass through and calculate the residual values of test sample and its reconstruction signal and realize the knowledge of line clogging degree and three-way piece
Not.
If a certain test sample y belongs to the i-th class acoustic signals, feature vector VyBy the corresponding instruction of the i-th class acoustic signals
Practicing sample characteristics approximatively indicates and reconstructs by linearly i.e.:
Wherein αi,jFor sparse coefficient, j=1,2 ..., ni, Vi,jIndicate the feature of i-th j-th of sample of class acoustic signals to
Amount, under whole training samples, VyIt is rewritable at:
From the above equation, we can see that such test sample of the atom pair of uniformity signal reconstruct contribution rate is maximum, remaining category-atom
It is almost nil to reconstruct contribution rate;I.e. test sample y only with belong to the i-th similar class training sample strong correlation, the i.e. training of the i-th class
The corresponding characterization coefficient, that is, solution vector α of sample is larger, and the corresponding characterization coefficient of other training samples is smaller or is equal to zero.
One group of the most sparse coefficient is selected, from solution vector α to use less training sample sparse representation test specimens
This, then the above problem, which is converted into, utilizes l0Norm seeks most sparse solution:
Minimum l0Norm solution is a NP-hard problem, it is difficult to direct solution.If α is sparse enough, l0Norm solves
It can be equivalent to l1Norm solves, and above formula is written as:
Due to often introducing noise in actual conditions, z is noise, so we are actually to solve this in our solutions
A formula:
Vy=V α+z (6)
So reformed into the bound term for solving this optimization problem:
Wherein, ε indicates allowable error, and the most sparse solution of test sample is calculated by above formulaIt utilizesFor sample weight
Structure coefficient and dictionary calculate test sample y in inhomogeneous reconstruct test sample:
The residual values for finally calculating test sample y and every class reconstructed sample, according to residual values riSize judge pipeline believe
Number classification, seek riMinimum value, then it represents that the test sample belongs to the i-th class signal, it may be assumed that
The beneficial effects of the present invention are:
1 overcomes traditional detection in the disadvantage of drainage pipeline fault detection, can be the case where engineering staff does not descend pipeline
Under, carry out fault detection.
2 active detecting methods be used for drainage pipeline fault detection, can more timely debug, reduce property loss with
Environmental pollution
3 detection methods are extracted signal various features, compensate for single feature failure and extract insufficient situation, can be more complete
The characteristic of the reflection pipeline in face, while branch pipe tee connection part signal and jam signal can be differentiated.
4 improve the accuracy of recognition result, have certain robustness to extraneous environmental change.
Detailed description of the invention
Fig. 1 is a kind of detection device schematic diagram based on acoustics active detecting buried drain pipe road plugging fault and three-way piece;
Fig. 2 is the diagnostic method flow chart of a kind of buried drain pipe road plugging fault and branch pipe tee connection part;
Four kinds of different operating condition pipeline time domain acoustic pressure waveform diagrams that Fig. 3 is 0.1s;
Fig. 4 is sparse coefficient distribution map after normal duct acoustics signal WAVELET PACKET DECOMPOSITION;
Fig. 5 is sparse coefficient distribution map after the acoustic signal of normal pipeline containing three-way piece WAVELET PACKET DECOMPOSITION;
Fig. 6 is sparse coefficient distribution map after slight blocking duct acoustics signal WAVELET PACKET DECOMPOSITION;
Fig. 7 is that severe blocks sparse coefficient distribution map after duct acoustics signal WAVELET PACKET DECOMPOSITION.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples.
Embodiment 1: the detection device based on acoustics buried drain pipe road plugging fault and three-way piece.Experimental provision such as attached drawing
Shown in 1.When it is implemented, two telescope supports are insinuated into duct bottom by well lid, two bars distance side by side is fixed therein
The lower end loudspeaker of a piece telescope support emits acoustic signals in buried drain pipe road, and loudspeaker model selects U.S. EV
UW30 pallesthesiometer, acoustic signals generate 10 seconds sine by the computer control sound card equipped with WinLMS software and sweep
Frequency acoustical signal, sound card model Asus Xonar D-Kara, the frequency range of signal are 100-6000 hertz, amplified signal
It is transferred to loudspeaker via the inner conductors of telescopic rod I, selects the power amplifier of LM3886 model;Another telescope support bottom
Acoustic receiver is placed at end, receives reflected sound wave, and two acoustic receivers are to place up and down, and sound wave passes through flexible branch again
The inner conductors of frame reach filter and are filtered, and select model AB1500-100F6HA filter to be filtered, after filtering
Signal be input in computer and carry out data processing.
Embodiment 2: case verification, tool are carried out using Bradford, Britain pipeline laboratory data in the present embodiment
The method of body is as described in foregoing summary part.
Extract signal: experiment flow is as shown in Fig. 2.Before detection, in order to obtain normal pipeline, normal pipe containing three-way piece
Training data under road, slightly blocking pipeline, severe blocking four kinds of operating conditions of pipeline, laboratory such as Fig. 1 carry out experiment porch and build,
Computer obtains the training signal of four kinds of operating conditions, as shown in Figure 3.20 groups of data of every class signal behavior for training, use by 8 groups of data
In test.
Selection characteristic component signal: the signal under four kinds of operating conditions being input in MATLAB and is analyzed, and is used training
Normal pipeline signal, the signal of normal pipeline containing three-way piece and in various degree blocking pipe signal carry out WAVELET PACKET DECOMPOSITION, selection
Qualified each frequency range component signal carries out feature extraction.
Feature extraction: and then the characteristic extraction procedure of signal is carried out, feature extraction is carried out to each frequency range component, extracts it
Multiple joints of extraction are characterized different classes of pipeline as characteristic set by energy-distributing feature, Sample Entropy, wave character
Signal.
Testing classification device: super complete word is constructed with the feature vector for the signal (training sample) first collected on this basis
Allusion quotation, the feature connection one column feature vector set of composition of each frequency range component.
Detection signal (test sample) is acquired on the basis of super complete dictionary using sparse representation method in different classes of
Sparse representation coefficient (as shown in figs. 4-7), from Fig. 4-7 it is found that test sample solve sparse representation coefficient and same type believe
The sparse representation coefficient of same type signal is larger in number strong correlation, that is, training sample dictionary, the sparse representation system of other type signals
Number is zero or smaller.Test sample is trained to the signal sparse representation of same type in sample dictionary, can preferably approach test
Sample.Sparse representation coefficient and dictionary calculate test sample in inhomogeneous reconstruct test sample, calculate each classification reconstruct sample
The reconstructed residual (as shown in table 1) of this and test sample returns to signal classification described in the smallest residual values as test signal classification.
Table 1 extracts the test sample classification results of SRC classification based on wavelet packet character
It is stifled to be classified as severe in the 4th class for the 16th test sample (acoustic signal of normal pipeline containing three-way piece) mistake in table 1
Fill in duct acoustics signal.But total result shows that the classifier based on sparse representation can accurately identify various types of signal.
In order to prove the validity of this paper algorithm, SRC algorithm, support vector machines are constructed respectively in experiment simulation
Algorithm, the disaggregated model of extreme learning machine (extreme learning machine, ELM) algorithm and wavelet packet+SRC algorithm,
Many experiments are carried out on identical data set and (as shown in table 2) is compared to the average value of experimental identification rate.
The comparison of 2 method discrimination of table
The classification results of various classifiers in contrast table 2 are it is found that wavelet packet enhancing sparse representation classifying quality is better than pole
It limits learning machine, support vector machines and is based on global feature SRC.
Above in conjunction with attached drawing, the embodiment of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (7)
1. a kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method, feature based on acoustics active detecting exists
In: specific step is as follows for the method:
For S1 using the acoustic signals in detection device collection phase buried drain pipe road as training sample, acoustic signals include normal
Acoustic signals under pipeline, the normal pipeline containing three-way piece, slight blocking pipeline and severe blocking four kinds of operating conditions of pipeline;
S2 carries out WAVELET PACKET DECOMPOSITION to four kinds of acoustic signals in training sample and obtains each frequency range component under four kinds of operating conditions, then
Each frequency range component is extracted into energy-distributing feature, Sample Entropy and wave character respectively, by multiple features cascade as feature to
Duration set characterizes four kinds of different acoustic signals;
S3 constructs super complete dictionary using the feature vector of training sample;
S4 acquires detection signal i.e. test sample in different classes of using sparse representation method on the basis of super complete dictionary
Reconstruction signal, the residual values by calculating test sample and its reconstruction signal realize the identification of line clogging degree and three-way piece.
2. the buried drain pipe road plugging fault and branch pipe tee connection part according to claim 1 based on acoustics active detecting is examined
Disconnected method, it is characterised in that: the detection device in the step S1 includes two telescope supports, sound card, signal amplifier, loudspeakings
Device, acoustic receiver, filter and be equipped with WinLMS computer;
Two telescope supports stretch to shaft bottom from same Sewage well cover, are fixed therein the loudspeaking of a telescope support lower end
Device emits acoustic signals in buried drain pipe road, and acoustic signals are the signal that computer controls that sound card generates, and puts through signal
The big amplified signal of device is transferred to loudspeaker via the inner conductors of telescope support;The bottom end placement sound of another telescope support
Wave receiver receives reflected sound wave, and the inner conductors that sound wave passes through this telescope support again reach filter and are filtered,
Filtered signal is input in computer and carries out data processing.
3. the buried drain pipe road plugging fault and branch pipe tee connection part according to claim 2 based on acoustics active detecting is examined
Disconnected method, it is characterised in that: using pipeline tail portion to be blocked to the collection for being used for reflected acoustic wave when detection device in the step S1.
4. the buried drain pipe road plugging fault and branch pipe tee connection part according to claim 1 based on acoustics active detecting is examined
Disconnected method, it is characterised in that: the severe blocking pipeline in the step S1 refers to that the shared height of tamper has been more than pipe diameter
1/3, the slight pipeline that blocks refers to that the shared height of tamper is less than the 1/3 of pipe diameter.
5. the buried drain pipe road plugging fault and branch pipe tee connection part according to claim 1 based on acoustics active detecting is examined
Disconnected method, it is characterised in that: each frequency range component in the step S2 chooses the frequency range component comprising frequency 100-6000Hz, house
Abandon other frequency range components;The energy-distributing feature includes that energy, energy accounting and Energy-Entropy, wave character refer to comprising degree of skewness
Mark, kurtosis index, peak-to-peak value, peak index, pulse index, margin index and root amplitude.
6. the buried drain pipe road plugging fault and branch pipe tee connection part diagnosis side according to claim 1 based on acoustics active detecting
Method, it is characterised in that: the detailed process of the step S3 are as follows: the feature connection of each frequency range component is formed into a column feature vector set,
V indicates the eigenvectors matrix of whole training samples,
K is total classification number i.e. 4 classes of pipeline acoustic signals, niIndicate the number of samples of the i-th class acoustic signals, i=1,2 ..., k.
7. the buried drain pipe road plugging fault and branch pipe tee connection part according to claim 1 based on acoustics active detecting is examined
Disconnected method, it is characterised in that: the detailed process of the step S4 are as follows: it sets a certain test sample y and belongs to the i-th class acoustic signals,
Feature vector VyIt is approximatively indicated and is reconstructed by linearly i.e. by the corresponding training sample feature of the i-th class acoustic signals:
Wherein αi,jFor sparse coefficient, j=1,2 ..., ni, Vi,jThe feature vector for indicating i-th j-th of sample of class acoustic signals,
Under whole training samples, VyIt is rewritable at:
From the above equation, we can see that such test sample of the atom pair of uniformity signal reconstruct contribution rate is maximum, the reconstruct of remaining category-atom
Contribution rate is almost nil;
One group of the most sparse coefficient is selected from solution vector α, to use less training sample sparse representation test sample, then
The above problem, which is converted into, utilizes l0Norm seeks most sparse solution:
If α is sparse enough, l0Norm solution can be equivalent to l1Norm solves, and above formula is written as:
Practical solve introduces noise z, it may be assumed that
Vy=V α+z
Its bound term becomes:
Wherein, ε indicates allowable error, and the most sparse solution of test sample is calculated by above formulaIt utilizesIt is reconstructed for sample and is
Several and dictionary calculates test sample y in inhomogeneous reconstruct test sample:
The residual values for finally calculating test sample y and every class reconstructed sample, according to residual values riSize judge the class of pipe signal
Not, r is soughtiMinimum value, then it represents that the test sample belongs to the i-th class signal, it may be assumed that
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910150736.XA CN109827081B (en) | 2019-02-28 | 2019-02-28 | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910150736.XA CN109827081B (en) | 2019-02-28 | 2019-02-28 | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109827081A true CN109827081A (en) | 2019-05-31 |
CN109827081B CN109827081B (en) | 2020-12-11 |
Family
ID=66864852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910150736.XA Expired - Fee Related CN109827081B (en) | 2019-02-28 | 2019-02-28 | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109827081B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN112198232A (en) * | 2020-09-14 | 2021-01-08 | 昆明理工大学 | Drainage pipeline working condition detection and identification method |
CN113340997A (en) * | 2021-05-11 | 2021-09-03 | 西安交通大学 | Laser shock peening defect online detection method based on acoustic emission dual-channel range |
CN114136604A (en) * | 2021-11-30 | 2022-03-04 | 三门核电有限公司 | Rotary equipment fault diagnosis method and system based on improved sparse dictionary |
CN114352946A (en) * | 2022-03-15 | 2022-04-15 | 湖北显源给排水工程设计院有限公司 | Drainage engineering pipeline blocks up early warning system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5490062A (en) * | 1994-05-11 | 1996-02-06 | The Regents Of The University Of California | Real-time neural network earthquake profile predictor |
CN202040552U (en) * | 2010-08-12 | 2011-11-16 | 北京知容寓远软件科技有限公司 | System for monitoring the leakage or obstruction of pipeline base on low frequency sound wave |
CN104373821A (en) * | 2014-11-21 | 2015-02-25 | 天津科技大学 | Natural gas pipeline safety monitoring device based on acoustical science active spurring |
CN105893971A (en) * | 2016-04-01 | 2016-08-24 | 上海理工大学 | Traffic signal lamp recognition method based on Gabor and sparse representation |
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 |
CN107461611A (en) * | 2017-08-24 | 2017-12-12 | 南京邮电大学 | The leakage detection method and leak detecting device being combined based on small echo and EMD reconstruct |
WO2017214031A1 (en) * | 2016-06-06 | 2017-12-14 | Hexagon Technology As | Inline cycle fuse |
CN109034546A (en) * | 2018-06-06 | 2018-12-18 | 北京市燃气集团有限责任公司 | A kind of intelligent Forecasting of city gas Buried Pipeline risk |
CN109063762A (en) * | 2018-07-23 | 2018-12-21 | 昆明理工大学 | A kind of line clogging fault recognition method based on DT-CWT and S4VM |
-
2019
- 2019-02-28 CN CN201910150736.XA patent/CN109827081B/en not_active Expired - Fee Related
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5490062A (en) * | 1994-05-11 | 1996-02-06 | The Regents Of The University Of California | Real-time neural network earthquake profile predictor |
CN202040552U (en) * | 2010-08-12 | 2011-11-16 | 北京知容寓远软件科技有限公司 | System for monitoring the leakage or obstruction of pipeline base on low frequency sound wave |
CN104373821A (en) * | 2014-11-21 | 2015-02-25 | 天津科技大学 | Natural gas pipeline safety monitoring device based on acoustical science active spurring |
CN105893971A (en) * | 2016-04-01 | 2016-08-24 | 上海理工大学 | Traffic signal lamp recognition method based on Gabor and sparse representation |
WO2017214031A1 (en) * | 2016-06-06 | 2017-12-14 | Hexagon Technology As | Inline cycle fuse |
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 |
CN107461611A (en) * | 2017-08-24 | 2017-12-12 | 南京邮电大学 | The leakage detection method and leak detecting device being combined based on small echo and EMD reconstruct |
CN109034546A (en) * | 2018-06-06 | 2018-12-18 | 北京市燃气集团有限责任公司 | A kind of intelligent Forecasting of city gas Buried Pipeline risk |
CN109063762A (en) * | 2018-07-23 | 2018-12-21 | 昆明理工大学 | A kind of line clogging fault recognition method based on DT-CWT and S4VM |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN112198232A (en) * | 2020-09-14 | 2021-01-08 | 昆明理工大学 | Drainage pipeline working condition detection and identification method |
CN113340997A (en) * | 2021-05-11 | 2021-09-03 | 西安交通大学 | Laser shock peening defect online detection method based on acoustic emission dual-channel range |
CN113340997B (en) * | 2021-05-11 | 2024-01-12 | 西安交通大学 | Online detection method for laser shock peening defect based on acoustic emission double-channel range |
CN114136604A (en) * | 2021-11-30 | 2022-03-04 | 三门核电有限公司 | Rotary equipment fault diagnosis method and system based on improved sparse dictionary |
CN114136604B (en) * | 2021-11-30 | 2023-11-28 | 三门核电有限公司 | Rotary equipment fault diagnosis method and system based on improved sparse dictionary |
CN114352946A (en) * | 2022-03-15 | 2022-04-15 | 湖北显源给排水工程设计院有限公司 | Drainage engineering pipeline blocks up early warning system |
CN114352946B (en) * | 2022-03-15 | 2022-06-03 | 湖北显源给排水工程设计院有限公司 | Drainage engineering pipeline blocks up early warning system |
Also Published As
Publication number | Publication date |
---|---|
CN109827081B (en) | 2020-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109827081A (en) | A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting | |
CN104132250B (en) | A kind of pipe leakage characteristic vector pickup method based on improvement wavelet packet | |
CN102606891B (en) | Water leakage detector, water leakage detecting system and water leakage detecting method | |
CN110454687A (en) | A kind of pipeline multipoint leakage localization method based on improvement VMD | |
CN106447040B (en) | Mechanical equipment health state evaluation method based on Heterogeneous Multi-Sensor Data fusion | |
CN107355686B (en) | A kind of detection method of drain line blockage failure | |
CN107218518B (en) | A kind of detection method of the detection device for drain line blockage failure | |
CN105488520A (en) | Multi-resolution singular-spectrum entropy and SVM based leakage acoustic emission signal identification method | |
CN109409308A (en) | A method of the birds species identification based on birdvocalization | |
CN109838696A (en) | Pipeline fault diagnostic method based on convolutional neural networks | |
CN104089699B (en) | A kind of substation equipment speech reconstruction algorithm | |
CN105956526A (en) | Method for identifying a microearthquake event with low signal-to-noise ratio based on multi-scale permutation entropy | |
CN111695465B (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
CN103234121A (en) | Acoustic signal based device and method for detecting gas pipeline leakages | |
CN108444696A (en) | A kind of gearbox fault analysis method | |
CN109668058B (en) | Water supply pipeline leakage identification method based on linear prediction cepstrum coefficient and lyapunov index | |
CN109063762B (en) | Pipeline blockage fault identification method based on DT-CWT and S4VM | |
CN106197650A (en) | A kind of method judging that audio signal is noiseless | |
CN109190272A (en) | Defects of concrete structure detection method based on elastic wave and machine learning | |
CN107355687B (en) | A kind of sewer pipe fault detection method | |
CN103675221A (en) | Water quality detection analysis system and water quality detection analysis method | |
CN110020637A (en) | A kind of analog circuit intermittent fault diagnostic method based on more granularities cascade forest | |
CN115618205A (en) | Portable voiceprint fault detection system and method | |
Li et al. | Non-destructive detection on the egg crack based on wavelet transform | |
CN106596025B (en) | Stability of foundation of fan suspended in road tunnel detection method and system based on impulse response |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201211 |
|
CF01 | Termination of patent right due to non-payment of annual fee |