CN106525349A - Combustible gas leakage detection method and system - Google Patents
Combustible gas leakage detection method and system Download PDFInfo
- Publication number
- CN106525349A CN106525349A CN201611018683.9A CN201611018683A CN106525349A CN 106525349 A CN106525349 A CN 106525349A CN 201611018683 A CN201611018683 A CN 201611018683A CN 106525349 A CN106525349 A CN 106525349A
- Authority
- CN
- China
- Prior art keywords
- combustible gas
- gas leakage
- acoustic signals
- module
- detected
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention provides a combustible gas leakage detection method and system, for solving the technical problems of low accuracy, application inconvenience, quite high cost and the like by use of a conventional combustible gas leakage detection technology. The combustible gas leakage detection method provided by the invention comprises the following steps: obtaining sound wave signals of a position to be detected; performing noise reduction preprocessing on the obtained sound wave signals; performing feature extraction on the sound wave signals obtained after the preprocessing and outputting feature vectors; and according to the output different feature vectors, automatically detecting a combustible gas leakage state of the position to be detected.
Description
Technical field
The present invention relates to combustible gas leakage detection technique field, and in particular to a kind of combustible gas leakage detection method and
System.
Background technology
In the equipment pipes containing fuel gas such as LNG gas stations, chemical plant, steam power plant, oil plant, steel plant, which connects
Oral area point is easy to leakage due to reasons such as corrosion and ageing, welding qualities in use, and this will cause great Jing
Ji loss and potential safety hazard.
It is existing to be used on the market detecting whether that the device of combustible gas leakage is mainly sensed including catalytic type fuel gas
Device and infrared two class of (laser) combustible gas probe.Wherein, the Cleaning Principle of catalytic type combustible gas sensor is：Combustible gas
When body enters detector, platinum filament surface can be caused to cause oxidation reaction (flameless combustion), its heat for producing makes the temperature of platinum filament
Rising causes the resistivity of platinum filament to change then, then the resistance variations after detecting platinum filament heating can be determined whether there is
Combustible gas leakage and the concentration of leakage.Although catalytic type combustible gas sensor low price, can due to what is revealed
Combustion gas body can volatilize in a short period of time moment, and setting combustible gas sensor carrys out detected gas needs enough concentration,
The accuracy that this allows for its measurement is relatively low.Infrared (laser) combustible gas probe is that have choosing to infrared light using fuel gas
The principle of absorption of selecting property is detecting the combustable gas concentration of site environment.But this kind of device is having finite concentration dust, water
Vapour particle and place is not easy to install faster for particle concentration change, and at present gas station, chemical plant etc. typically all build state in
Around road, ambient dust is big, and this has resulted in the bottleneck that infrared (laser) combustible gas probe is used, and its price also compared with
For costliness.
The content of the invention
In view of this, a kind of combustible gas leakage detection method and system are embodiments provided, is solved existing
Combustible gas leakage technology accuracy is low, using the technical problem such as inconvenient, relatively costly.
A kind of combustible gas leakage detection method that one embodiment of the invention is provided, including：Obtain the sound of position to be detected
Ripple signal；Noise reduction pretreatment is carried out to the acoustic signals of the acquisition；Acoustic signals to obtaining after pretreatment carry out feature and carry
Take, and output characteristic vector；The combustible gas leakage shape of position to be detected is gone out according to the different characteristic vector automatic detection of output
State；
Wherein, the acoustic signals to obtaining after pretreatment carry out feature extraction, and output characteristic vector includes：To institute
Stating pretreated acoustic signals carries out wavelet packet multi-resolution decomposition, obtains the wavelet packet coefficient of each node；To the decomposition
The bottom low frequency coefficient for obtaining and high frequency coefficient carry out wavelet package reconstruction, obtain the reconstruction signal of each frequency band of the bottom；From
Energy is extracted in the reconstruction signal of each frequency band of the bottom, and is exported to detection module as characteristic vector；
Wherein, the wavelet packet multi-resolution decomposition number of plies is 3 to 8 layers；
Wherein, the leak condition of the fuel gas passes through BP neural network training pattern automatic identification；
Wherein, described combustible gas leakage detection method is further included：If detecting position to be detected has combustible gas
When body is leaked, then trigger is sent to alarm module；Trigger is received, report is generated and exported when trigger is received
Alert signal；
Wherein, the acoustic signals for obtaining position to be detected include：Gather the simulation of the acoustic signals of position to be detected
Data；The analog data of the acoustic signals of the collection is converted into into numerical data and pretreatment module is sent to.
A kind of combustible gas leakage detecting system that one embodiment of the invention is provided, including sound transducer, pretreatment mould
Block, characteristic extracting module and detection module, wherein：The sound transducer is used for the acoustic signals for obtaining position to be detected；
The pretreatment module is for carrying out noise reduction pretreatment to the acoustic signals that the sound transducer is obtained；The feature extraction mould
Block for carrying out feature extraction to the pretreated acoustic signals of the pretreatment module, and output characteristic is vectorial；The detection
Module goes out the fuel gas of position to be detected for the different characteristic vector automatic detection exported according to the characteristic extracting module
Leak condition；
Wherein, the characteristic extracting module includes WAVELET PACKET DECOMPOSITION unit, reconfiguration unit and power feature extraction unit,
Wherein：The WAVELET PACKET DECOMPOSITION unit is obtained for carrying out wavelet packet multi-resolution decomposition to the pretreated acoustic signals
The wavelet packet coefficient of each node；The reconfiguration unit is for the bottom low frequency that obtains to the WAVELET PACKET DECOMPOSITION unit decomposition
Coefficient and high frequency coefficient carry out wavelet package reconstruction, obtain the reconstruction signal of each frequency band of the bottom；The power feature extraction list
Unit is for extracting energy from the reconstruction signal of each frequency band of the bottom, and exports as characteristic vector and give detection mould
Block；
Wherein, described combustible gas leakage detecting system, further includes：Alarm module, carrys out Autonomous test for receiving
The trigger that module sends, generates and output alarm signal when trigger is received；The detection module is further wrapped
Signal transmission unit is included, if having combustible gas leakage for detecting position to be detected, is sent to the alarm module and is triggered
Signal；
Wherein, the sound transducer includes collecting unit and AD conversion unit, wherein：The collecting unit is used to adopt
Collect the analog data of the acoustic signals of position to be detected；The AD conversion unit is for the sound wave that gathers the collecting unit
The analog data of signal is converted into numerical data and sends the pretreatment module to.
Combustible gas leakage detection method provided in an embodiment of the present invention and system, the acoustic signals for treating test position are entered
Row WAVELET PACKET DECOMPOSITION, the energy signal for extracting each frequency band of the bottom are input to detection module as characteristic vector, then using instruction
The BP neural network perfected to be input into real time data detect, can accurately judge that out combustible gas leakage species and
Concentration, improves accuracy, and convenient to use, and cost is relatively low.
Description of the drawings
The flow chart that Fig. 1 show a kind of combustible gas leakage detection method of one embodiment of the invention offer.
Fig. 2 show a kind of three layers of decomposition of wavelet packet of combustible gas leakage detection method of one embodiment of the invention offer
Structural representation.
The flow chart that Fig. 3 show a kind of combustible gas leakage detection method of another embodiment of the present invention offer.
Fig. 4 show a kind of structural representation of combustible gas leakage detecting system of one embodiment of the invention offer.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.Based on this
Embodiment in invention, the every other reality obtained under the premise of creative work is not made by those of ordinary skill in the art
Example is applied, the scope of protection of the invention is belonged to.
The Basic Design thinking of this programme is：High pressure fuel gas in leakage process, by pipe joint (leakage hole)
Distinctive acoustic signals can be formed when external eruption, this process can regard acoustic emission phenomenon as.We are using wavelet packet point
Solution method is decomposed to this acoustic emission signal, and using the energy of the bottom obtained after decomposition each frequency band as characteristic vector
Judge whether position to be detected has gas to leak to detect.
The flow chart that Fig. 1 show a kind of combustible gas leakage detection method of one embodiment of the invention offer.Such as Fig. 1 institutes
State, the combustible gas leakage detection method includes：
Step 101：Obtain the acoustic signals of position to be detected.In an embodiment of the present invention, the step 101 is specifically included
The analog data of the acoustic signals of position to be detected is gathered, the analog data of the acoustic signals of collection is converted into into numerical data simultaneously
Send pretreatment module to.
Step 102：Acoustic signals to obtaining carry out noise reduction pretreatment.In an embodiment of the present invention, become using small echo
Change threshold method carries out noise reduction process to acoustic signals, and concrete grammar is by selecting suitable threshold function table, in wavelet transformed domain
The middle noise for removing acoustic signals low amplitude value, then carries out the inverse transformation of wavelet transform, reconstructs the letter of the sound wave after noise reduction
Number.
In an embodiment of the present invention, in the choosing method of threshold function table, using a kind of improved threshold function table method,
Its expression formula is as follows：
Wherein, wj,kFor the wavelet coefficient of kth layer wavelet transformation,It is the wavelet coefficient after threshold process, λ is
The threshold value for being taken.
Because orthogonal wavelet transformation have it is very strong remove data dependence, it can make the energy of signal concentrate on wavelet field
In some big wavelet coefficients, and the energy of noise is distributed in whole wavelet field, and its amplitude is less, so, the above-mentioned small echos of Jing
After conversion, the larger wavelet coefficient of amplitude as much as possible is remained, preferable noise reduction is obtained.
Step 103：Acoustic signals to obtaining after pretreatment carry out feature extraction, and output characteristic vector.This area
Technical staff is appreciated that WAVELET PACKET DECOMPOSITION to the low frequency and radio-frequency component of signal while decomposing, and can realize to signal
Frequency band is evenly dividing, with good time-frequency characteristic, meanwhile, the integrity and orthogonality of wavelet packet obtain can primary signal
It is complete to retain.In an embodiment of the present invention, the step 103 is completed by WAVELET PACKET DECOMPOSITION technology, and detailed process includes as follows：
A. wavelet packet multi-resolution decomposition is carried out to pretreated acoustic signals, obtains the wavelet packet coefficient of each node,
Specifically, the multi-resolution decomposition of acoustic signals is represented by using wavelet packet decomposition：
Wherein, x (t) is sound wave primary signal, di,jT () is j-th node wavelet coefficient in i-th layer, h (k-2t) is low
Reduction of fractions to a common denominator solution filter function, g (k-2t) are high pass resolution filter function.
B. wavelet package reconstruction is carried out to the bottom low frequency coefficient that obtains of decomposition and high frequency coefficient, obtains the bottom each frequency
The reconstruction signal of band.
C. energy is extracted from the reconstruction signal of each frequency band of the bottom, and is exported as characteristic vector and is given detection mould
Block.
In the actual treatment to acoustic signals, the number of plies of WAVELET PACKET DECOMPOSITION can be selected as needed, it is real in the present invention one
Apply in example, the wavelet packet multi-resolution decomposition number of plies is 3 to 8 layers, will not both make amount of calculation excessive, also more can be precisely calculated each
In layer, the energy of different frequency signals concentrates situation.
Fig. 2 show one embodiment of the invention and acoustic signals is carried out with the schematic diagram of 3 layers of WAVELET PACKET DECOMPOSITION.As shown in Fig. 2
S represents primary signal, and L represents low band signal, and H represents high-frequency band signals, and the sequence number number at end represents the number of plies of wavelet decomposition,
That is scale parameter.It is low frequency signal L1 and high-frequency signal H1 by sound signal decomposition in decomposing at the 1st layer, it is then low to the 1st layer
Frequency signal L1 carries out the 2nd layer of decomposition again, is decomposed into relative low frequency signal LL2 and high-frequency signal HL2, in the same manner to the 1st layer
High-frequency signal H1 is also carried out the 2nd layer of decomposition, is decomposed into relative low frequency signal LH2 and high-frequency signal HH2, decomposes by that analogy
3rd layer.Then wavelet package reconstruction is carried out to the 3rd layer of low frequency coefficient and high frequency coefficient respectively, obtains the reconstruction signal of each frequency band
S3j(j=0,1 ..., 7), then the resultant signal after reconstructing is：
S=S30+S31+S32+S33+S34+S35+S36+S37
Again from third layer reconstruction signal S3jMiddle extraction each frequency band LLL3, HLL3, LHL3, HHL3, LLH3, HLH3, LHH3,
The energy of HHH3, if S3jCorresponding energy is E3j, then
Then the gross energy of acoustic signals is：
E=E30+E31+E32+E33+E34+E35+E36+E37
Wherein, N is the length of each split-band, xjkFor reconstruction signal S3jThe amplitude of all discrete points.
Following characteristic vector can be constructed using the energy of above-mentioned each frequency band：
T=[E30,E31,E32,E33,E34,E35,E36,E37]
For the convenience of detection, in an embodiment of the present invention, characteristic vector T is normalized, i.e. E3j'=
E3j/ E, then obtain normalized the feature parameter vectors T ', T '=[E30′,E31′,E32′,E33′,E34′,E35′,E36′,E37'],
Exactly the percentage ratio that the energy of the 3rd layer of each frequency band accounts for signal gross energy is exported to detection module as characteristic vector.
Step 104：The combustible gas leakage state of position to be detected is gone out according to the different characteristic vector automatic detection of output.
In an embodiment of the present invention, the leak condition of fuel gas is carried out automatically by BP neural network training pattern
Identification.Specifically method is：Sample is completed according to above-mentioned steps 101-103 to the leakage acoustic signals of a large amount of known fuel gas first
The extraction of eigen vector, these characteristic vectors is sent in BP neural network as training pattern and is trained, repeatedly anti-
Deconditioning after the accuracy of detection of requirement is practiced and is reached in refreshment, and the model for training is saved, for the inspection of real time data
Survey.Then unknown acoustic signals are completed after above-mentioned steps 101-103, its corresponding characteristic vector is obtained and is sent to training
In good BP neural network, you can the detection of the combustible gas leakage situation for completing to treat test position.
Combustible gas leakage detection method provided in an embodiment of the present invention, the acoustic signals for treating test position carry out small echo
Bag decomposes, the energy signal for extracting each frequency band of the bottom is input to detection module as characteristic vector, then using training
BP neural network to be input into real time data detect, the species and concentration of combustible gas leakage can be accurately judged that out,
Accuracy is improve, while more convenient quick.
As shown in figure 3, in an embodiment of the present invention, the combustible gas leakage detection method is further included：
Step 201：If when detecting position to be detected and having combustible gas leakage, sending trigger to alarm module.
Step 202：Trigger is received, is generated and output alarm signal when trigger is received.
Wherein, alarm signal can be the specific character signal and/or acoustical signal for pre-setting, through above-mentioned steps
104 characteristic vectors that identified are different, and the alarm signal for being generated is also different, for example, leak when having identified carbon monoxide
When, the word alarm signal which generates can be " carbon monoxide leakage alarm ", and corresponding audible ringing signal can be continuous two sound
Ring；When having identified that methane gas is leaked, its generate word alarm signal can be " methane oxidizing archaea warning ", corresponding sound
Sound alarm signal can be continuous three sound ring.In addition, alarm signal can also according to gas leak concentration difference be divided into slightly, in
The different grades of alarm signal such as degree and severe leakage, such staff just can be adopted according to the prompting of different alarm in time
Corresponding safety measure is taken, the generation of poisoning, fire or explosive incident is prevented, so as to ensure the safety of monitoring scene.
Fig. 4 show a kind of structural representation of combustible gas leakage detecting system of one embodiment of the invention offer.Such as
Shown in Fig. 4, the combustible gas leakage detecting system include sound transducer 10, pretreatment module 20, characteristic extracting module 30 with
And detection module 40.
Sound transducer 10 is used for the acoustic signals of the position to be detected for obtaining inflammable gas pipeline.Implement in the present invention one
In example, the sound transducer 10 specifically includes collecting unit 11 and AD conversion unit 12, wherein, collecting unit 11 is used to gather
The analog data of the acoustic signals of position to be detected, AD conversion unit 12 is for the acoustic signals that gather collecting unit 11
Analog data is converted into numerical data and sends pretreatment module 20 to.Certainly, above-mentioned AD conversion unit 12 is except collecting
Into in sound transducer 10, also can be connected with sound transducer 10 and pretreatment module 20, sound transducer 10 is detected
To the analog data of acoustical signal be converted into numerical data and be re-fed into pretreatment module 20 being processed, the present invention turns to modulus
The position for changing unit 12 is not specifically limited.
Pretreatment module 20 for carrying out noise reduction pretreatment to the acoustic signals that sound transducer 10 is obtained, the present invention one
In embodiment, pretreatment module 20 carries out noise reduction process to acoustic signals using Wavelet Transform Threshold method.It is suitable by selecting
Threshold function table, removes the noise of acoustic signals low amplitude value in wavelet transformed domain, then carries out the inverse transformation of wavelet transform,
Reconstruct the acoustic signals after noise reduction.
Characteristic extracting module 30 for carrying out feature extraction to pretreated acoustic signals, and output characteristic is vectorial.
In one embodiment of the invention, this feature extraction module 30 specifically includes WAVELET PACKET DECOMPOSITION unit 31, reconfiguration unit 32 and energy
Feature extraction unit 33, wherein, WAVELET PACKET DECOMPOSITION unit 31 is multiple dimensioned for carrying out wavelet packet to pretreated acoustic signals
Decompose, obtain the wavelet packet coefficient of each node, reconfiguration unit 32 is for decomposing the most bottom for obtaining to WAVELET PACKET DECOMPOSITION unit 31
Layer low frequency coefficient and high frequency coefficient carry out wavelet package reconstruction, obtain the reconstruction signal of each frequency band of the bottom, power feature extraction
Unit 33 extracts energy in the reconstruction signal for the bottom each frequency band obtained from the reconstruct of reconfiguration unit 32, and as
Characteristic vector is exported to detection module 40.
Detection module 40 goes out location to be checked for the different characteristic vector automatic detection exported according to characteristic extracting module 30
The combustible gas leakage state put.In an embodiment of the present invention, detection module 40 by BP neural network training pattern to can
The leak condition of combustion gas body carries out automatic identification, and its specific recognition methods is as it was previously stated, will not be described here.
In an embodiment of the present invention, the combustible gas leakage detecting system further includes alarm module, detection module
40 further include signal transmission unit, if having combustible gas leakage for detecting position to be detected, send out to alarm module
Trigger is sent, is easy to staff to take safety measures in time, prevent the generation of poisoning, fire or explosive incident, so as to
Ensure the safety of monitoring scene.
Combustible gas leakage detecting system provided in an embodiment of the present invention, the acoustic signals that sound transducer is obtained are through pre-
After processing module noise reduction process, characteristic extracting module is transferred to, through small echo of the characteristic extracting module to acoustic signals to be detected
After bag decomposes, the energy signal of each frequency band of the extraction bottom is input to detection module as characteristic vector and is detected, Neng Goujing
Really judge the species and concentration of combustible gas leakage, improve accuracy, easy to use, cost is relatively low.
Although it will be understood by those skilled in the art that above example describes some of combustible gas leakage detecting system
Module, but this division is not enforceable.In fact, according to the embodiment of the present invention, above-described two or
The feature and function of more multimode can be embodied in a module.Conversely, the feature and work(of an above-described module
Can be able to be to be embodied by multiple modules with Further Division.
It will be understood by those skilled in the art that technical scheme can be realized with software, specifically, can be with
It is that the mode of computer program is realized.Such as, in similar RAM, ROM, hard disk and/or any appropriate storage medium, storage can
Code is performed, when the executable code is performed, it is possible to achieve the function that above example of the present invention is referred to.In addition, this
Bright embodiment can also pass through being implemented in combination in for hardware or software and hardware.Hardware components can be patrolled using special
Collect to realize；Software section can be stored in memory, by appropriate instruction execution system, such as microprocessor or special
Design hardware to perform.It will be understood by those skilled in the art that above-mentioned device can use computer executable instructions
And/or be included in processor control routine to realize, such as in the such as mounting medium of disk, CD or DVD-ROM, such as only
This is provided in the data medium of the programmable memory or such as optics or electrical signal carrier of reading memorizer (firmware)
The code of sample.The present invention device and its module can by such as super large-scale integration OR gate array, such as logic chip,
The programmable hardware device of the quasiconductor or field programmable gate array of transistor etc., programmable logic device etc.
Hardware circuit is realized, it is also possible to realized with the software by various types of computing devices, it is also possible to by above-mentioned hardware circuit and
The combination of software such as firmware is realizing.For example, when the fuel gas detecting system provided by the embodiment of the present invention passes through hardware
When realizing, AD conversion unit 12 can be an AD7893 chip, and alarm module 70 can be the electricity of commercially available representative warning message
Subsignal relay-set.
Presently preferred embodiments of the present invention is the foregoing is only, not to limit the present invention, all essences in the present invention
Within god and principle, any modification for being made, equivalent etc. should be included within the scope of the present invention.
Claims (10)
1. a kind of combustible gas leakage detection method, it is characterised in that include：
Obtain the acoustic signals of position to be detected；
Noise reduction pretreatment is carried out to the acoustic signals of the acquisition；
Acoustic signals to obtaining after pretreatment carry out feature extraction, and output characteristic vector；
The combustible gas leakage state of position to be detected is gone out according to the different characteristic vector automatic detection of output.
2. combustible gas leakage detection method according to claim 1, it is characterised in that described to obtaining after pretreatment
Acoustic signals carry out feature extraction, and output characteristic vector includes：
Wavelet packet multi-resolution decomposition is carried out to the pretreated acoustic signals, the wavelet packet coefficient of each node is obtained；
Wavelet package reconstruction is carried out to the bottom low frequency coefficient that obtains and high frequency coefficient of decomposing, the bottom each frequency band is obtained
Reconstruction signal；
Extract energy from the reconstruction signal of each frequency band of the bottom, and export as characteristic vector and give detection mould
Block.
3. combustible gas leakage detection method according to claim 2, it is characterised in that the wavelet packet multi-resolution decomposition
The number of plies is 3 to 8 layers.
4. combustible gas leakage detection method according to claim 1, it is characterised in that the leakage shape of the fuel gas
State passes through BP neural network training pattern automatic identification.
5. combustible gas leakage detection method according to claim 1, it is characterised in that further include：
If when detecting position to be detected and having combustible gas leakage, sending trigger to alarm module；
Trigger is received, is generated and output alarm signal when trigger is received.
6. combustible gas leakage detection method according to claim 1, it is characterised in that acquisition position to be detected
Acoustic signals include：
Gather the analog data of the acoustic signals of position to be detected；
The analog data of the acoustic signals of the collection is converted into into numerical data and pretreatment module is sent to.
7. a kind of combustible gas leakage detecting system, it is characterised in that including sound transducer, pretreatment module, feature extraction
Module and detection module, wherein：
The sound transducer is used for the acoustic signals for obtaining position to be detected；
The pretreatment module is for carrying out noise reduction pretreatment to the acoustic signals that the sound transducer is obtained；
The characteristic extracting module is for carrying out feature extraction to the pretreated acoustic signals of the pretreatment module, and exports
Characteristic vector；
The detection module goes out location to be checked for the different characteristic vector automatic detection exported according to the characteristic extracting module
The combustible gas leakage state put.
8. combustible gas leakage detecting system according to claim 7, it is characterised in that the characteristic extracting module includes
WAVELET PACKET DECOMPOSITION unit, reconfiguration unit and power feature extraction unit, wherein：
The WAVELET PACKET DECOMPOSITION unit obtains each for carrying out wavelet packet multi-resolution decomposition to the pretreated acoustic signals
The wavelet packet coefficient of individual node；
The reconfiguration unit enters for the bottom low frequency coefficient that obtains to the WAVELET PACKET DECOMPOSITION unit decomposition and high frequency coefficient
Row wavelet package reconstruction, obtains the reconstruction signal of each frequency band of the bottom；
The power feature extraction unit is for extracting energy from the reconstruction signal of each frequency band of the bottom, and is made
It is characterized vector to export to detection module.
9. combustible gas leakage detecting system according to claim 7, it is characterised in that further include：
Alarm module, for receiving the trigger for coming that self-detection module sends, generates when trigger is received and exports
Alarm signal；
The detection module further includes signal transmission unit, if having combustible gas leakage for detecting position to be detected,
Then trigger is sent to the alarm module.
10. video monitoring system according to claim 7, it is characterised in that the sound transducer includes collecting unit
And AD conversion unit, wherein：
The collecting unit is used for the analog data of the acoustic signals for gathering position to be detected；
The analog data of acoustic signals of the AD conversion unit for the collecting unit is gathered is converted into numerical data
And send the pretreatment module to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611018683.9A CN106525349A (en) | 2016-11-18 | 2016-11-18 | Combustible gas leakage detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611018683.9A CN106525349A (en) | 2016-11-18 | 2016-11-18 | Combustible gas leakage detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106525349A true CN106525349A (en) | 2017-03-22 |
Family
ID=58352936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611018683.9A Pending CN106525349A (en) | 2016-11-18 | 2016-11-18 | Combustible gas leakage detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106525349A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108361559A (en) * | 2018-02-27 | 2018-08-03 | 中煤科工集团重庆研究院有限公司 | Method for improving sound wave leakage detection accuracy of coal mine gas extraction pipe network |
| CN108361560A (en) * | 2018-03-21 | 2018-08-03 | 天津科技大学 | A kind of pipe safety recognition methods being used for natural gas line safety monitoring assembly based on wavelet packet |
| CN109555977A (en) * | 2018-11-23 | 2019-04-02 | 水联网技术服务中心（北京）有限公司 | The equipment and recognition methods of leak noise measuring |
| CN110398320A (en) * | 2019-07-09 | 2019-11-01 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection localization method and system being easy to Continuous optimization |
| CN111022941A (en) * | 2019-12-27 | 2020-04-17 | 重庆科技学院 | Natural gas pipeline leakage detection method based on LSTM recurrent neural network |
| CN111351618A (en) * | 2018-12-21 | 2020-06-30 | 北京新联铁集团股份有限公司 | Air tightness detection method and system for rail transit rolling stock |
| CN114838201A (en) * | 2022-04-26 | 2022-08-02 | 高川 | Underground gas pipeline detecting and positioning system |
| CN115824519A (en) * | 2023-02-14 | 2023-03-21 | 中国海洋大学 | Valve leakage fault comprehensive diagnosis method based on multi-sensor information fusion |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6389881B1 (en) * | 1999-05-27 | 2002-05-21 | Acoustic Systems, Inc. | Method and apparatus for pattern match filtering for real time acoustic pipeline leak detection and location |
| CN101539241A (en) * | 2009-05-07 | 2009-09-23 | 北京航空航天大学 | Hierarchical multi-source data fusion method for pipeline linkage monitoring network |
| CN102563361A (en) * | 2012-01-18 | 2012-07-11 | 中国石油大学(华东) | Device and method for detecting and positioning leakage of gas transmission pipeline based on conventional data and sound wave signals |
| CN105864643A (en) * | 2016-03-24 | 2016-08-17 | 华北电力大学 | Gas pipeline leakage positioning experimental device and method based on RBF neural network |
| CN106090628A (en) * | 2016-06-14 | 2016-11-09 | 东莞市联洲知识产权运营管理有限公司 | A kind of gas pipe leakage location test system and localization method thereof |
-
2016
- 2016-11-18 CN CN201611018683.9A patent/CN106525349A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6389881B1 (en) * | 1999-05-27 | 2002-05-21 | Acoustic Systems, Inc. | Method and apparatus for pattern match filtering for real time acoustic pipeline leak detection and location |
| CN101539241A (en) * | 2009-05-07 | 2009-09-23 | 北京航空航天大学 | Hierarchical multi-source data fusion method for pipeline linkage monitoring network |
| CN102563361A (en) * | 2012-01-18 | 2012-07-11 | 中国石油大学(华东) | Device and method for detecting and positioning leakage of gas transmission pipeline based on conventional data and sound wave signals |
| CN105864643A (en) * | 2016-03-24 | 2016-08-17 | 华北电力大学 | Gas pipeline leakage positioning experimental device and method based on RBF neural network |
| CN106090628A (en) * | 2016-06-14 | 2016-11-09 | 东莞市联洲知识产权运营管理有限公司 | A kind of gas pipe leakage location test system and localization method thereof |
Non-Patent Citations (9)
| Title |
|---|
| 姚德臣: "《轨道交通轴承故障诊断技术》", 31 March 2017, 中国铁道出版社 * |
| 崔谦 等: "多尺度相关分析在管道泄漏检测中的应用", 《电子测量与仪器学报》 * |
| 杨宏宇: "基于小波分析与BP神经网络的管道泄漏诊断方法的研究", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
| 梁红涛: "《最新化工生产工艺设计与化工产品检测技术手册（下卷）》", 31 March 2004, 银声音像出版社 * |
| 王永红 等: "基于小波分析的气体泄漏检测", 《检测与计量》 * |
| 王立坤 等: "基于神经网络的管道泄漏声波信号特征识别", 《仪器仪表学报》 * |
| 王致杰 等: "《大型风力发电机组状态监测与智能故障诊断》", 30 September 2013, 上海交通大学出版社 * |
| 裴峻峰 等: "《机械故障诊断技术第2版》", 30 September 2010, 中国石油大学出版社 * |
| 赵银善 等: "一种改进的小波阈值函数去噪方法", 《计算机工程与应用》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108361559A (en) * | 2018-02-27 | 2018-08-03 | 中煤科工集团重庆研究院有限公司 | Method for improving sound wave leakage detection accuracy of coal mine gas extraction pipe network |
| CN108361559B (en) * | 2018-02-27 | 2019-06-14 | 中煤科工集团重庆研究院有限公司 | Method for improving sound wave leakage detection accuracy of coal mine gas extraction pipe network |
| CN108361560A (en) * | 2018-03-21 | 2018-08-03 | 天津科技大学 | A kind of pipe safety recognition methods being used for natural gas line safety monitoring assembly based on wavelet packet |
| CN109555977A (en) * | 2018-11-23 | 2019-04-02 | 水联网技术服务中心（北京）有限公司 | The equipment and recognition methods of leak noise measuring |
| CN111351618A (en) * | 2018-12-21 | 2020-06-30 | 北京新联铁集团股份有限公司 | Air tightness detection method and system for rail transit rolling stock |
| CN110398320A (en) * | 2019-07-09 | 2019-11-01 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection localization method and system being easy to Continuous optimization |
| CN110398320B (en) * | 2019-07-09 | 2020-11-20 | 北京讯腾智慧科技股份有限公司 | Gas leakage detection positioning method and system easy for continuous optimization |
| CN111022941A (en) * | 2019-12-27 | 2020-04-17 | 重庆科技学院 | Natural gas pipeline leakage detection method based on LSTM recurrent neural network |
| CN111022941B (en) * | 2019-12-27 | 2021-05-28 | 重庆科技学院 | Natural gas pipeline leakage detection method based on LSTM recurrent neural network |
| CN114838201A (en) * | 2022-04-26 | 2022-08-02 | 高川 | Underground gas pipeline detecting and positioning system |
| CN115824519A (en) * | 2023-02-14 | 2023-03-21 | 中国海洋大学 | Valve leakage fault comprehensive diagnosis method based on multi-sensor information fusion |
| CN115824519B (en) * | 2023-02-14 | 2023-05-12 | 中国海洋大学 | Comprehensive diagnosis method for valve leakage faults based on multi-sensor information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106525349A (en) | Combustible gas leakage detection method and system | |
| CN100567978C (en) | The supersonic phased array for detecting oil gas pipeline girth weld defect type automatic identifying method | |
| CN110751073A (en) | Pipeline early damage mode identification method based on distributed optical fiber sensing and deep learning | |
| CN103439631B (en) | Ground net corrosion condition detection method and system | |
| CN103064008B (en) | A kind of Nolinear analog circuit soft fault diagnostic method based on Hilbert-Huang transform | |
| CN112013286B (en) | Method and device for positioning pipeline leakage point, storage medium and terminal | |
| CN109649432B (en) | System and method for monitoring integrity of steel rail of cloud platform based on guided wave technology | |
| CN107435817A (en) | A kind of 2 leak detection accurate positioning methods of pressure pipeline | |
| Mei et al. | Adaptive signal enhancement based on improved VMD-SVD for leak location in water-supply pipeline | |
| Wang et al. | Pipeline leak detection method based on acoustic-pressure information fusion | |
| CN111695465A (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
| CN109827081B (en) | Buried drainage pipeline blocking fault and pipeline tee part diagnosis method based on acoustic active detection | |
| CN106291281A (en) | A kind of substation equipment shelf depreciation alignment system and method thereof | |
| CN109063762B (en) | Pipeline blockage fault identification method based on DT-CWT and S4VM | |
| CN105488520A (en) | Multi-resolution singular-spectrum entropy and SVM based leakage acoustic emission signal identification method | |
| CN107218518A (en) | A kind of detection method of detection means for drain line blockage failure | |
| CN107917341A (en) | Oil pipeline leakage detection method and device | |
| CN111486345A (en) | Grain depot underground pipe network liquid leakage on-line monitoring and early warning method and device | |
| Ma et al. | Early fault diagnosis of shaft crack based on double optimization maximum correlated kurtosis deconvolution and variational mode decomposition | |
| CN105092691B (en) | A kind of quantitative detecting method and detector of the accumulation of pipeline internal oxidition skin | |
| CN204269770U (en) | A kind of chip security detection system | |
| Chen et al. | Pipeline leak AE signal denoising based on improved SSA-K-α index-VMD-MD | |
| CN105909979A (en) | Leakage acoustic wave feature extraction method based on fusion of wavelet transform and blind source separation algorithm | |
| CN106093181A (en) | Parameter of magnetic characteristic, magnetic Barkhausen, magnetosonic launch detection method and device | |
| CN105135217A (en) | Modified petroleum pipeline leak detecting method based on wavelet analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |