CN109555977A - The equipment and recognition methods of leak noise measuring - Google Patents
The equipment and recognition methods of leak noise measuring Download PDFInfo
- Publication number
- CN109555977A CN109555977A CN201811410070.9A CN201811410070A CN109555977A CN 109555977 A CN109555977 A CN 109555977A CN 201811410070 A CN201811410070 A CN 201811410070A CN 109555977 A CN109555977 A CN 109555977A
- Authority
- CN
- China
- Prior art keywords
- leak
- classification
- noise information
- leak noise
- predetermined position
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
This application discloses the equipment and recognition methods of a kind of leak noise measuring.Applied to water supply network, wherein the predetermined position of water supply network is correspondingly arranged on noise probe, this method comprises: being popped one's head in by noise, obtains from the collected leak noise information in predetermined position;Using be based on machine learning training pattern, classification leak noise information being determined as in predetermined multiple classifications;And the classification based on leak noise information, determine the predetermined position of the corresponding water supply network of leak noise information with the presence or absence of leak.To solve the technical problem that current leak detecting device is at high cost, complicated for operation and low precision.
Description
Technical field
This application involves intelligent terminal fields, in particular to the equipment and recognition methods of a kind of leak noise measuring.
Background technique
The leakage loss problem of country's water supply network, traditional leak detection mode mostly use passive type scene soil's rigidity at present, main
Differentiate by audition, one of capital equipment of audition is exactly noise meter.Noise meter on the market generally uses at present
Effect is not so good, and cost of layout is high.For example: a noise meter with teletransmission wants more than 3,000 yuan, 1000 family it is small
Area at least needs to arrange 40 to 50 noises probe to accomplish effective monitoring, and cost of layout accumulation at least needs 120,000, and
It does not include the labour cost and other facility expenses included.
For poor, the at high cost problem of above-mentioned noise meter using effect, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides the equipment and recognition methods of a kind of leak noise measuring, at least to solve to leak hunting at present
High, the complicated for operation and low precision technical problem of equipment cost.
According to an aspect of an embodiment of the present invention, a kind of recognition methods of leak noise monitoring is provided, is applied to supply
Pipe network, wherein the predetermined position of water supply network is correspondingly arranged on noise probe, this method comprises: being popped one's head in by noise, obtains
From the collected leak noise information in predetermined position, wherein leak noise information arranges according to the sequence of acquisition time;Benefit
Be based on machine learning training pattern, classification leak noise information being determined as in predetermined multiple classifications;With
And the classification based on leak noise information, determine the predetermined position of the corresponding water supply network of leak noise information with the presence or absence of leakage
Water.
Optionally, model is the LSTM model built under TensorFlow frame.
Optionally, using machine learning training pattern is based on, leak noise information is determined as predetermined multiple classes
The operation of a classification in not, comprising: the characteristic value for extracting leak noise information, by the feature value vector of leak noise information
Change, is converted into the first input data that suitable LSTM model is handled;First input data is input to LSTM model, is utilized
LSTM model classifies to the first input data, and calculates the probability of each classification;And the probability based on each classification, really
Determine the classification of input data.
Optionally, method further includes generating multiple classifications by following operation: being mentioned respectively for multiple leak noise informations
Characteristic value is taken, the feature value vector of multiple leak noise informations is obtained into multiple feature value vector sequences, wherein each feature
It is worth the equal length of sequence vector, and arranges according to the sequence of acquisition time, forms instruction by all feature value vector sequences
Practice sample set;And the LSTM model is trained using training sample set, generate multiple classifications.
Other side according to an embodiment of the present invention additionally provides a kind of equipment of leak noise monitoring, is applied to supply
Pipe network, wherein the predetermined position of water supply network is correspondingly arranged on noise probe, which includes: processor;And memory,
It is connected to the processor, for providing the instruction of processing following steps for processor: being popped one's head in, obtained from pre-determined bit by noise
Set collected leak noise information;Using machine learning training pattern is based on, leak noise information is determined as predefining
Multiple classifications in a classification;And the classification based on leak noise information, determine the corresponding water supply of leak noise information
The predetermined position of pipe network whether there is leak.
Other side according to an embodiment of the present invention additionally provides a kind of equipment of leak noise monitoring, is applied to supply
Pipe network, wherein the predetermined position of water supply network is correspondingly arranged on noise probe, which includes: that leak noise obtains module,
For obtaining from the collected leak noise information in predetermined position;Analysis module is based on machine learning training pattern for utilizing,
Classification leak noise information being determined as in predetermined multiple classifications;Determination module, for being based on leak noise
The classification of information determines the predetermined position of the corresponding water supply network of leak noise information with the presence or absence of leak;And alarm module,
There are leaks in predetermined position for working as the corresponding water supply network of determining leak noise information, then issue alarm signal;Work as determination
Leak is not present in the predetermined position of the corresponding water supply network of leak noise information, then does not issue alarm signal.
Further, what analysis module used is built under TensorFlow frame based on machine learning training pattern
LSTM model.
Further, analysis module includes: to extract characteristic value module, will for extracting the characteristic value of leak noise information
The feature value vector of leak noise information is converted into the first input data that suitable LSTM model is handled;Categorization module,
For the first input data to be input to LSTM model, classified using LSTM model to the first input data, and calculated each
The probability of a classification;And determining module determines the classification of input data for the probability based on each classification.
Further, equipment further includes determining multiple class Modules, wherein determining that multiple class Modules include: to obtain training
Sample set module, for extracting characteristic value for multiple leak noise informations respectively, by the characteristic value of multiple leak noise informations
Vectorization obtains multiple feature value vector sequences, wherein the equal length of each feature value vector sequence, and according to acquisition time
Sequencing arrangement, form training sample set by all feature value vector sequences;And training module, for utilizing training sample
This collection is trained LSTM model, generates multiple classifications.
In embodiments of the present invention, noise information is analyzed using based on machine learning training pattern, and then determined
The corresponding water supply network of noise information whether there is leak, has achieved the purpose that quick judgement leakage point, has realized according to noise
Transmitting file can judge whether the technical effect with leak feature in the recording of information, so solve current leak detecting device at
This height, technical problem complicated for operation and low precision.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 be a kind of terminal of the recognition methods of leak noise monitoring according to the embodiment of the present disclosure 1 (or
Mobile device) hardware block diagram;
Fig. 2 is a kind of flow diagram of the recognition methods of leak noise monitoring according to the embodiment of the present disclosure 1;
Fig. 3 is the schematic diagram of data interaction between the neuron in the LSTM model according to the embodiment of the present disclosure 1;
Fig. 4 is the framework of entire neural network in the LSTM according to the embodiment of the present disclosure 1;
Fig. 5 (a) is the neuron connection before connecting Dropout layers in the LSTM model according to the embodiment of the present disclosure 1
Schematic diagram;
Fig. 5 (b) is the neuron connection after connecting Dropout layers in the LSTM model according to the embodiment of the present disclosure 1
Schematic diagram;
Fig. 6 is the structural schematic diagram of the equipment of leak noise monitoring according to the embodiment of the present disclosure 2;And
Fig. 7 is the structural schematic diagram of the equipment of leak noise monitoring according to the embodiment of the present disclosure 3.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Below
Description only actually at least one exemplary embodiment be it is illustrative, never as to the present invention and its application or make
Any restrictions.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Unless specifically stated otherwise, positioned opposite, the digital table of the component and step that otherwise illustrate in these embodiments
It is not limited the scope of the invention up to formula and numerical value.Simultaneously, it should be appreciated that for ease of description, each portion shown in attached drawing
The size divided not is to draw according to actual proportionate relationship.For technology, side known to person of ordinary skill in the relevant
Method and equipment may be not discussed in detail, but in the appropriate case, and technology, method and apparatus should be considered as authorizing specification
A part.In shown here and discussion all examples, any occurrence should be construed as merely illustratively, rather than
As limitation.Therefore, the other examples of exemplary embodiment can have different values.It should also be noted that similar label and word
Mother indicates similar terms in following attached drawing, therefore, once it is defined in a certain Xiang Yi attached drawing, then in subsequent attached drawing
It does not need that it is further discussed.
Embodiment 1
According to the embodiment of the present disclosure, a kind of embodiment of the recognition methods of leak noise monitoring is provided.It needs to illustrate
It is that step shown in the flowchart of the accompanying drawings can be in the department of computer science of such as one group computer (mobile terminal) executable instruction
Uniting, (mobile terminal system) is middle to be executed, although also, logical order is shown in flow charts, and it in some cases, can
With the steps shown or described are performed in an order that is different from the one herein.
Embodiment of the method provided by the embodiment of the present application can be in mobile terminal, terminal or similar operation
It is executed in device.Fig. 1 shows a kind of terminal device 10 for realizing information processing method (for example, terminal or shifting
Dynamic equipment etc.) hardware block diagram.As shown in Figure 1, terminal device 10 may include it is one or more (in figure using 102a,
102b ... ..., 102n are shown) (processor 102 can include but is not limited to Micro-processor MCV or programmable patrols processor 102
The processing unit of volume device FPGA etc.), memory 104 for storing data and the transmission module for communication function
106.It in addition to this, can also include: display, input/output interface (I/O interface), the port universal serial bus (USB)
(a port that can be used as in the port of I/O interface is included), network interface, power supply and/or camera.The common skill in this field
Art personnel are appreciated that structure shown in FIG. 1 is only to illustrate, and do not cause to limit to the structure of above-mentioned electronic device.For example,
Terminal device 10 may also include than shown in Fig. 1 more perhaps less component or with the configuration different from shown in Fig. 1.
It is to be noted that said one or multiple processors 102 and/or other data processing circuits lead to herein
Can often " data processing circuit " be referred to as.The data processing circuit all or part of can be presented as software, hardware, firmware
Or any other combination.In addition, data processing circuit for single independent processing module or all or part of can be integrated to end
In any one in other elements in end equipment 10.As involved in the embodiment of the present application, the data processing circuit
(such as the selection for the variable resistance end path connecting with interface) is controlled as a kind of processor.
Memory 104 can be used for storing the software program and module of application software, such as the information in the embodiment of the present disclosure
Corresponding program instruction/the data storage device of processing method, the software that processor 102 is stored in memory 104 by operation
Program and module realize the Hole Detection of above-mentioned application program thereby executing various function application and data processing
Method.Memory 104 may include high speed random access memory, may also include nonvolatile memory, such as one or more magnetism
Storage device, flash memory or other non-volatile solid state memories.In some instances, memory 104 can further comprise phase
The memory remotely located for processor 102, these remote memories can pass through network connection to terminal device 10.It is above-mentioned
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of terminal device 10 provide.In an example, transmitting device 106 includes a Network adaptation
Device (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to it is mutual
Networking is communicated.In an example, transmitting device 106 can be radio frequency (Radio Frequency, RF) module, use
In wirelessly being communicated with internet.
Display can such as touch-screen type liquid crystal display (LCD), the liquid crystal display aloow user with
The user interface of terminal device 10 interacts.
Herein it should be noted that in some optional embodiments, above-mentioned terminal device 10 shown in FIG. 1 may include hard
Part element (including circuit), software element (including the computer code that may be stored on the computer-readable medium) or hardware element
With the combination of both software elements.It should be pointed out that Fig. 1 is only an example of particular embodiment, and it is intended to show that
It may be present in the type of the component in above-mentioned terminal device 10.
Under above-mentioned running environment, this application provides a kind of recognition methods of leak noise monitoring.
Refering to what is shown in Fig. 2, a kind of recognition methods of leak noise monitoring of the present embodiment, it should be noted that in attached drawing
The step of process illustrates can execute in a computer system such as a set of computer executable instructions, although also,
Logical order is shown in flow chart, but in some cases, it can be to be different from shown by sequence execution herein or retouch
The step of stating.The method of leak noise testing described in the present embodiment is applied to water supply network, wherein the pre-determined bit of water supply network
It sets and is correspondingly arranged on noise probe, this method comprises:
S202: being popped one's head in by noise, is obtained from the collected leak noise information in predetermined position;
S204: using machine learning training pattern is based on, leak noise information is determined as predetermined multiple classifications
In a classification;And
S206: the classification based on leak noise information determines the predetermined position of the corresponding water supply network of leak noise information
With the presence or absence of leak.
To analyze using based on machine learning training pattern noise information, and then determine that noise information is corresponding
Water supply network whether there is leak, achieved the purpose that quick judgement leakage point, realized in the recording according to noise information
Transmitting file is that can determine whether the technical effect with leak feature, and then solve that current leak detecting device is at high cost, operation is multiple
Miscellaneous and low precision technical problem.
Further, model is the LSTM model built under TensorFlow frame.
Wherein, Fig. 3 shows the schematic diagram of data interaction between the neuron in LSTM model, and Fig. 4 shows whole in LSTM
The framework of a neural network, Fig. 5 (a) and Fig. 5 (b) show Dropout layers in LSTM model of function and effect schematic diagram.?
In the neural network of LSTM model, need to connect dropout when information is transmitted between the same moment multilayer neuron
Layer, illustrates the function and effect of Dropout with reference to shown in Fig. 5, and Fig. 5 (a) is the neural network structure of standard, wherein each white
Circle represents a neuron, and Fig. 5 (b) is the neural network structure connected after Dropout layers, and part of neuron is (i.e.
The circle of built-in "×" in figure) turned off at random, so that Dropout reduces neural computing generation by way of regularization
Over-fitting, therefore the over-fitting that generates when reducing LSTM (shot and long term memory) training data using Dropout in the present embodiment,
To promote the performance of LSTM model.
Further, using machine learning training pattern is based on, leak noise information is determined as predetermined multiple
The operation of a classification in classification, comprising: extract leak noise information characteristic value, by the characteristic value of leak noise information to
Quantization, is converted into the first input data that suitable LSTM model is handled;First input data is input to LSTM model, benefit
Classified with LSTM model to the first input data, and calculates the probability of each classification;And the probability based on each classification,
Determine the classification of input data.
Further, further include that multiple classifications are generated by following operation: being extracted respectively for multiple leak noise informations
The feature value vector of multiple leak noise informations is obtained multiple feature value vector sequences, wherein each characteristic value by characteristic value
The equal length of sequence vector, and arrange according to the sequence of acquisition time, training is formed by all feature value vector sequences
Sample set;And LSTM model is trained using training sample set, generate multiple classifications.
To analyze using based on machine learning training pattern noise information, and then determine that noise information is corresponding
Water supply network whether there is leak, achieved the purpose that quick judgement leakage point, realized in the recording according to noise information
Transmitting file is that can determine whether the technical effect with leak feature, and then solve that current leak detecting device is at high cost, operation is multiple
Miscellaneous and low precision technical problem.
Embodiment 2
With reference to Fig. 6, the embodiment of the present disclosure 2 provides a kind of equipment 60 of leak noise monitoring, is applied to water supply network,
The predetermined position of middle water supply network is correspondingly arranged on noise probe, which includes: processor 602;And memory 601,
It is connect with processor 602, for providing the instruction of processing following steps for processor 602: being popped one's head in, obtained from predetermined by noise
The leak noise information that station acquisition arrives;Using machine learning training pattern is based on, leak noise information is determined as in advance really
A classification in fixed multiple classifications;And the classification based on leak noise information, determine the corresponding confession of leak noise information
The predetermined position of pipe network whether there is leak.
It should be noted that noise probe will be adopted by wireless network (NB-iot, 2G, 3G, 4G, lora) from predetermined position
The leak noise information collected is sent to processor 602.To be popped one's head in by noise, the noise information that collection in worksite arrives is sent
To processor 602, and then complete by the operation of processor 602 judgement to live network of rivers pipeline water leakage situation.
It further, is the LSTM model built under TensorFlow frame based on machine learning training pattern.
Further, processor 602 is also provided using based on machine learning training pattern, and leak noise information is determined as
The instruction of the operation of a classification in predetermined multiple classifications, comprising: the characteristic value for extracting leak noise information will leak
The feature value vector of water noise information is converted into the first input data that suitable LSTM model is handled;By the first input
Data are input to LSTM model, are classified using LSTM model to first input data, and calculate the general of each classification
Rate;And the probability based on each classification, determine the classification of input data.
Further, processor 602 also provides the instruction for generating multiple classifications: mentioning respectively for multiple leak noise informations
Characteristic value is taken, the feature value vector of multiple leak noise informations is obtained into multiple feature value vector sequences, wherein each feature
It is worth the equal length of sequence vector, and arranges according to the sequence of acquisition time, forms instruction by all feature value vector sequences
Practice sample set;And LSTM model is trained using training sample set, generate multiple classifications.
To analyze using based on machine learning training pattern noise information, and then determine that noise information is corresponding
Water supply network whether there is leak, achieved the purpose that quick judgement leakage point, realized in the recording according to noise information
Transmitting file is that can determine whether the technical effect with leak feature, and then solve that current leak detecting device is at high cost, operation is multiple
Miscellaneous and low precision technical problem.
Embodiment 3
With reference to Fig. 7, the embodiment of the present disclosure 3 provides a kind of equipment 70 of leak noise monitoring, is applied to water supply network,
The predetermined position of middle water supply network is correspondingly arranged on noise probe 701, which includes: data transmission module 701, for obtaining
From the collected leak noise information in predetermined position;Analysis module 703, for will leak using machine learning training pattern is based on
Water noise information is determined as a classification in predetermined multiple classifications;Determination module 704, for being believed based on leak noise
The classification of breath determines the predetermined position of the corresponding water supply network of leak noise information with the presence or absence of leak.
Wherein, noise Probe arrangement is in the predetermined position of water supply network in the present embodiment, daily periodically by position
Water pipe noise recorded and be uploaded to analysis module.
It should be noted that noise probe will be adopted by wireless network (NB-iot, 2G, 3G, 4G, lora) from predetermined position
The leak noise information collected is sent to data transmission module 701.To be popped one's head in by noise, the noise that collection in worksite arrives is believed
Breath is sent to data transmission module 701, and then is completed by the operation of the equipment 70 of leak noise monitoring to live network of rivers pipeline
The judgement of water leakage situation.Wherein, the equipment of leak noise monitoring described in the present embodiment is different from the characteristics of prior art:
Noise measuring equipment has been simplified, has only been needed by the way that noise Probe arrangement is obtained network of rivers pipeline at tested point in in-site measurement
Leak noise information transfers to data transmission module 701, analysis to the operation of concrete analysis and the judgement of leak noise information
Module 703 and determination module 704 operate, and wherein data transmission module 701 is periodically received is made an uproar by the leak that noise probe is sent
Acoustic intelligence.The exploitation and simple in equipment of device-dependent program, to substantially reduce the development difficulty and cost of equipment, simultaneously
Also ensure the stability that equipment judges leak noise information.
Further, what analysis module 703 used is to take under TensorFlow frame based on machine learning training pattern
The LSTM model built.
Further, analysis module 703 includes: to extract characteristic value module 7031, for extracting the spy of leak noise information
The feature value vector of leak noise information is converted the first input data that suitable LSTM model is handled by value indicative;Point
Generic module 7032 divides the first input data using LSTM model for the first input data to be input to LSTM model
Class, and calculate the probability of each classification;And determining module 7033 determines input data for the probability based on each classification
Classification.
Further, equipment further includes determining multiple class Modules 702, wherein determining that multiple class Modules include: to obtain
Training sample set module 7021, for extracting characteristic value for multiple leak noise informations respectively, by multiple leak noise informations
Feature value vector obtain multiple feature value vector sequences, wherein the equal length of each feature value vector sequence, and according to
The sequencing of acquisition time arranges, and forms training sample set by all feature value vector sequences;And training module 7022, it uses
In being trained using the training sample set to the LSTM model, the multiple classification is generated.
To analyze using based on machine learning training pattern noise information, and then determine that noise information is corresponding
Water supply network whether there is leak, achieved the purpose that quick judgement leakage point, realized in the recording according to noise information
Transmitting file is that can determine whether the technical effect with leak feature, and then solve that current leak detecting device is at high cost, operation is multiple
Miscellaneous and low precision technical problem.
In the description of the present invention, it is to be understood that, the noun of locality such as " front, rear, top, and bottom, left and right ", " it is laterally, vertical,
Vertically, orientation or positional relationship indicated by level " and " top, bottom " etc. is normally based on orientation or position shown in the drawings and closes
System, is merely for convenience of description of the present invention and simplification of the description, in the absence of explanation to the contrary, these nouns of locality do not indicate that
It must have a particular orientation or be constructed and operated in a specific orientation with the device or element for implying signified, therefore cannot manage
Solution is limiting the scope of the invention;The noun of locality " inside and outside " refers to inside and outside the profile relative to each component itself.
For ease of description, spatially relative term can be used herein, as " ... on ", " ... top ",
" ... upper surface ", " above " etc., for describing such as a device shown in the figure or feature and other devices or spy
The spatial relation of sign.It should be understood that spatially relative term is intended to comprising the orientation in addition to device described in figure
Except different direction in use or operation.For example, being described as if the device in attached drawing is squeezed " in other devices
It will be positioned as " under other devices or construction after part or construction top " or the device of " on other devices or construction "
Side " or " under other devices or construction ".Thus, exemplary term " ... top " may include " ... top " and
" in ... lower section " two kinds of orientation.The device can also be positioned with other different modes and (is rotated by 90 ° or in other orientation), and
And respective explanations are made to the opposite description in space used herein above.
In addition, it should be noted that, limiting components using the words such as " first ", " second ", it is only for be convenient for
Corresponding components are distinguished, do not have Stated otherwise such as, there is no particular meanings for above-mentioned word, therefore should not be understood as to this
The limitation of invention protection scope.
In addition, above-mentioned the embodiment of the present application serial number is for illustration only, do not represent the advantages or disadvantages of the embodiments.In the upper of the application
It states in embodiment, all emphasizes particularly on different fields to the description of each embodiment, there is no the part being described in detail in some embodiment, may refer to it
The associated description of his embodiment.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of recognition methods of leak noise monitoring, which is characterized in that it is applied to water supply network, wherein the water supply network
Predetermined position is correspondingly arranged on noise probe, this method comprises:
It is popped one's head in, is obtained from the collected leak noise information in the predetermined position by the noise;
Using machine learning training pattern is based on, the leak noise information is determined as one in predetermined multiple classifications
A classification;And
Based on the classification of the leak noise information, determine that the predetermined position of the corresponding water supply network of the leak noise information is
It is no that there are leaks.
2. the method according to claim 1, wherein the model is built under TensorFlow frame
LSTM model.
3. according to the method described in claim 2, it is characterized in that, using machine learning training pattern is based on, by the leak
Noise information is determined as the operation of a classification in predetermined multiple classifications, comprising:
The characteristic value for extracting the leak noise information converts the feature value vector of the leak noise information to suitable
The first input data that the LSTM model is handled;
First input data is input to the LSTM model, using the LSTM model to first input data into
Row classification, and calculate the probability of each classification;And
Based on the probability of each classification, the classification of the input data is determined.
4. according to the method described in claim 2, it is characterized in that, the method also includes by following operation, described in generation
Multiple classifications:
Characteristic value is extracted for multiple leak noise informations respectively, the feature value vector of the multiple leak noise information is obtained
To multiple feature value vector sequences, wherein the equal length of each feature value vector sequence, and according to the successive suitable of acquisition time
Sequence arrangement, forms training sample set by all feature value vector sequences;And
The LSTM model is trained using the training sample set, generates the multiple classification.
5. a kind of equipment of leak noise monitoring, which is characterized in that be applied to water supply network, wherein the water supply network is predetermined
Position is correspondingly arranged on noise probe, which includes:
Processor;And
Memory is connected to the processor, for providing the instruction of processing following steps for the processor:
It is popped one's head in, is obtained from the collected leak noise information in the predetermined position by the noise;
Using machine learning training pattern is based on, the leak noise information is determined as one in predetermined multiple classifications
A classification;And
Based on the classification of the leak noise information, determine that the predetermined position of the corresponding water supply network of the leak noise information is
It is no that there are leaks.
6. a kind of equipment of leak noise monitoring, which is characterized in that be applied to water supply network, wherein the water supply network is predetermined
Position is correspondingly arranged on noise probe, which includes:
Leak noise measurement module, for obtaining from the collected leak noise information in the predetermined position;
Analysis module, for the leak noise information being determined as predetermined using machine learning training pattern is based on
A classification in multiple classifications;
Determination module determines the corresponding water supplying pipe of the leak noise information for the classification based on the leak noise information
The predetermined position of net whether there is leak.
7. equipment according to claim 6, which is characterized in that the analysis module used trains mould based on machine learning
Type is the LSTM model built under TensorFlow frame.
8. equipment according to claim 7, which is characterized in that the analysis module includes:
Characteristic value module is extracted, for extracting the characteristic value of the leak noise information, by the feature of the leak noise information
It is worth vectorization, is converted into the first input data for being suitble to the LSTM model to be handled;
Categorization module, for first input data to be input to the LSTM model, using the LSTM model to described
First input data is classified, and calculates the probability of each classification;And
Determining module determines the classification of the input data for the probability based on each classification.
9. equipment according to claim 7, which is characterized in that the equipment further includes determining multiple class Modules, wherein
The multiple class Modules of determination include:
Training sample set module is obtained, for extracting characteristic value for multiple leak noise informations respectively, by the multiple leak
The feature value vector of noise information obtains multiple feature value vector sequences, wherein the length phase of each feature value vector sequence
Deng, and arrange according to the sequence of acquisition time, training sample set is formed by all feature value vector sequences;And
Training module generates the multiple classification for being trained using the training sample set to the LSTM model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811410070.9A CN109555977A (en) | 2018-11-23 | 2018-11-23 | The equipment and recognition methods of leak noise measuring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811410070.9A CN109555977A (en) | 2018-11-23 | 2018-11-23 | The equipment and recognition methods of leak noise measuring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109555977A true CN109555977A (en) | 2019-04-02 |
Family
ID=65867262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811410070.9A Pending CN109555977A (en) | 2018-11-23 | 2018-11-23 | The equipment and recognition methods of leak noise measuring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109555977A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110185939A (en) * | 2019-05-16 | 2019-08-30 | 西北工业大学 | Gas pipe leakage recognition methods based on convolutional neural networks |
CN112634945A (en) * | 2020-12-15 | 2021-04-09 | 浙江和达科技股份有限公司 | Intelligent water leakage sound identification method based on cloud platform |
CN113944888A (en) * | 2021-11-03 | 2022-01-18 | 北京软通智慧科技有限公司 | Gas pipeline leakage detection method, device, equipment and storage medium |
US11854367B1 (en) * | 2017-09-29 | 2023-12-26 | Alarm.Com Incorporated | Detecting events based on the rhythm and flow of a property |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011127546A1 (en) * | 2010-04-15 | 2011-10-20 | Asel-Tech Tecnologia E Automação Ltda. | Integrated system with acoustic technology, mass imbalance and neural network for detecting, locating and quantifying leaks in ducts |
CN102269972A (en) * | 2011-03-29 | 2011-12-07 | 东北大学 | Method and device for compensating pipeline pressure missing data based on genetic neural network |
WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
CN106090630A (en) * | 2016-06-16 | 2016-11-09 | 厦门数析信息科技有限公司 | Fluid pipeline leak hunting method based on integrated classifier and system thereof |
CN106525349A (en) * | 2016-11-18 | 2017-03-22 | 山西中天信科技股份有限公司 | Combustible gas leakage detection method and system |
CN107061996A (en) * | 2017-03-10 | 2017-08-18 | 内蒙古大学 | A kind of water supply line leakage detecting and locating method |
CN107480705A (en) * | 2017-07-24 | 2017-12-15 | 厦门快商通科技股份有限公司 | A kind of running water pipe leakage detection method |
CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
CN107832913A (en) * | 2017-10-11 | 2018-03-23 | 微梦创科网络科技(中国)有限公司 | The Forecasting Methodology and system to monitoring data trend based on deep learning |
CN108488638A (en) * | 2018-03-28 | 2018-09-04 | 东北大学 | Line leakage system and method based on sound wave suction wave hybrid monitoring |
CN108709092A (en) * | 2018-05-28 | 2018-10-26 | 山东省科学院激光研究所 | Line leakage method, apparatus and system |
-
2018
- 2018-11-23 CN CN201811410070.9A patent/CN109555977A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011127546A1 (en) * | 2010-04-15 | 2011-10-20 | Asel-Tech Tecnologia E Automação Ltda. | Integrated system with acoustic technology, mass imbalance and neural network for detecting, locating and quantifying leaks in ducts |
CN102269972A (en) * | 2011-03-29 | 2011-12-07 | 东北大学 | Method and device for compensating pipeline pressure missing data based on genetic neural network |
WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
CN106090630A (en) * | 2016-06-16 | 2016-11-09 | 厦门数析信息科技有限公司 | Fluid pipeline leak hunting method based on integrated classifier and system thereof |
CN106525349A (en) * | 2016-11-18 | 2017-03-22 | 山西中天信科技股份有限公司 | Combustible gas leakage detection method and system |
CN107061996A (en) * | 2017-03-10 | 2017-08-18 | 内蒙古大学 | A kind of water supply line leakage detecting and locating method |
CN107480705A (en) * | 2017-07-24 | 2017-12-15 | 厦门快商通科技股份有限公司 | A kind of running water pipe leakage detection method |
CN107590516A (en) * | 2017-09-16 | 2018-01-16 | 电子科技大学 | Gas pipeline leak detection recognition methods based on Fibre Optical Sensor data mining |
CN107832913A (en) * | 2017-10-11 | 2018-03-23 | 微梦创科网络科技(中国)有限公司 | The Forecasting Methodology and system to monitoring data trend based on deep learning |
CN108488638A (en) * | 2018-03-28 | 2018-09-04 | 东北大学 | Line leakage system and method based on sound wave suction wave hybrid monitoring |
CN108709092A (en) * | 2018-05-28 | 2018-10-26 | 山东省科学院激光研究所 | Line leakage method, apparatus and system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11854367B1 (en) * | 2017-09-29 | 2023-12-26 | Alarm.Com Incorporated | Detecting events based on the rhythm and flow of a property |
CN110185939A (en) * | 2019-05-16 | 2019-08-30 | 西北工业大学 | Gas pipe leakage recognition methods based on convolutional neural networks |
CN112634945A (en) * | 2020-12-15 | 2021-04-09 | 浙江和达科技股份有限公司 | Intelligent water leakage sound identification method based on cloud platform |
CN113944888A (en) * | 2021-11-03 | 2022-01-18 | 北京软通智慧科技有限公司 | Gas pipeline leakage detection method, device, equipment and storage medium |
CN113944888B (en) * | 2021-11-03 | 2023-12-08 | 北京软通智慧科技有限公司 | Gas pipeline leakage detection method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109555977A (en) | The equipment and recognition methods of leak noise measuring | |
Jabbar et al. | An IoT Raspberry Pi-based parking management system for smart campus | |
CN109961009A (en) | Pedestrian detection method, system, device and storage medium based on deep learning | |
CN106092195B (en) | A kind of monitoring water environment system | |
CN102525442B (en) | Method and device for measuring human body pulse | |
CN108896725B (en) | Water quality monitoring method, device, system, computer equipment and storage medium | |
US11249645B2 (en) | Application management method, storage medium, and electronic apparatus | |
CN110110627B (en) | Real-time target detection method for computing resource limitation platform deployment | |
CN108121961A (en) | Inspection Activity recognition method, apparatus, computer equipment and storage medium | |
CN106267774A (en) | Moving state identification method and apparatus | |
CN107273299A (en) | Software testing device, software test platform and method | |
CN109951363A (en) | Data processing method, apparatus and system | |
CN113094325B (en) | Device deployment method, device, computer system and computer readable storage medium | |
CN107729901A (en) | Method for building up, device and the image processing method and system of image processing model | |
CN110233988A (en) | Geological prospecting management system | |
CN108322737A (en) | Image frame per second measurement method and device | |
CN105589801A (en) | Mobile phone cluster test method and system | |
CN110022529A (en) | The method and apparatus of target area demographics based on two kinds of sensing modes | |
CN114707632A (en) | Sensor network sensor fault positioning method, system, equipment and medium | |
CN114449439B (en) | Underground pipe gallery space positioning method and device | |
CN111652168B (en) | Group detection method, device, equipment and storage medium based on artificial intelligence | |
CN109242868A (en) | Image processing method, device, electronic equipment and storage medium | |
CN115112661B (en) | Defect detection method, device, computer equipment and storage medium | |
CN115859161B (en) | Fault prediction method, device, terminal and storage medium | |
CN117146385A (en) | Ventilation system and method based on Internet of things |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |
|
RJ01 | Rejection of invention patent application after publication |