CN110501428A - Trouble-shooter and fault diagnosis system - Google Patents
Trouble-shooter and fault diagnosis system Download PDFInfo
- Publication number
- CN110501428A CN110501428A CN201910925897.1A CN201910925897A CN110501428A CN 110501428 A CN110501428 A CN 110501428A CN 201910925897 A CN201910925897 A CN 201910925897A CN 110501428 A CN110501428 A CN 110501428A
- Authority
- CN
- China
- Prior art keywords
- data
- pressure regulator
- pressure gas
- acoustic emission
- fault diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims description 30
- 238000013527 convolutional neural network Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims 1
- 238000006243 chemical reaction Methods 0.000 abstract description 5
- 239000007789 gas Substances 0.000 description 63
- 230000006870 function Effects 0.000 description 14
- 239000000567 combustion gas Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 206010061245 Internal injury Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013028 emission testing Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Acoustics & Sound (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The disclosure provides a kind of trouble-shooter, for detecting the failure of high-pressure gas pressure regulator, it is characterized in that, the trouble-shooter includes: acoustic emission sensor, it is adsorbed on the pipeline for being connected to the high-pressure gas pressure regulator, and the acoustic emission signal for acquiring the high-pressure gas pressure regulator；Pitot tube is mounted on the pipeline, for acquiring the data on flows in the pipeline；Data collecting card for receiving the acoustic emission signal, and the acoustic emission signal is amplified, is filtered and analog-to-digital conversion, to obtain sound emission data；Data recording field instrument, for data on flows described in timing acquiring；Movable data memory, for being obtained respectively from the data recording field instrument and the data collecting card and storing the sound emission data and the data on flows；Data processing and fault diagnosis host, for judging the failure of the high-pressure gas pressure regulator according to the combination of the sound emission data, the data on flows and pressure.
Description
Technical field
This application involves combustion gas fault diagnosis technology fields, more particularly, to a kind of failure of high-pressure gas pressure regulator
Diagnostic device and fault diagnosis system.
Background technique
High-pressure gas pressure regulator will appear failure in actual use, show as the variation of the gas pressure intensity of its inlet and outlet.
In order to guarantee the operational safety of high-pressure gas pressure regulator, it is necessary to fixed to the real time data acquisition that high-pressure gas pressure regulator generates
Phase processing.
In recent years, acoustic emission is widely used in pipeline or valve leaks etc. because it is highly sensitive with high discrimination power
In low-voltage safety monitoring.High-pressure gas pressure regulator occurs import and export gas pressure intensity when small failure and changes less, but such as
The failures such as crackle, gas leakage can generate abnormal apparent acoustic emission signal in operation, and the spectral range of abnormal signal
It is wide, constrain application of the acoustic emission testing technology in high-voltage regulator detection.
Therefore, it is necessary to a kind of devices of accuracy rate that can be improved fault diagnosis.
Summary of the invention
On the one hand, the disclosure provides a kind of trouble-shooter, for detecting the failure of high-pressure gas pressure regulator, feature
It is, the trouble-shooter includes:
Acoustic emission sensor is adsorbed on the pipeline for being connected to the high-pressure gas pressure regulator, and described for acquiring
The acoustic emission signal of high-pressure gas pressure regulator；
Pitot tube is mounted on the pipeline, for acquiring the data on flows in the pipeline；
Data collecting card for receiving the acoustic emission signal, and the acoustic emission signal is amplified, is filtered and mould
Number conversion, to obtain sound emission data；
Data processing and fault diagnosis host, for according to the sound emission data, the data on flows and the high pressure
The failure of the pressure data that gas pressure regulator, governor is shown combined to judge the high-pressure gas pressure regulator.
In accordance with an embodiment of the present disclosure, the data processing and fault diagnosis host be according to specific data processing algorithm,
The sound emission data are subjected to feature extraction and are merged into assemblage characteristic with the data on flows, the pressure data, and
The failure of the high-pressure gas pressure regulator is judged according to the assemblage characteristic.
In accordance with an embodiment of the present disclosure, the data processing and fault diagnosis host are also structured to utilize wavelet package transforms
Algorithm carries out the feature extraction to extract the energy of wavelet packet coefficient.
In accordance with an embodiment of the present disclosure, 4 layers of wavelet package transforms are carried out to the sound emission data, and calculates 4th layer point
The energy of the wavelet packet coefficient of amount, as characteristics of Acoustic Emission.
In accordance with an embodiment of the present disclosure, the data processing and fault diagnosis host are also structured to special according to the combination
Training neural network is levied, to obtain training pattern, the input of the training pattern is the assemblage characteristic, is exported as fault diagnosis
As a result, wherein the training pattern is obtained by following processing:
Using the assemblage characteristic as input, the output of convolutional neural networks is obtained；
According to the output of convolutional neural networks annotation results corresponding with the assemblage characteristic, the convolution mind is calculated
Loss function through network；
The parameter of the convolutional neural networks is adjusted according to the loss function, until loss function is restrained, is obtained described
Training pattern.
The disclosure also provides a kind of fault diagnosis system characterized by comprising
High-pressure gas pressure regulator is arranged between high-pressure gas pipeline, for detecting the pressure of the high-pressure gas pipeline
Power；
Acoustic emission sensor is adsorbed on the high-pressure gas pipeline, and for acquiring the high-pressure gas pressure regulator
Acoustic emission signal；
Pitot tube is mounted on the high-pressure gas pipeline, for acquiring the flow number in the high-pressure gas pipeline
According to；
Data collecting card for receiving the acoustic emission signal, and the acoustic emission signal is amplified, is filtered and mould
Number conversion, to obtain sound emission data；
Data processing and fault diagnosis host, for according to the sound emission data, the data on flows and the high pressure
The failure of the pressure data of gas pressure regulator, governor detection combined to judge the high-pressure gas pressure regulator.
Detailed description of the invention
Be described in detail exemplary embodiment by referring to accompanying drawing, feature for those of ordinary skill in the art will become it is aobvious and
It is clear to, in which:
Fig. 1 is to be examined according to the high-pressure gas pressure regulator failure based on flow, sound emission and pressure of embodiment of the disclosure
Disconnected apparatus structure.
Specific embodiment
Now with reference to the example embodiment being shown in the accompanying drawings, wherein identical label always shows identical component.
Fig. 1 is the high-pressure gas pressure regulator trouble-shooter based on flow and sound emission according to embodiment of the disclosure
Structure.
Trouble-shooter according to an embodiment of the present disclosure is the trouble-shooter based on flow and sound emission, is used for
Detect the failure of high-pressure gas pressure regulator.In embodiment, trouble-shooter includes acoustic emission sensor 5, Pitot tube 3, number
According to capture card 6, data recording field instrument 4, data processing and fault diagnosis host 8.
In embodiment, high-pressure gas pressure regulator 2 is arranged between high-pressure gas pipeline 1, for detecting high-pressure gas pipe
The pressure in road.Acoustic emission sensor 5 can be adsorbed on high-pressure gas pressure regulator 2, for acquiring the sound of high-pressure gas pressure regulator
Emit signal, and the acoustic emission signal that will test is transferred to data collecting card 6.For example, the frequency response of acoustic emission sensor
Range is 0.1Hz to 15kHz.Analog-digital converter can be set in data collecting card, the acoustic emission signal conversion that will be simulated
For digital signal.Before the acoustic emission signal that will be simulated carries out analog-to-digital conversion, the acoustic emission signal of the simulation can be amplified
And filtering, to improve the signal-to-noise ratio of acoustic emission signal.The resolution ratio of analog-digital converter is 24bit, sample rate 128K/s.Pitot
Pipe 3 is mounted on the high-pressure gas pipeline 1 of 2 side of high-pressure gas pressure regulator, for acquiring the data on flows of high-pressure gas pipeline,
And collected data on flows timing is sent to data recording field instrument 4.Pitot tube is a kind of flowmeter, is only needed during installation
A comparable hole is made a call on the suitable position of pipeline, and its probe is inserted into pipeline center, that is, is convenient to be installed.Finish
The measurement range of trustship is wide, and flow can precise measurement in 0.2t/h~50000t/h.To low flow velocity, small flow, Large Diameter Pipeline
Measurement effect it is further preferred that.
In embodiment, it is additionally provided with memory in data recording field instrument 4 and data collecting card 6, for storing respectively
Acoustic emission signal and data on flows.
In embodiment, trouble-shooter can also include movable data memory 7, for remembering from field data
Data are obtained in record instrument 4 and data collecting card 6, and are stored for further processing.Movable data memory 7 can be by data
Copy to data processing and fault diagnosis host 8.
In accordance with an embodiment of the present disclosure, although it is not shown in the figure, the combustion gas that gas pressure regulator, governor can be detected
The pressure data of pipeline is supplied to data processing and fault diagnosis host 8.
Data processing and fault diagnosis host 8 are according to specific data processing algorithm, after acoustic emission signal is extracted feature
Merge composition assemblage characteristic with flow, pressure data.
In accordance with an embodiment of the present disclosure, data processing and fault diagnosis host 8 are also structured to according to the assemblage characteristic
Training neural network, to obtain training pattern, the input of the training pattern is the assemblage characteristic, is exported as fault type,
Wherein, the training pattern is obtained by following processing:
Using the assemblage characteristic as input, the output of convolutional neural networks is obtained；
According to the output of convolutional neural networks annotation results corresponding with the assemblage characteristic, the convolution mind is calculated
Loss function through network；
The parameter of the convolutional neural networks is adjusted according to the loss function, until loss function is restrained, is obtained described
Training pattern.
It is understood that sound emission can be defined as physical phenomenon, pass through the fast quick-release of the energy in object or material
It puts and generates instantaneous elasticity wave, the deformation or rupture of material are because discharging strain by internal force or external force and in the form of elastic wave
Energy.Acoustic emission is a kind of Dynamic Non-Destruction Measurement method based on acoustic emission phenomenon, for judging the internal injury journey of structure
Degree, is very suitable to long-term real-time device fault detection.Therefore, this step by obtain gas pressure regulator, governor acoustic emission signal come into
Fault detection of the row to gas pressure regulator, governor.
In accordance with an embodiment of the present disclosure, data processing and fault diagnosis host 8 can carry out the acoustic emission signal small
Wave packet transform, and the energy of wavelet packet coefficient is extracted as characteristics of Acoustic Emission.
Wherein, Wavelet Packet Algorithm be a kind of pair of signal extending out from wavelet analysis carry out more careful analysis with
The method of reconstruct, the high frequency section that it can cannot segment wavelet analysis are further decomposed.It is small compared with wavelet transformation
Wave packet transform has higher resolution ratio, can focus on any details of analysis object, extracts more reflection signal characteristics
Information, therefore be widely used in fault diagnosis field.
Specifically, wavelet package transforms are carried out to acoustic emission signal to extract the energy of wavelet packet coefficient as characteristics of Acoustic Emission
When, it can be in the following ways: 4 layers of wavelet package transforms are carried out to acoustic emission signal；Calculate the wavelet packet coefficient of the 4th layer of component
Energy is as characteristics of Acoustic Emission.If this step carries out 4 layers of wavelet package transforms, the wavelet packet of the 4th layer of component to acoustic emission signal
The energy of coefficient can be 8 dimension energy features.
In accordance with an embodiment of the present disclosure, 8 dimension energy features can be merged into 10 dimensional features of composition with pressure, flow.
In accordance with an embodiment of the present disclosure, pressure characteristic (that is, pressure data), the traffic characteristic of gas pressure regulator, governor can be merged
(that is, data on flows) and characteristics of Acoustic Emission, to obtain the assemblage characteristic of gas pressure regulator, governor.It is understood that this step
It can be passed to obtain positioned at combustion gas by transferring outlet pressure historical data, the rate of discharge historical data of combustion gas transmission pipeline
The pressure characteristic and traffic characteristic of gas pressure regulator, governor on defeated pipeline.
Therefore, because assemblage characteristic dimension is more, it is rich in information more abundant, assemblage characteristic can more accurately reflect
The actual state of gas pressure regulator, governor, to realize the purpose that more accurately whether detection gas pressure regulator, governor breaks down.
In accordance with an embodiment of the present disclosure, assemblage characteristic training convolutional neural networks, to obtain gas pressure regulator, governor failure instruction
Practice model.
Wherein, convolutional neural networks are 5 layers, including input layer, convolutional layer, pond layer, full articulamentum and output layer.Its
In, the input layers of convolutional neural networks is for obtaining the input for being input to convolutional neural networks, and convolutional layer is for being inputted
Data carry out feature extraction, pond layer be used for extracted feature progress local sampling, full articulamentum then to sampled result into
Row mapping, output layer export mapping result.For example, can by 10 dimensional features (including pressure characteristic, traffic characteristic and
The characteristics of Acoustic Emission of 8 dimensions) it is input in 5 layers of convolutional neural networks and trains network to differentiate to failure.
Specifically, this step, can be in the following ways when according to assemblage characteristic training convolutional neural networks: will combine
Feature obtains the output of convolutional neural networks as input；According to the output of convolutional neural networks mark corresponding with assemblage characteristic
Note is as a result, calculate the loss function of convolutional neural networks；According to the ginseng for the loss function adjustment convolutional neural networks being calculated
Number, until loss function is restrained, training obtains gas pressure regulator, governor failure training pattern.
That is, the target of this step training convolutional neural networks is so that the loss function of convolutional neural networks is received
It holds back.Wherein, loss function convergence can reach preset threshold for loss function, or this loss function and former losses
The number that difference between function is less than preset threshold is more than preset times, etc..
Wherein, the corresponding annotation results of assemblage characteristic can be, if gas pressure regulator, governor breaks down, corresponding mark knot
Fruit is 0, if gas pressure regulator, governor is without failure, corresponding annotation results are 1.Therefore, training obtains by the above process
Training pattern just can export corresponding numerical value according to the assemblage characteristic inputted, and then can be real according to the numerical value exported
The purpose whether existing accurate judgement gas pressure regulator, governor breaks down.
For example, if the output result of gas pressure regulator, governor failure training pattern is closer to 0, indicate that gas pressure regulator, governor occurs
The probability of failure is bigger, if the output result of gas pressure regulator, governor failure training pattern indicates that normal probability is bigger closer to 1.
It therefore, can be with when judging whether gas pressure regulator, governor breaks down according to gas pressure regulator, governor failure training pattern
In the following ways: obtaining the output result of gas pressure regulator, governor；Acquired output result is compared with preset threshold, if
More than preset threshold, it is determined that gas pressure regulator, governor is without failure, otherwise determines that gas pressure regulator, governor breaks down.
For example, if preset threshold is 0.3, if when the output result of gas pressure regulator, governor failure training pattern is 0.4,
Show that gas pressure regulator, governor is normal, if the output result of gas pressure regulator, governor failure training pattern is 0.2, surface gas pressure regulator, governor goes out
Existing failure.
Therefore, the present invention is special by the obtained combination of flow, pressure and characteristics of Acoustic Emission for merging gas pressure regulator, governor
Sign, Lai Xunlian obtain gas pressure regulator, governor failure training pattern, the gas pressure regulator, governor failure training pattern that training is obtained
Fault detection is carried out according to more abundant information, to effectively solve to detect caused detection mistake using single features
Problem, to improve the accuracy rate of fault detection.
The trouble-shooter can cover the frequency range of the issuable all acoustic emission signals of pressure regulator failure, can
The secure data of high-pressure gas pressure regulator is acquired and handled in real time to realize, the technical functionality diagnosed fault automatically.
Although specifically illustrating and describing present inventive concept referring to the embodiment of present inventive concept, should manage
Solution, without departing from the spirit and scope of the disclosure, can carry out various changes in form and details.
Claims (6)
1. a kind of trouble-shooter, for detecting the failure of high-pressure gas pressure regulator, which is characterized in that the fault diagnosis dress
It sets and includes:
Acoustic emission sensor is adsorbed on the pipeline for being connected to the high-pressure gas pressure regulator, and for acquiring the high pressure
The acoustic emission signal of gas pressure regulator, governor；
Pitot tube is mounted on the pipeline, for acquiring the data on flows in the pipeline；
Data collecting card for receiving the acoustic emission signal, and the acoustic emission signal is amplified, is filtered and modulus turns
It changes, to obtain sound emission data；
Data processing and fault diagnosis host, for according to the sound emission data, the data on flows and the high-pressure gas
The failure of the pressure data that pressure regulator is shown combined to judge the high-pressure gas pressure regulator.
2. trouble-shooter according to claim 1, which is characterized in that the data processing and fault diagnosis host are pressed
According to specific data processing algorithm, by the sound emission data carry out feature extraction and with the data on flows, the number pressure
According to being merged into assemblage characteristic, and the failure of the high-pressure gas pressure regulator is judged according to the assemblage characteristic.
3. trouble-shooter according to claim 2, which is characterized in that the data processing and fault diagnosis host are also
The energy for being configured to extract wavelet packet coefficient using wavelet package transforms algorithm carries out the feature extraction.
4. trouble-shooter according to claim 3, which is characterized in that carry out 4 layers of small echo to the sound emission data
Packet transform, and the energy of the wavelet packet coefficient of the 4th layer of component is calculated, as characteristics of Acoustic Emission.
5. trouble-shooter according to claim 3, which is characterized in that the data processing and fault diagnosis host are also
It is configured to according to assemblage characteristic training neural network, to obtain training pattern, the input of the training pattern is described
Assemblage characteristic exports as fault diagnosis result, wherein the training pattern is obtained by following processing:
Using the assemblage characteristic as input, the output of convolutional neural networks is obtained；
According to the output of convolutional neural networks annotation results corresponding with the assemblage characteristic, the convolutional Neural net is calculated
The loss function of network；
The parameter of the convolutional neural networks is adjusted according to the loss function, until loss function is restrained, obtains the training
Model.
6. a kind of fault diagnosis system characterized by comprising
High-pressure gas pressure regulator is arranged between high-pressure gas pipeline, for detecting the pressure of the high-pressure gas pipeline；
Acoustic emission sensor is adsorbed on the high-pressure gas pipeline, and the sound for acquiring the high-pressure gas pressure regulator
Emit signal；
Pitot tube is mounted on the high-pressure gas pipeline, for acquiring the data on flows in the high-pressure gas pipeline；
Data collecting card for receiving the acoustic emission signal, and the acoustic emission signal is amplified, is filtered and modulus turns
It changes, to obtain sound emission data；
Data processing and fault diagnosis host, for according to the sound emission data, the data on flows and the high-pressure gas
The failure of the pressure data of pressure regulator detection combined to judge the high-pressure gas pressure regulator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910925897.1A CN110501428A (en) | 2019-09-27 | 2019-09-27 | Trouble-shooter and fault diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910925897.1A CN110501428A (en) | 2019-09-27 | 2019-09-27 | Trouble-shooter and fault diagnosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110501428A true CN110501428A (en) | 2019-11-26 |
Family
ID=68593018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910925897.1A Pending CN110501428A (en) | 2019-09-27 | 2019-09-27 | Trouble-shooter and fault diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110501428A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112602562A (en) * | 2020-12-02 | 2021-04-06 | 深圳市农博创新科技有限公司 | Irrigation pipeline fault detection system based on machine learning and intelligent irrigation system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100764092B1 (en) * | 2006-05-03 | 2007-10-09 | 한국원자력연구원 | System and method for monitoring condition of check valve using acoustic emission sensor |
| CN105737912A (en) * | 2016-03-21 | 2016-07-06 | 金洪光 | Pitot type diffusion flow monitor |
| CN207763929U (en) * | 2017-12-06 | 2018-08-24 | 北京市燃气集团有限责任公司 | High-pressure gas pressure regulator failure detector based on sound emission |
| CN211478951U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Fault diagnosis device and fault diagnosis system |
| CN211477587U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Online safety early warning device and fault diagnosis system |
| CN211478167U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Fault diagnosis device and fault diagnosis system |
-
2019
- 2019-09-27 CN CN201910925897.1A patent/CN110501428A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100764092B1 (en) * | 2006-05-03 | 2007-10-09 | 한국원자력연구원 | System and method for monitoring condition of check valve using acoustic emission sensor |
| CN105737912A (en) * | 2016-03-21 | 2016-07-06 | 金洪光 | Pitot type diffusion flow monitor |
| CN207763929U (en) * | 2017-12-06 | 2018-08-24 | 北京市燃气集团有限责任公司 | High-pressure gas pressure regulator failure detector based on sound emission |
| CN211478951U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Fault diagnosis device and fault diagnosis system |
| CN211477587U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Online safety early warning device and fault diagnosis system |
| CN211478167U (en) * | 2019-09-27 | 2020-09-11 | 北京市燃气集团有限责任公司 | Fault diagnosis device and fault diagnosis system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112602562A (en) * | 2020-12-02 | 2021-04-06 | 深圳市农博创新科技有限公司 | Irrigation pipeline fault detection system based on machine learning and intelligent irrigation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100573381C (en) | The diagnostic device that is used for Process Control System | |
| CN107963239A (en) | A kind of booster failure detection device and detection method based on audio | |
| CN106872155B (en) | exhaust valve performance test system and test method | |
| CN107202028B (en) | A kind of turbocharger centrifugal compressor surge recognition methods | |
| CN101208589A (en) | Diagnostic equipment for process control system | |
| CN105842596A (en) | High-sensitivity local defect diagnosis method for power cable | |
| CN104359389A (en) | Pulsed eddy current measuring method for measuring relative wall thickness variable of ferromagnetic component | |
| CN109838696A (en) | Pipeline fault diagnostic method based on convolutional neural networks | |
| CN115451347B (en) | Intelligent monitoring system and method for petroleum pipeline safety | |
| Ma et al. | Negative pressure wave-flow testing gas pipeline leak based on wavelet transform | |
| CN112858845A (en) | Partial discharge diagnosis method for gas insulated switchgear | |
| CN104764564B (en) | Valves leakage detection method based on sonic sensor | |
| CN103032626B (en) | System and method for diagnosing fault of adjusting valve | |
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| CN104316277A (en) | Acoustic detection and blind signal separation-based air tightness monitoring method and apparatus | |
| CN107228740A (en) | Leakage inline diagnosis method in gas valve | |
| CN106368675A (en) | Oil and gas well sand production monitor and sand production monitoring data processing method | |
| CN103267652B (en) | Intelligent online diagnosis method for early failures of equipment | |
| CN110501428A (en) | Trouble-shooter and fault diagnosis system | |
| CN105909979B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
| CN105784918A (en) | In-situ measuring method and device for combustion heat release rate | |
| CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
| CN110186521A (en) | Vortex street moisture based on Wavelet Ridge feature extraction crosses reading compensation and flow-measuring method | |
| CN211478167U (en) | Fault diagnosis device and fault diagnosis system | |
| CN101949772A (en) | Method for measuring pressure reliving rate of pressure reducing valve and detection method of pressure reducing valve |
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 |