CN110321585A - Based on GA-BP neural network switchgear method for detecting insulation defect and system - Google Patents
Based on GA-BP neural network switchgear method for detecting insulation defect and system Download PDFInfo
- Publication number
- CN110321585A CN110321585A CN201910281121.0A CN201910281121A CN110321585A CN 110321585 A CN110321585 A CN 110321585A CN 201910281121 A CN201910281121 A CN 201910281121A CN 110321585 A CN110321585 A CN 110321585A
- Authority
- CN
- China
- Prior art keywords
- switch cabinet
- air switch
- neural network
- insulation defect
- defect
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 117
- 238000009413 insulation Methods 0.000 title claims abstract description 87
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000007789 gas Substances 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 24
- 239000002184 metal Substances 0.000 claims description 11
- 229910052751 metal Inorganic materials 0.000 claims description 11
- 239000012212 insulator Substances 0.000 claims description 10
- 239000007787 solid Substances 0.000 claims description 6
- 239000002923 metal particle Substances 0.000 claims description 4
- 239000011800 void material Substances 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010292 electrical insulation Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 208000013935 Electric injury Diseases 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Gas-Insulated Switchgears (AREA)
Abstract
The invention discloses one kind to be based on GA-BP neural network switchgear method for detecting insulation defect and system, the switchgear is air switch cabinet, this method comprises the following steps: establishing training dataset, the training dataset include work normally when air switch cabinet in gaseous species and content data, and under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；Construct GA-BP neural network model；GA-BP neural network model is trained using the training dataset, obtains the identification model with identification air switch cabinet insulation defect function；Periodically measure air switch cabinet composition of gases within to be detected and content；It is identified using gas componant and content of the identification model to measurement, and exports recognition result.Method provided by the invention can be to avoid extraneous interference, to improve accuracy rate.
Description
Technical field
The present invention relates to technical field of electric equipment, and in particular to one kind is lacked based on the insulation of GA-BP neural network switchgear
Fall into detection method and system.
Background technique
Switchgear is matched as the important of user that be directly facing of route folding, power equipment control and protection in electric system
Electric equipment, safe operation will directly affect the reliability of customer power supply.Metal device in switchgear is in manufacture assembling process
In caused by or operation in the insulation defect that generates, can cause that shelf depreciation occurs in switchgear.Switchgear is in longtime running
Insulation degradation can be caused in turn result in electrical insulation strength reduction because of shelf depreciation under state, it, will be right if causing power outage
People's production and living cause huge economic loss.
Currently, being passed through by the discharge signal that ultrasonic Detection Method detects air switch cabinet interior insulation defect
Dielectric decaying is serious, and recognition efficiency is lower, and sensitivity is poor；Transient state voltage-to-ground TEV detection method is larger in background interference
When judge that state of insulation accuracy is lower；Pulse current detection method anti-interference ability is poor；Conventional method is opened in detection air
Close the limitation all existed in cabinet built-in electrical insulation defect in varying degrees.
Summary of the invention
In view of the deficiencies in the prior art, the purpose of the present invention is to provide one kind is opened based on GA-BP neural network
Cabinet method for detecting insulation defect and system are closed, the interference of ambient atmos is avoided, to improve accuracy rate.
To achieve the above objectives, the technical solution adopted by the present invention is that: one kind based on GA-BP neural network switchgear insulate
Defect inspection method, the switchgear are air switch cabinet, are included the following steps:
Establish training dataset, the training dataset includes gaseous species and content in air switch cabinet when working normally
Data, and under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；
Construct GA-BP neural network model；
GA-BP neural network model is trained using the training dataset, obtains that there is identification air switch cabinet
The identification model of insulation defect function；
Periodically measure air switch cabinet composition of gases within to be detected and content；
It is identified using gas componant and content of the identification model to measurement, and exports recognition result.
Further, the detection method further includes following steps:
Insulation defect recording device is provided, the insulation defect recording device is connect with identification model；
The insulation defect recording device is successively to continuously recognition result judges twice, if continuously identifying twice
It as a result is same insulation defect type, then the insulation defect recording device records judging result；Otherwise, without record.
Further, the different insulative defect type include solid metal protrusion defect, insulator void defects,
Insulator surface metal filth defect and free metal particle defects.
Further, the gaseous species include CO, NO2And NO gas.
Further, the GA-BP neural network model includes input layer, hidden layer and output layer, the input layer packet
M input node is included, M is equal with the number of gaseous species；The output layer includes N+1 output node, N and insulation defect
Type number is equal.
Further, the measurement period T of the gas sensor meets: 2h≤T≤4h.
Further, gas sensor is provided, the gas sensor is connect with identification model；
The gas sensor is installed in air switch cabinet to be detected, which is measured by the gas sensor
Air cock cabinet composition of gases within and content.
The present invention also provides one kind to be based on GA-BP neural network switchgear insulation defect detection system, the switchgear
For air switch cabinet comprising:
Data reception module is used to receive air switch cabinet composition of gases within to be detected and content data；
Identification model is trained to obtain using training dataset to GA-BP neural network model, and the trained number
Include gaseous species and content data in air switch cabinet when working normally according to collection, and occurs under different insulative defect type
Gaseous species and content data in air switch cabinet when shelf depreciation；The identification model is according to the received number of data reception module
According to the insulation defect type for identifying air switch cabinet to be detected；
Output module is used to export recognition result.
The present invention also provides one kind to be based on GA-BP neural network switchgear insulation defect detection system, the switchgear
For air switch cabinet comprising:
Data collector is used to acquire air switch cabinet composition of gases within to be detected and content data；
Neural network server is preset with identification model, and the identification model is using training dataset to GA-BP nerve
Network model is trained to obtain, the training dataset include work normally when air switch cabinet in gaseous species and content number
According to, and under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；It is described
The neural network server data that collector acquires for receiving data simultaneously identify air switch cabinet to be detected according to the data
Insulation defect type, and export recognition result.
Further, the detection system further includes insulation defect recording device, and the insulation defect recording device is used for
Successively to continuously recognition result judges twice, if continuously recognition result is same insulation defect type twice for this,
The then insulation defect recording device records judging result；Otherwise, without record.
Compared with the prior art, the advantages of the present invention are as follows:
(1) present invention acquires corresponding training dataset, is instructed by training dataset to GA-BP neural network model
Practice, to obtain the identification model that can identify air switch cabinet insulation defect function, then measures air switch cabinet to be detected
Gas componant and content data, identified by identification model.What the present invention acquired is the gas in air switch cabinet, is kept away
Exempt from the interference of ambient atmos, to improve accuracy rate.
(2) present invention by insulation defect recording device successively to continuously recognition result judges twice, when continuous
Recognition result twice be same insulation defect type, just think that the air switch cabinet is implicitly present in insulation defect, insulation lacks
Fall into recording device records judging result；Otherwise, it is believed that shelf depreciation is to be caused by other reasons, and extinguished, at this time
Without record, it is believed that the air switch cabinet is in normal operating condition, thus the case where reducing wrong report.Service personnel passes through note
The judging result of record will appreciate that insulation defect information that may be present in switchgear and solve existing security risk, reduction office
Switchgear tripping times caused by portion discharges, it is ensured that shelf depreciation caused by by insulation defect does not endanger switchgear, guarantees switch
The safe operation of cabinet safety and stability, power supply reliability and power grid.
Detailed description of the invention
Fig. 1 is provided in an embodiment of the present invention based on GA-BP neural network switchgear method for detecting insulation defect flow chart；
Fig. 2 is provided by one embodiment of the present invention based on GA-BP neural network switchgear insulation defect detection system frame
Figure；
Fig. 3 be another embodiment of the present invention provide based on GA-BP neural network switchgear insulation defect detection system
Block diagram.
Specific embodiment
Invention is further described in detail with reference to the accompanying drawings and embodiments.
Shown in Figure 1, the embodiment of the invention provides one kind to be detected based on GA-BP neural network switchgear insulation defect
Method, switchgear are air switch cabinet, are included the following steps:
S1: collecting sample carries out storage and class formative to collected sample, so that training dataset is established, training
Data set includes gaseous species and content data in air switch cabinet when working normally, and is issued in different insulative defect type
Gaseous species and content data in air switch cabinet when raw shelf depreciation；
The different insulative defect type of air switch cabinet mainly include solid metal protrusion defect, insulator air gap lack
Sunken, insulator surface metal filth defect and free metal particle defects；Detection air switch cabinet in gas mainly have CO,
NO2And NO gas.
S2: building GA-BP neural network model；GA-BP neural network model includes input layer, hidden layer and output layer,
Input layer includes M input node, and M is equal with the number of gaseous species, and in the present embodiment, there are three types of gaseous species: CO, NO2
And NO gas, therefore, M=3 respectively corresponds CO, NO2And NO gas；Output layer includes N+1 output node, N and insulation
The type number of defect is equal, output node when 1 in N+1 is air switch cabinet normal work, and in the present embodiment, insulation is lacked
It falls into there are four types of types: solid metal protrusion defect, insulator void defects, insulator surface metal filth defect and free gold
Belong to particle defects, therefore, N=4 respectively corresponds solid metal protrusion defect, insulator void defects, insulator surface metal
Four insulation defects of filthy defect and free metal particle defects；Hidden layer uses 8 nodes.
S3: training dataset is input to GA-BP neural network model, GA-BP neural network model is trained, is obtained
To the identification model with identification air switch cabinet insulation defect function；
S4: air switch cabinet composition of gases within to be detected and content data, the time interval of measurement are periodically measured
No less than 2h, to improve recognition accuracy, measurement period T's is generally in the range of 2h≤T≤4h, can usually take T=2h；
In the present embodiment, also offer gas sensor, gas sensor are connect with identification model；Gas sensor is installed
In in air switch cabinet to be detected, the air switch cabinet composition of gases within and content are measured by gas sensor, gas passes
Sensor is by storage battery power supply.
S5: identification model receives the gas componant and content data of measurement, and gas componant and content progress to measurement
Identification, to export recognition result.
S6: providing insulation defect recording device, and insulation defect recording device is connect with identification model；Insulation defect record dress
It sets successively and respectively to continuously recognition result judges twice,
S7: if continuous recognition result twice is same insulation defect type, then it is assumed that the air switch cabinet is deposited really
In insulation defect, insulation defect recording device records judging result；
S8: otherwise, it is believed that shelf depreciation is to be caused by other reasons, and extinguished, and at this time without record, is recognized
Normal operating condition is in for the air switch cabinet.
Such as: measurement in two hours is primary, the result after the data measured every time are identified be successively denoted as respectively a1, a2,
A3, a4, a5, a6, a7 ..., insulation defect recording device judge whether a1 and a2 is same insulation defect type, if it is,
Judging result is recorded, which includes specific insulation defect type present in air switch cabinet, then judge a2 and a3, according to
It is secondary to analogize, until the last one recognition result participates in judgement；If it is not, then not recording, a2 and a3 are then judged, successively class
It pushes away, until the last one recognition result participates in judgement.
In order to guarantee the real-time of detection, it is ensured that the insulation defect of air switch cabinet is found and solved in time, is being known
When other model identifies first recognition result a1, insulation defect recording device wouldn't be judged, second knowledge out to be identified
When other result a2, insulation defect recording device can carry out the judgement of a1 and a2, it is to be identified go out third recognition result a3 when, absolutely
Edge defect record device can carry out the judgement of a2 and a3 namely after recognition result at least obtains two, insulation defect record
Device can be successively to continuously recognition result judges twice.
The record of insulation defect recording device is inspected periodically, service personnel can refer to the maintenance that the record carries out switchgear.
In step S1, the sample number acquired under normal condition and every kind of insulation defect state answer it is enough, to guarantee to identify
The accuracy of model；
The principle of the present invention are as follows: 10kV switchgear generallys use filling air as the mode of insulating gas to improve insulation
Performance, when shelf depreciation occurring in air switch cabinet, epoxy resin can be decomposed because electric injury occurs, and insulating gas also can be because
High temperature and pressure is reacted with oxygen, moisture and solid dielectric insulation, so that some stable gaseous state derivatives are generated, predominantly CO,
NO2, NO gas, and these gaseous state derivatives and insulation defect type are closely related, therefore, the corresponding training of present invention acquisition
Data set is trained GA-BP neural network model by training dataset, so that obtaining can identify that air switch cabinet is exhausted
The identification model of edge defect function, then the gas componant and content data of air switch cabinet to be detected are measured, by identifying mould
Type is identified.What the present invention acquired is the gas in air switch cabinet, avoids the interference of ambient atmos, to improve accurately
Rate.
The present invention by insulation defect recording device successively to continuously recognition result judges twice, when continuous two
Secondary recognition result is same insulation defect type, just thinks that the air switch cabinet is implicitly present in insulation defect, insulation defect note
Recording device records judging result；Otherwise, it is believed that shelf depreciation is to be caused by other reasons, and extinguished, at this time not into
Row record, it is believed that the air switch cabinet is in normal operating condition, thus the case where reducing wrong report.Service personnel passes through record
Judging result will appreciate that insulation defect information that may be present in switchgear and solve existing security risk, reduces part and puts
10kV switchgear tripping times caused by electricity, it is ensured that shelf depreciation caused by by insulation defect does not endanger switchgear, guarantees switch
The safe operation of cabinet safety and stability, power supply reliability and power grid.
Shown in Figure 2, the embodiment of the invention also provides one kind to be examined based on GA-BP neural network switchgear insulation defect
Examining system, switchgear are air switch cabinet comprising data reception module, identification model and output module；Wherein:
Data reception module is for receiving air switch cabinet composition of gases within to be detected and content data；
Identification model is trained to obtain using training dataset to GA-BP neural network model, and training dataset packet
Gaseous species and content data in air switch cabinet when including normal work, and part occurs under different insulative defect type and puts
Gaseous species and content data in air switch cabinet when electric；Identification model is to be checked according to the received data identification of data reception module
The insulation defect type of the air switch cabinet of survey；
Output module is for exporting recognition result.
Shown in Figure 3, the embodiment of the invention also provides one kind to be examined based on GA-BP neural network switchgear insulation defect
Examining system, switchgear are air switch cabinet comprising data collector, neural network server and insulation defect recording device；
Wherein:
Data collector is for acquiring air switch cabinet composition of gases within to be detected and content data；
Neural network server is preset with identification model, and identification model is using training dataset to GA-BP neural network mould
Type is trained to obtain, training dataset include work normally when air switch cabinet in gaseous species and content data, Yi Ji
Under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；Neural network server
The data of collector acquisition and the insulation defect type of air switch cabinet to be detected is identified according to the data for receiving data,
And export recognition result；
Insulation defect recording device is used for successively to continuously recognition result judges twice, if continuously identifying twice
It as a result is same insulation defect type, then insulation defect recording device records judging result；Otherwise, without record.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only the embodiment of the present invention, are not intended to restrict the invention, all in the spirit and principles in the present invention
Within, any modification, equivalent substitution, improvement and etc. done, be all contained in apply pending scope of the presently claimed invention it
It is interior.The content being not described in detail in this specification belongs to the prior art well known to professional and technical personnel in the field.
Claims (10)
1. one kind is based on GA-BP neural network switchgear method for detecting insulation defect, the switchgear is air switch cabinet, special
Sign is, includes the following steps:
Establish training dataset, the training dataset includes gaseous species and content number in air switch cabinet when working normally
According to, and under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；
Construct GA-BP neural network model；
GA-BP neural network model is trained using the training dataset, obtains that there is identification air switch cabinet insulation
The identification model of defect function；
Periodically measure air switch cabinet composition of gases within to be detected and content；
It is identified using gas componant and content of the identification model to measurement, and exports recognition result.
2. detection method as described in claim 1, which is characterized in that the detection method further includes following steps:
Insulation defect recording device is provided, the insulation defect recording device is connect with identification model；
The insulation defect recording device is successively to continuously recognition result judges twice, if continuous recognition result twice
For same insulation defect type, then the insulation defect recording device records judging result；Otherwise, without record.
3. detection method as described in claim 1, it is characterised in that: the different insulative defect type includes solid metal
Protrusion defect, insulator void defects, insulator surface metal filth defect and free metal particle defects.
4. detection method as described in claim 1, it is characterised in that: the gaseous species include CO, NO2And NO gas.
5. detection method as described in claim 1, it is characterised in that: the GA-BP neural network model includes input layer, hidden
Containing layer and output layer, the input layer includes M input node, and M is equal with the number of gaseous species；The output layer includes N+
1 output node, N are equal with the type number of insulation defect.
6. detection method as described in claim 1, it is characterised in that: the measurement period T of the gas sensor meets: 2h≤
T≤4h。
7. detection method as described in claim 1, it is characterised in that: provide gas sensor, the gas sensor and knowledge
Other model connection；
The gas sensor is installed in air switch cabinet to be detected, which is measured by the gas sensor and is opened
Close cabinet composition of gases within and content.
8. one kind is based on GA-BP neural network switchgear insulation defect detection system, the switchgear is air switch cabinet, special
Sign is comprising:
Data reception module is used to receive air switch cabinet composition of gases within to be detected and content data；
Identification model is trained to obtain using training dataset to GA-BP neural network model, and the training dataset
Including work normally when air switch cabinet in gaseous species and content data, and under different insulative defect type occur part
Gaseous species and content data in air switch cabinet when electric discharge；The identification model is known according to the received data of data reception module
The insulation defect type of air switch cabinet not to be detected；
Output module is used to export recognition result.
9. one kind is based on GA-BP neural network switchgear insulation defect detection system, the switchgear is air switch cabinet, special
Sign is comprising:
Data collector is used to acquire air switch cabinet composition of gases within to be detected and content data；
Neural network server is preset with identification model, and the identification model is using training dataset to GA-BP neural network
Model is trained to obtain, the training dataset include work normally when air switch cabinet in gaseous species and content data,
And under different insulative defect type occur shelf depreciation when air switch cabinet in gaseous species and content data；The nerve
The network server data that collector acquires for receiving data simultaneously identify the exhausted of air switch cabinet to be detected according to the data
Edge defect type, and export recognition result.
10. detection system as claimed in claim 9, it is characterised in that: the detection system further includes insulation defect record dress
It sets, the insulation defect recording device is used for successively to continuously recognition result judges twice, if this continuously knows twice
Other result is same insulation defect type, then the insulation defect recording device records judging result；Otherwise, without note
Record.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910281121.0A CN110321585A (en) | 2019-04-09 | 2019-04-09 | Based on GA-BP neural network switchgear method for detecting insulation defect and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910281121.0A CN110321585A (en) | 2019-04-09 | 2019-04-09 | Based on GA-BP neural network switchgear method for detecting insulation defect and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321585A true CN110321585A (en) | 2019-10-11 |
Family
ID=68112887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910281121.0A Pending CN110321585A (en) | 2019-04-09 | 2019-04-09 | Based on GA-BP neural network switchgear method for detecting insulation defect and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321585A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007365A (en) * | 2019-11-25 | 2020-04-14 | 国网四川省电力公司广安供电公司 | Ultrasonic partial discharge identification method and system based on neural network |
| CN114928019A (en) * | 2022-07-19 | 2022-08-19 | 深圳市世坤科技实业有限公司 | Electric switch emergency protection system and method of automatic control system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1091539A (en) * | 1993-11-27 | 1994-08-31 | 北方交通大学 | The artificial nerve net parallel computer implementation method |
| CN1694130A (en) * | 2005-03-24 | 2005-11-09 | 上海大学 | Identification method of mobile number plate based on three-channel parallel artificial nerve network |
| CN1889136A (en) * | 2005-06-30 | 2007-01-03 | 上海市延安中学 | Apparatus for fatigue driving prealarming system |
| CN101183317A (en) * | 2006-11-14 | 2008-05-21 | 中兴通讯股份有限公司 | Method for real-time interrupting synchronization with multiple progress states |
| CN104038383A (en) * | 2014-04-14 | 2014-09-10 | 贵州电力试验研究院 | Switch based process level network message analysis method |
| CN105632102A (en) * | 2014-10-29 | 2016-06-01 | 李艳 | Fatigue driving early-warning system device |
| CN107229914A (en) * | 2017-05-26 | 2017-10-03 | 北京工业大学 | A kind of Handwritten Digit Recognition method based on depth Q learning strategies |
| CN109459671A (en) * | 2018-09-27 | 2019-03-12 | 国网浙江省电力有限公司湖州供电公司 | A kind of switch cabinet state monitoring method of the improvement neural network based on genetic algorithm |
-
2019
- 2019-04-09 CN CN201910281121.0A patent/CN110321585A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1091539A (en) * | 1993-11-27 | 1994-08-31 | 北方交通大学 | The artificial nerve net parallel computer implementation method |
| CN1694130A (en) * | 2005-03-24 | 2005-11-09 | 上海大学 | Identification method of mobile number plate based on three-channel parallel artificial nerve network |
| CN1889136A (en) * | 2005-06-30 | 2007-01-03 | 上海市延安中学 | Apparatus for fatigue driving prealarming system |
| CN101183317A (en) * | 2006-11-14 | 2008-05-21 | 中兴通讯股份有限公司 | Method for real-time interrupting synchronization with multiple progress states |
| CN104038383A (en) * | 2014-04-14 | 2014-09-10 | 贵州电力试验研究院 | Switch based process level network message analysis method |
| CN105632102A (en) * | 2014-10-29 | 2016-06-01 | 李艳 | Fatigue driving early-warning system device |
| CN107229914A (en) * | 2017-05-26 | 2017-10-03 | 北京工业大学 | A kind of Handwritten Digit Recognition method based on depth Q learning strategies |
| CN109459671A (en) * | 2018-09-27 | 2019-03-12 | 国网浙江省电力有限公司湖州供电公司 | A kind of switch cabinet state monitoring method of the improvement neural network based on genetic algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 李良军: "变电设备在线监测技术应用研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007365A (en) * | 2019-11-25 | 2020-04-14 | 国网四川省电力公司广安供电公司 | Ultrasonic partial discharge identification method and system based on neural network |
| CN114928019A (en) * | 2022-07-19 | 2022-08-19 | 深圳市世坤科技实业有限公司 | Electric switch emergency protection system and method of automatic control system |
| CN114928019B (en) * | 2022-07-19 | 2022-11-01 | 深圳市世坤科技实业有限公司 | Electric switch emergency protection system and method of automatic control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105606975B (en) | A kind of orientable superfrequency cable local discharge detection method and device | |
| CN112201260B (en) | Transformer running state online detection method based on voiceprint recognition | |
| CN102156245B (en) | A kind of mine high-voltage cable on-line fault diagnosis and method for early warning | |
| CN109856299A (en) | A kind of transformer online monitoring differentiation threshold value dynamic setting method, system | |
| CN106405475A (en) | Electric energy meter abnormity diagnosis method | |
| CN108459295B (en) | CVT on-line monitoring system and method based on distributed data acquisition processing | |
| CN105116246B (en) | A kind of operation of power networks protection on-line analysis method | |
| CN103885438B (en) | The Auto-Test System of a kind of transformer station measuring and controlling equipment and method | |
| CN110188309B (en) | Oil-immersed power transformer defect early warning method based on hidden Markov model | |
| CN103200051A (en) | Intelligent substation message simulation testing and association message analysis system and method | |
| CN110321585A (en) | Based on GA-BP neural network switchgear method for detecting insulation defect and system | |
| CN110347717A (en) | A kind of big data storage method based on urban electric power equipment monitoring | |
| CN109490685B (en) | Early defect early warning method of transformer based on-line monitoring of dissolved gas in oil | |
| CN106921522A (en) | Intelligent substation network message record analysis device networked information model inspection device | |
| CN111521953A (en) | Rail transit contact net leakage current detecting system | |
| CN110647924A (en) | GIS equipment state evaluation method based on support vector description and K-nearest neighbor algorithm | |
| CN113030666A (en) | Large-scale transformer discharge fault diagnosis method and device | |
| CN116449235A (en) | Method and system for processing test data of energy storage battery | |
| WO2024078344A1 (en) | Monitoring method, system and apparatus for quality of high-frequency external power grid | |
| CN109270383A (en) | A kind of non-intrusion type charging pile automatic testing method | |
| CN113092927A (en) | Alternating current filter state diagnosis method based on wave recording waveform image and artificial intelligence | |
| CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
| CN117169639A (en) | Product detection method and system for power adapter production | |
| CN115935264A (en) | Power grid transient voltage stability assessment method based on time-space information synchronous learning | |
| CN115733258A (en) | Control method of all-indoor intelligent substation system based on Internet of things technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191011 |