CN108051709A - Transformer state online evaluation analysis method based on artificial intelligence technology - Google Patents
Transformer state online evaluation analysis method based on artificial intelligence technology Download PDFInfo
- Publication number
- CN108051709A CN108051709A CN201711242291.5A CN201711242291A CN108051709A CN 108051709 A CN108051709 A CN 108051709A CN 201711242291 A CN201711242291 A CN 201711242291A CN 108051709 A CN108051709 A CN 108051709A
- Authority
- CN
- China
- Prior art keywords
- transformer
- data
- analysis
- module
- information
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 115
- 238000011156 evaluation Methods 0.000 title claims abstract description 36
- 238000005516 engineering process Methods 0.000 title claims abstract description 18
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 8
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 7
- 230000002194 synthesizing Effects 0.000 claims abstract description 7
- 238000004891 communication Methods 0.000 claims description 14
- 238000003745 diagnosis Methods 0.000 claims description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 9
- 230000000875 corresponding Effects 0.000 claims description 8
- 238000004804 winding Methods 0.000 claims description 8
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 239000007789 gas Substances 0.000 description 16
- 230000000994 depressed Effects 0.000 description 3
- 206010056871 Device failure Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001131 transforming Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
Abstract
The invention discloses the transformer state online evaluation analysis methods based on artificial intelligence technology, belong to technical field of electric power, including establishing transformer synthesis in-circuit diagnostic system, historical failure information module, real-time data acquisition module, failure perception analysis module, artificial intelligence analysis's module, transformer online evaluation analysis module and MMI man-machine interfaces are established in data center's processing server, it is more, online monitoring data using analysis not enough and the technical issues of well operation maintenance personnel cannot be instructed to be handled to solve fault misdescription in the prior art；The present invention can greatly improve the reliability to transformer online monitoring and equipment state assessment, reduce the rate of false alarm and rate of failing to report of equipment, reduce the labor intensity of operations staff.
Description
Technical field
The invention belongs to technical field of electric power, the transformer state online evaluation point more particularly to based on artificial intelligence technology
Analysis method.
Background technology
Power transformer is the important pivot equipment of electric system, its operating condition and electric system whether safe operation
It is directly related, once breaking down necessarily causes locally even whole system paralysis, seriously affecting daily life production just
Often power supply, so as to cause huge loss.
Current transformer state online monitoring system reflects following problem in operation：
1. equipment rate of false alarm is high：After transformer online monitoring various kinds of equipment puts into operation, compatible analysis, Ge Gemo are not carried out
Block is relatively independent, is just present with many equipment fault wrong reports.
2. the utilization and analysis of transformer online monitoring data are inadequate：After data largely upload, lack the analysis to data
Processing means for defect analysis and failure predication still by experience, do not automatically analyze function, practical function effectively and timely
It is bad.Transformer online monitoring equipment, can not be accurately to fortune once break down as a result, be only prompted to user's failure situation
Dimension personnel's instruction.
3. the defects of transformer, is analyzed and fail result cannot instruct operation maintenance personnel to be analyzed and handled well：At present
The service work of equipment is all to overhaul rather than overhaul on demand on time, is run in spite of illness so as to cause transformer or transformer is transported
It is overhauled in the case of row is good, causes very big waste.
The content of the invention
The object of the present invention is to provide the transformer state online evaluation analysis methods based on artificial intelligence technology, solve
In the prior art fault misdescription it is more, it is online monitoring data using analysis not enough and cannot instruct well at operation maintenance personnel
The technical issues of reason.
To achieve the above object, the present invention uses following technical scheme：
Transformer state online evaluation analysis method based on artificial intelligence technology, includes the following steps：
Step 1：Transformer synthesis in-circuit diagnostic system is established, transformer synthesis in-circuit diagnostic system includes sensor list
Member, data communication module, IED devices and data center processing server, sensor unit are connected with IED devices, IED devices with
Data communication module connects, and data communication module is connected with data center processing server；
Step 2：Sensor unit gathers the current operating data information of transformer, and current operating data information is transmitted
IED devices are given, and are summarized by IED devices, generate real time data, IED devices are by data communication module by real time data
Send data center's processing server to；
Step 3：Historical failure information module, real-time data acquisition module, event are established in data center's processing server
Hinder perception analysis module, artificial intelligence analysis's module, transformer online evaluation analysis module and MMI man-machine interfaces, real time data
Acquisition module receives and stores real time data, and sends real time data to failure perception analysis module, failure perception analysis mould
Block carries out perception analysis to real time data, carries out discriminatory analysis by threshold diagnostic and time domain waveform diagnosis, obtains number of faults
According to；
Step 4：Transformer fault information bank is stored in historical failure information module and solves scheme base, historical failure letter
Breath module establishes transformer fault information model, failure perception analysis module according to transformer fault information bank and solution scheme base
Fault data is sent to artificial intelligence analysis module by api interface, artificial intelligence module is according to transformer fault information mould
Type is analyzed using diagnostician's analysis system, is drawn analysis result and is solved scheme proposals, artificial intelligence module will be analyzed
As a result transformer online evaluation analysis module is sent to solution scheme proposals；
Step 5：Transformer online evaluation analysis module according to analysis result and solve scheme proposals generation text message and
Chart-information, and pass through MMI man-machine interfaces and show the text message and the chart-information.
The sensor unit includes Gas in Oil of Transformer harvester, iron core grounding current collecting device, part and puts
Electric harvester, loaded switch information acquisition control device, cooler information acquisition control device, casing information collecting device,
Winding temperature measurement device, load data harvester, top oil harvester, temperature collection device and non electrical quantity information are adopted
Acquisition means.
The type information of various transformers and relevant failure accident record, the solution are stored in the fault message storehouse
Various failure accidents are certainly stored in scheme base and record corresponding solution method；The transformer fault information model includes transformation
Device failure accident records and the solution method of corresponding failure accident record.
When performing step 3, failure perception analysis module carries out perception analysis to real time data, includes the following steps：
Step S1：Carry out threshold diagnostic：Whether more than defined threshold judge the operation of transformer according to gained characteristic quantity
State；
Step S2：Transformer is monitored in real time by time domain waveform diagnosis：By all data of monitoring according at any time
Between the curve that changes and typical curve carry out model and compare to judge the operating status of transformer.
The characteristic quantity is the Gas in Oil of Transformer data, iron core grounding current data, part of sensor unit acquisition
Discharge data, loaded switch information data, cooler information data, casing information data, winding temperature measurement data, load data number
According to, top oil data, ambient temperature data and non electrical quantity information data.
When performing step 4, artificial intelligence module uses diagnostician's analysis system according to transformer fault information model
It is analyzed, is included the following steps：
Step S3：Transformer fault information model is used for establishing transformer fault domain knowledge, by transformer fault information
Model imports diagnostician's analysis system；
Step S4：The initial data gathered in real time and failure perception analysis module are obtained into fault data by perception analysis
Result store to historical failure information module；
Step S5：Analysis is made inferences using the inference mechanism in diagnostician's analysis system, and result is exported to change
Depressor online evaluation analysis module.
Transformer state online evaluation analysis method of the present invention based on artificial intelligence technology, solves existing skill
Fault misdescription is more in art, online monitoring data utilizes analysis not enough and the skill that operation maintenance personnel cannot be instructed to be handled well
Art problem；The present invention can greatly improve the reliability to transformer online monitoring and equipment state assessment, reduce the mistake of equipment
Report rate and rate of failing to report reduce the labor intensity of operations staff.
Description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the artwork block diagram of the data communication module of the present invention；
Fig. 3 is the system structure diagram of the present invention；
Fig. 4 is the Threshold Analysis decision flow chart of the present invention；
Fig. 5 is the rough set Troubleshooting Flowchart of the present invention.
Specific embodiment
The transformer state online evaluation analysis method based on artificial intelligence technology as Figure 1-Figure 5, including as follows
Step：
Step 1：Transformer synthesis in-circuit diagnostic system is established, transformer synthesis in-circuit diagnostic system includes sensor list
Member, data communication module, IED devices and data center processing server, sensor unit are connected with IED devices, IED devices with
Data communication module connects, and data communication module is connected with data center processing server；
The IED devices are that (the transformer data integration device is the prior art to transformer data integration device, therefore not
Narration in detail).
Step 2：Sensor unit gathers the current operating data information of transformer, and current operating data information is transmitted
IED devices are given, and are summarized by IED devices, generate real time data, IED devices are by data communication module by real time data
Send data center's processing server to；
The data communication module is mainly connected with IED devices, and data are obtained for obtaining sensor, and by the number of acquisition
According in deposit real-time data acquisition module, while the data gathered by analysis result and in real time upload to higher level and dispatch system.
Step 3：Historical failure information module, real-time data acquisition module, event are established in data center's processing server
Hinder perception analysis module, artificial intelligence analysis's module, transformer online evaluation analysis module and MMI man-machine interfaces, real time data
Acquisition module receives and stores real time data, and sends real time data to failure perception analysis module, failure perception analysis mould
Block carries out perception analysis to real time data, carries out discriminatory analysis by threshold diagnostic and time domain waveform diagnosis, obtains number of faults
According to；
Real time memory resident database is established in real-time data acquisition module, stores the one piece of data monitored in real time, data include：Oil
In 7 kinds of gases and Wei Shui, load current, environment temperature, top oil, winding temperature, non electrical quantity data (pressure relief valve, again
Gas, light gas, body oil level, total protection signal etc.), cooler state, loaded switch monitoring information, casing monitoring information
(end shield electric current, dielectric loss, equivalent capacitance etc.), iron core grounding electric current, partial discharge quantity and local discharge phase etc. are real
When monitoring data, comprise in addition current transformer nominal parameter, current transformer volume casing nominal parameter, current transformer volume
Loaded switch nominal parameter, current transformer volume cooler nominal parameter, current transformer load characteristic related data and curve
Data.
The analysis method that failure perception analysis module uses includes monitoring variable Threshold Analysis method, three ratio Analysis of oil dissolved gas
Method, oil dissolved gas cube analytic approach, oil dissolved gas David's trigonometric analysis method, time domain waveform diagnosis；Failure perception analysis mould
Block is mainly analyzed and determined by traditional transformer state analysis, threshold decision and time domain waveform diagnoses, transformer state analysis master
To pass through traditional three method for analyzing ratio of oil dissolved gas, oil dissolved gas cube analytic approach, oil dissolved gas David's trigonometric analysis method；
Threshold Analysis judges, the threshold value of each monitoring data of Main Basiss and the change rate threshold value of monitoring data judge, time domain
Waves diagnosis is mainly in the curve of test that dispatches from the factory to the data versus time curve and transformer of transformer online monitoring
Control carries out judgement equipment state；
As shown in Fig. 2, failure perception analysis module sets threshold value to real time data, it is then alarm more than threshold value, is no more than
Threshold value is then normal.
Step 4：Transformer fault information bank is stored in historical failure information module and solves scheme base, historical failure letter
Breath module establishes transformer fault information model, failure perception analysis module according to transformer fault information bank and solution scheme base
Fault data is sent to artificial intelligence analysis module by api interface, artificial intelligence module is according to transformer fault information mould
Type is analyzed using diagnostician's analysis system, is drawn analysis result and is solved scheme proposals, artificial intelligence module will be analyzed
As a result transformer online evaluation analysis module is sent to solution scheme proposals；
The data that transformer fault information model mainly preserves include：Failure transformer nominal parameter, failure transformer volume
Casing nominal parameter, failure transformer volume loaded switch nominal parameter, failure transformer volume cooler nominal parameter, transformer are born
History number before load characteristic, failure title, transformer fault phenomenon, transformer fault reason, repair suggestion, transformer break down
According to this and failure data analyzing model method etc..
The network structure built in advance using real-time data acquisition module data in the building process of data model model, and
Model parameter is optimized, and then improves the accuracy rate of category of model.The data newly collected finally are inputted training to complete
Model in be detected, the accuracy rate of testing model.
Diagnostic expert system uses rough set fault diagnosis mode, can efficiently use transformer monitoring device acquisition number
According to by being analyzed and processed to monitoring obtained unlabeled exemplars on-line, the relation between discovery data extracts useful spy
Property, obtain brief and concise knowledge expression：Include the following steps：
Step A：According to the real time data of acquisition, according to rough set theory expression formula, S=(U, A), wherein U are by right in S
As the set of composition, and A=(CUD), diagnostic expert system formation condition property set (C) and decision kind set (D), C represent to become
Depressor fault signature collection, D indication transformer fault type collection；
Step B：Diagnostic expert system is according to transformer fault feature set (in light gas, grave gas, pressure relief valve, oil
Micro- water, iron core grounding electric current etc.) and transformer fault set of types (turn-to-turn short circuit, spark discharge, switch fault, screen electric discharge etc.
Deng) the old description transformer analysis expert information system S of generation decision table (forming a two-dimensional table)；
Step C：Yojan, yojan mode Main Basiss transformer fault type are carried out to all conditions attribute in decision table
The feature of corresponding gathered data, for the result of yojan by 0 in two-dimensional table and 1, Fuzzy Processing becomes 0,0.5,1 or other numbers
According to value；
Step D：Decision table is formed to each yojan, according to transformer fault feature set and transformer fault set of types
Data characteristic calculates rough membership U；
Step E：Given confidence level U0, according to U>U0Rule be included in transformer fault rule set；
Step F：Last diagnostic is made according to transformer fault rule set.
Step 5：Transformer online evaluation analysis module according to analysis result and solve scheme proposals generation text message and
Chart-information, and pass through MMI man-machine interfaces and show the text message and the chart-information.
Transformer online evaluation analysis module sets different deduction of points values to the quantity of state of transformer, that is, distributes different power
Weight, the state of equipment can really be reflected by ensureing the evaluation score value of transformer state amount；According to transformer characteristic, joined with transformer
Number, running state of transformer etc. obtain transformer evaluation measurement, according to the selection requirement of transformer state amount, are selected from measurement
Quantity of state directly related with equipment performance is taken, quantitative model is determined according to quantity of state property, with reference to real-time status analysis result, profit
The evaluation of part of appliance, integral device is realized with evaluation method, transformer online evaluation analysis module in monitoring data to occurring
Situations such as bad data, transformer break down, carries out transformer online evaluation analysis, and each case corresponds to corresponding evaluation
Score value corresponds to five kinds of state grades according to score value：Well, normally, pay attention to, abnormal and " great exception ".
The sensor unit includes Gas in Oil of Transformer harvester, and (Gas in Oil of Transformer harvester is existing
Technology, therefore do not describe in detail), (iron core grounding current collecting device is the prior art to iron core grounding current collecting device, therefore unknown
Thin narration), shelf depreciation harvester (shelf depreciation harvester is the prior art, therefore is not described in detail), loaded switch letter
Cease acquisition control device (loaded switch information acquisition control device is the prior art, therefore is not described in detail), cooler information is adopted
Integrate control device (cooler information acquisition control device does not describe in detail as the prior art), casing information collecting device (set
Pipe information collecting device be the prior art, therefore not in detail describe), winding temperature measurement device (winding temperature measurement device be the prior art, therefore
Not in detail describe), load data harvester (load data harvester be the prior art, therefore not in detail describe), top oil
Warm harvester (top oil harvester is the prior art, therefore is not described in detail), temperature collection device (environment temperature
Harvester is the prior art, thus not in detail describe) and non electrical quantity information collecting device (non electrical quantity information collecting device be it is existing
Technology, therefore do not describe in detail).
The type information of various transformers and relevant failure accident record, the solution are stored in the fault message storehouse
Various failure accidents are certainly stored in scheme base and record corresponding solution method；The transformer fault information model includes transformation
Device failure accident records and the solution method of corresponding failure accident record.
When performing step 3, failure perception analysis module carries out perception analysis to real time data, includes the following steps：
Step S1：Carry out threshold diagnostic：Whether more than defined threshold judge the operation of transformer according to gained characteristic quantity
State；
Step S2：Transformer is monitored in real time by time domain waveform diagnosis：By all data of monitoring according at any time
Between the curve that changes and typical curve carry out model and compare to judge the operating status of transformer.
The characteristic quantity is the Gas in Oil of Transformer data, iron core grounding current data, part of sensor unit acquisition
Discharge data, loaded switch information data, cooler information data, casing information data, winding temperature measurement data, load data number
According to, top oil data, ambient temperature data and non electrical quantity information data.
When performing step 4, artificial intelligence module uses diagnostician's analysis system according to transformer fault information model
It is analyzed, is included the following steps：
Step S3：Transformer fault information model is used for establishing transformer fault domain knowledge, by transformer fault information
Model imports diagnostician's analysis system；
Step S4：The initial data gathered in real time and failure perception analysis module are obtained into fault data by perception analysis
Result store to historical failure information module；
Step S5：Analysis is made inferences using the inference mechanism in diagnostician's analysis system, and result is exported to change
Depressor online evaluation analysis module.
Diagnostic expert system utilizes the expert system (expert system in the artificial intelligence field in artificial intelligence field
For the prior art, therefore do not describe in detail) transformer real time data is analyzed and determined.
Transformer state online evaluation analysis method of the present invention based on artificial intelligence technology, solves existing skill
Fault misdescription is more in art, online monitoring data utilizes analysis not enough and the skill that operation maintenance personnel cannot be instructed to be handled well
Art problem；The present invention can greatly improve the reliability to transformer online monitoring and equipment state assessment, reduce the mistake of equipment
Report rate and rate of failing to report reduce the labor intensity of operations staff.
Claims (6)
1. the transformer state online evaluation analysis method based on artificial intelligence technology, it is characterised in that：Include the following steps：
Step 1：Transformer synthesis in-circuit diagnostic system is established, transformer synthesis in-circuit diagnostic system includes sensor unit, number
It is connected according to communication module, IED devices and data center processing server, sensor unit with IED devices, IED devices and data
Communication module connects, and data communication module is connected with data center processing server；
Step 2：Sensor unit gathers the current operating data information of transformer, and current operating data information is sent to
IED devices, and summarized by IED devices, real time data is generated, IED devices are passed real time data by data communication module
Give data center's processing server；
Step 3：Historical failure information module, real-time data acquisition module, failure sense are established in data center's processing server
Know analysis module, artificial intelligence analysis's module, transformer online evaluation analysis module and MMI man-machine interfaces, real-time data acquisition
Module receives and stores real time data, and sends real time data to failure perception analysis module, failure perception analysis module pair
Real time data carries out perception analysis, carries out discriminatory analysis by threshold diagnostic and time domain waveform diagnosis, obtains fault data；
Step 4：Transformer fault information bank is stored in historical failure information module and solves scheme base, historical failure information mould
Root tuber establishes transformer fault information model according to transformer fault information bank and solution scheme base, and failure perception analysis module will be former
Barrier data send artificial intelligence analysis's module to by api interface, and artificial intelligence module is adopted according to transformer fault information model
It is analyzed with diagnostician's analysis system, draw analysis result and solves scheme proposals, artificial intelligence module is by analysis result
Transformer online evaluation analysis module is sent to scheme proposals are solved；
Step 5：Transformer online evaluation analysis module is according to analysis result and solves scheme proposals generation text message and chart
Information, and pass through MMI man-machine interfaces and show the text message and the chart-information.
2. the transformer state online evaluation analysis method based on artificial intelligence technology, feature exist as described in claim 1
In:The sensor unit includes Gas in Oil of Transformer harvester, iron core grounding current collecting device, shelf depreciation acquisition
Device, loaded switch information acquisition control device, cooler information acquisition control device, casing information collecting device, winding are surveyed
Warm device, load data harvester, top oil harvester, temperature collection device and non electrical quantity information gathering dress
It puts.
3. the transformer state online evaluation analysis method based on artificial intelligence technology, feature exist as described in claim 1
In:The type information of various transformers and relevant failure accident record, the solution party are stored in the fault message storehouse
Various failure accidents are stored in case storehouse and record corresponding solution method；The transformer fault information model includes transformer event
Hinder the solution method of accident record and corresponding failure accident record.
4. the transformer state online evaluation analysis method based on artificial intelligence technology, feature exist as described in claim 1
In:When performing step 3, failure perception analysis module carries out perception analysis to real time data, includes the following steps：
Step S1：Carry out threshold diagnostic：Whether more than defined threshold judge the operating status of transformer according to gained characteristic quantity；
Step S2：Transformer is monitored in real time by time domain waveform diagnosis：By all data of monitoring according to becoming at any time
The curve of change compares to judge the operating status of transformer with typical curve progress model.
5. the transformer state online evaluation analysis method based on artificial intelligence technology, feature exist as claimed in claim 4
In:The characteristic quantity is the Gas in Oil of Transformer data, iron core grounding current data, shelf depreciation number of sensor unit acquisition
According to, loaded switch information data, cooler information data, casing information data, winding temperature measurement data, load data data, top
Portion's oil temperature data, ambient temperature data and non electrical quantity information data.
6. the transformer state online evaluation analysis method based on artificial intelligence technology, feature exist as described in claim 1
In:When performing step 4, artificial intelligence module is divided according to transformer fault information model using diagnostician's analysis system
Analysis, includes the following steps：
Step S3：Transformer fault information model is used for establishing transformer fault domain knowledge, by transformer fault information model
Import diagnostician's analysis system；
Step S4：The initial data gathered in real time and failure perception analysis module are obtained into the knot of fault data by perception analysis
Fruit is stored to historical failure information module；
Step S5：Analysis is made inferences using the inference mechanism in diagnostician's analysis system, and result is exported to transformer
Online evaluation analysis module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711242291.5A CN108051709A (en) | 2017-11-30 | 2017-11-30 | Transformer state online evaluation analysis method based on artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711242291.5A CN108051709A (en) | 2017-11-30 | 2017-11-30 | Transformer state online evaluation analysis method based on artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108051709A true CN108051709A (en) | 2018-05-18 |
Family
ID=62121577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711242291.5A Pending CN108051709A (en) | 2017-11-30 | 2017-11-30 | Transformer state online evaluation analysis method based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108051709A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002672A (en) * | 2018-09-30 | 2018-12-14 | 珠海市运泰利自动化设备有限公司 | A kind of design method of the intelligent producing line based on optic test |
| CN109146093A (en) * | 2018-08-08 | 2019-01-04 | 成都保源酷码科技有限公司 | A kind of electric power equipment on-site exploration method based on study |
| CN110609187A (en) * | 2019-09-21 | 2019-12-24 | 厦门加华电力科技有限公司 | Intelligent management system based on SF6 electrical equipment data detection and intelligent analysis |
| CN111458604A (en) * | 2019-12-27 | 2020-07-28 | 广东电网有限责任公司电力科学研究院 | Transformer self-sensing-based oscillation type lightning impulse test system and method |
| CN111983523A (en) * | 2020-08-24 | 2020-11-24 | 国网上海市电力公司 | Transformer running state data acquisition and analysis system and method based on big data platform |
| CN112652138A (en) * | 2020-12-16 | 2021-04-13 | 国网安徽省电力有限公司检修分公司 | Large transformer fire alarm early warning method based on same quantity comparison |
| CN112859803A (en) * | 2021-01-04 | 2021-05-28 | 中车青岛四方车辆研究所有限公司 | Detection equipment and health state evaluation method for bicycle brake control device |
| CN114252724A (en) * | 2022-03-02 | 2022-03-29 | 山东和兑智能科技有限公司 | Intelligent detection method and detection system for transformer |
| CN114459529A (en) * | 2020-11-09 | 2022-05-10 | 特变电工京津冀智能科技有限公司 | Intelligent maintenance device of oil-filled bushing, transformer and power transformation system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1484034A (en) * | 2002-09-18 | 2004-03-24 | 新疆特变电工股份有限公司 | On-line intelligent monitoring system for transformer and intelligent analysis diagnosis method thereof |
| CN101452040A (en) * | 2008-12-30 | 2009-06-10 | 中国瑞林工程技术有限公司 | Ferro resonance failure diagnosis expert system |
| WO2013008246A1 (en) * | 2011-07-13 | 2013-01-17 | Crompton Greaves Limited | An intelligent transformer monitoring system |
| CN103020219A (en) * | 2012-12-10 | 2013-04-03 | 广东电网公司电力科学研究院 | Network-based expert system tool for power grid fault diagnosis |
| CN103076526A (en) * | 2013-01-16 | 2013-05-01 | 国网电力科学研究院 | Fault diagnosis method based on transformer panoramic state information |
| CN103135014A (en) * | 2012-12-14 | 2013-06-05 | 西安电子科技大学 | Transformer fault diagnosis method based on case-based reasoning |
| CN103487514A (en) * | 2013-09-05 | 2014-01-01 | 昆明理工大学 | Online monitoring information aggregating method of transformer based on wavelet transform and evidence reasoning |
| CN103678765A (en) * | 2013-10-31 | 2014-03-26 | 上海交通大学 | Transformer operating state comprehensive evaluation method based on on-line monitoring |
| CN105867346A (en) * | 2016-03-24 | 2016-08-17 | 国家电网公司 | State evaluation and maintenance decision support method for transformer |
| CN106324406A (en) * | 2016-09-21 | 2017-01-11 | 许继集团有限公司 | Transformer direct-current magnetic bias fault diagnosis method and device |
| CN104362736B (en) * | 2014-09-17 | 2017-03-15 | 特变电工衡阳变压器有限公司 | A kind of Intelligent component cabinet and its monitoring method for intelligent transformer |
| CN106932712A (en) * | 2016-12-30 | 2017-07-07 | 江苏南瑞泰事达电气有限公司 | A kind of circuit breaker failure diagnostic method based on improvement Fuzzy Petri Net |
-
2017
- 2017-11-30 CN CN201711242291.5A patent/CN108051709A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1484034A (en) * | 2002-09-18 | 2004-03-24 | 新疆特变电工股份有限公司 | On-line intelligent monitoring system for transformer and intelligent analysis diagnosis method thereof |
| CN101452040A (en) * | 2008-12-30 | 2009-06-10 | 中国瑞林工程技术有限公司 | Ferro resonance failure diagnosis expert system |
| WO2013008246A1 (en) * | 2011-07-13 | 2013-01-17 | Crompton Greaves Limited | An intelligent transformer monitoring system |
| CN103020219A (en) * | 2012-12-10 | 2013-04-03 | 广东电网公司电力科学研究院 | Network-based expert system tool for power grid fault diagnosis |
| CN103135014A (en) * | 2012-12-14 | 2013-06-05 | 西安电子科技大学 | Transformer fault diagnosis method based on case-based reasoning |
| CN103076526A (en) * | 2013-01-16 | 2013-05-01 | 国网电力科学研究院 | Fault diagnosis method based on transformer panoramic state information |
| CN103487514A (en) * | 2013-09-05 | 2014-01-01 | 昆明理工大学 | Online monitoring information aggregating method of transformer based on wavelet transform and evidence reasoning |
| CN103678765A (en) * | 2013-10-31 | 2014-03-26 | 上海交通大学 | Transformer operating state comprehensive evaluation method based on on-line monitoring |
| CN104362736B (en) * | 2014-09-17 | 2017-03-15 | 特变电工衡阳变压器有限公司 | A kind of Intelligent component cabinet and its monitoring method for intelligent transformer |
| CN105867346A (en) * | 2016-03-24 | 2016-08-17 | 国家电网公司 | State evaluation and maintenance decision support method for transformer |
| CN106324406A (en) * | 2016-09-21 | 2017-01-11 | 许继集团有限公司 | Transformer direct-current magnetic bias fault diagnosis method and device |
| CN106932712A (en) * | 2016-12-30 | 2017-07-07 | 江苏南瑞泰事达电气有限公司 | A kind of circuit breaker failure diagnostic method based on improvement Fuzzy Petri Net |
Non-Patent Citations (6)
| Title |
|---|
| 董立新 等: "模糊粗糙集数据挖掘方法在电力变压器故障诊断中的应用研究——基于油中溶解气体的分析诊断", 《电力系统及其自动化学报》 * |
| 蔡虹 等: "一种基于粗糙-模糊集理论的知识获取方法", 《电脑知识与技术》 * |
| 赵小霞: "变压器检修策略的智能推理系统", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 陈尔奎等: "基于专家系统的变压器故障诊断", 《控制工程》 * |
| 项新建: "基于粗糙集理论的变压器故障诊断专家系统研究", 《仪器仪表学报》 * |
| 魏丽峰等: "浅谈专家系统在干式变压器故障诊断系统中的应用", 《山西电力》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146093A (en) * | 2018-08-08 | 2019-01-04 | 成都保源酷码科技有限公司 | A kind of electric power equipment on-site exploration method based on study |
| CN109002672A (en) * | 2018-09-30 | 2018-12-14 | 珠海市运泰利自动化设备有限公司 | A kind of design method of the intelligent producing line based on optic test |
| CN110609187A (en) * | 2019-09-21 | 2019-12-24 | 厦门加华电力科技有限公司 | Intelligent management system based on SF6 electrical equipment data detection and intelligent analysis |
| CN111458604A (en) * | 2019-12-27 | 2020-07-28 | 广东电网有限责任公司电力科学研究院 | Transformer self-sensing-based oscillation type lightning impulse test system and method |
| CN111983523A (en) * | 2020-08-24 | 2020-11-24 | 国网上海市电力公司 | Transformer running state data acquisition and analysis system and method based on big data platform |
| CN114459529A (en) * | 2020-11-09 | 2022-05-10 | 特变电工京津冀智能科技有限公司 | Intelligent maintenance device of oil-filled bushing, transformer and power transformation system |
| CN112652138A (en) * | 2020-12-16 | 2021-04-13 | 国网安徽省电力有限公司检修分公司 | Large transformer fire alarm early warning method based on same quantity comparison |
| CN112859803A (en) * | 2021-01-04 | 2021-05-28 | 中车青岛四方车辆研究所有限公司 | Detection equipment and health state evaluation method for bicycle brake control device |
| CN114252724A (en) * | 2022-03-02 | 2022-03-29 | 山东和兑智能科技有限公司 | Intelligent detection method and detection system for transformer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108051709A (en) | Transformer state online evaluation analysis method based on artificial intelligence technology | |
| CN102368634B (en) | Unified information platform system for state monitoring of intelligent transformer substation | |
| CN105891629B (en) | A kind of discrimination method of transformer equipment failure | |
| CN104020754B (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
| CN109765883B (en) | Power distribution automation terminal operation state evaluation and fault diagnosis method | |
| CN106199305A (en) | Underground coal mine electric power system dry-type transformer insulation health state evaluation method | |
| CN109102171A (en) | A kind of substation equipment condition intelligent evaluation system and method based on big data | |
| CN107358366B (en) | Distribution transformer fault risk monitoring method and system | |
| CN101446827B (en) | Process fault analysis device of process industry system and method therefor | |
| CN103218695A (en) | Secondary equipment intelligence state evaluation diagnostic system and method thereof | |
| CN107346466A (en) | A kind of control method and device of electric power dispatching system | |
| CN103926490B (en) | A kind of power transformer error comprehensive diagnosis method with self-learning function | |
| CN106199494A (en) | A kind of intelligent diagnosis system based on metering device fault | |
| CN103078403B (en) | On-line state evaluation method for secondary system of intelligent substation | |
| CN103164775A (en) | Automatic evaluation platform and method for power grid equipment status | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| CN107967520A (en) | A kind of synthetical condition assessment theoretical method towards novel intelligent station relay protection device | |
| CN102866313A (en) | Power tunnel cable running state comprehensive monitoring method | |
| CN105044499A (en) | Method for detecting transformer state of electric power system equipment | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN106997513A (en) | The distribution net equipment state evaluation system analyzed based on big data | |
| CN110674189A (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| CN108414877A (en) | One kind to transformer fault for carrying out pre-warning system and method | |
| CN103616877B (en) | Monitoring diagnostic method and system for energy pipe network | |
| CN106602731A (en) | Electric power equipment state monitoring diagnosis system based on cloud end |
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: 20180518 |
|
| RJ01 | Rejection of invention patent application after publication |