CN106682081A - Multi-model based comprehensive transformer performance analysis system - Google Patents

Multi-model based comprehensive transformer performance analysis system Download PDF

Info

Publication number
CN106682081A
CN106682081A CN201611047360.2A CN201611047360A CN106682081A CN 106682081 A CN106682081 A CN 106682081A CN 201611047360 A CN201611047360 A CN 201611047360A CN 106682081 A CN106682081 A CN 106682081A
Authority
CN
China
Prior art keywords
analysis
data
module
result
transformer performance
Prior art date
Application number
CN201611047360.2A
Other languages
Chinese (zh)
Inventor
黄星
曹敏
赵薇
张林山
杨政
杨莉
Original Assignee
云南电网有限责任公司电力科学研究院
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 云南电网有限责任公司电力科学研究院 filed Critical 云南电网有限责任公司电力科学研究院
Priority to CN201611047360.2A priority Critical patent/CN106682081A/en
Publication of CN106682081A publication Critical patent/CN106682081A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21Design, administration or maintenance of databases
    • G06F16/211Schema design and management
    • G06F16/212Schema design and management with details for data modelling support
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22Indexing; Data structures therefor; Storage structures
    • G06F16/2282Tablespace storage structures; Management thereof
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/248Presentation of query results

Abstract

The invention discloses a multi-model based comprehensive transformer performance analysis system. The system comprises a base database, a model analysis module and a feature analysis module. The base database is used for storage of equipment records and acquisition and storage of oil chromatographic data; the model analysis module is used for analyzing the oil chromatographic data according to a characteristic gas method, a David triangle method, a TD diagramming method and a tri-ratio method to obtain analysis results; the feature analysis module is used for feature analysis of the analysis results of the model analysis module to obtain feature analysis results. The multi-model based comprehensive transformer performance analysis system has advantages of improvement of accuracy in transformer performance diagnosis, decrease of false alarm rate and improvement of diagnosis result reliability.

Description

Transformer performance overall analysis system based on multi-model

Technical field

The present invention relates to transformer performance analysis technical field, more specifically, it is related to a kind of change based on multi-model Depressor performance synthesis analysis system.

Background technology

With the fast development of China's industrial economy, electricity needs is grown at top speed, requirement also day of the reliable supply of electric power Benefit increases.Power transformer is the nucleus equipment of power system, has extremely important effect in the safe and reliable power supply of power network.Electricity Power transformer is a kind of static electrical equipment, is another for the alternating voltage (electric current) of a certain numerical value is become into frequency identical The equipment of the different voltage of one or more numerical value (electric current), power transformer breaks down and will directly influence power supply.

In recent years, developing rapidly with power construction, what power equipment put into increasingly increases.Such as the equipment event of transformer Barrier also increasingly increases, and due to existing preventive trial method in general, still can not effectively find to become when powered Hidden fault inside depressor, the current widely used gas chromatography of power system searches transformer insulated defect.Calculate Mode is main based on single Algorithm Analysis model, and total algorithm analysis model reference level is low, specialized equipment performance Analysis model, it is difficult to the need for meeting the information analysis of intelligent grid complex data and increasingly complicated equipment state analysis.

The content of the invention

It is an object of the invention to provide a kind of transformer performance overall analysis system based on multi-model, solve by list One problem that algorithm model result of calculation is unilateral, confidence level is not high.

In order to solve the above-mentioned technical problem, the present invention provides following technical scheme:

A kind of transformer performance overall analysis system based on multi-model that the present invention is provided, the system includes:

Basic database, for the storage of equipment account, for the acquisition and storage of oil colours modal data;

Model analysis module, for by characteristic gas method, David's trigonometry, TD figures method and three-ratio method to oil chromatography number According to the analysis for carrying out, analysis result is obtained;

Characteristics analysis module, for the analysis result of the model analysis module to be carried out into signature analysis, obtains feature point Analysis result.

Preferably, the above-mentioned transformer performance overall analysis system based on multi-model, the basic database is additionally operable to go through The storage of history fault data.

Preferably, the above-mentioned transformer performance overall analysis system based on multi-model, the system also includes:

Authentication module, for by the signature analysis result and the historical failure contrast verification, obtaining the result.

Preferably, the above-mentioned transformer performance overall analysis system based on multi-model, the system also includes:

Model analysis database, for storing analysis result, signature analysis result and the result.

Preferably, the above-mentioned transformer performance overall analysis system based on multi-model, the system also includes:

Data-pushing module, for the data in basic database and model analysis database to be pushed;

Application service module, for receiving the data that the data-pushing module is pushed.

Preferably, the above-mentioned transformer performance overall analysis system based on multi-model,

The application service module, is additionally operable to the displaying of data.

The transformer performance overall analysis system based on multi-model that the present invention is provided, incorporates various transformer performances point Analysis algorithm model, including oil chromatography characteristic gas method, David's trigonometry, TD figures method and three-ratio method, by algorithm above mould Type |input paramete, computation rule are encoded and integrated, and export transformer equipment status information.The method successfully combines many Individual algorithm model feature, and difference, advantage between each algorithm model are rationally make use of, optimize and formed a set of brand-new algorithm Model, comprehensive and accurate transformer equipment status information can be obtained by the brand-new algorithm model.It is logical so as to solve Cross the single problem that algorithm model result of calculation is unilateral, confidence level is not high.The transformer based on multi-model that the present invention is provided Can overall analysis system, raising transformer performance diagnostic accuracy, reduction rate of false alarm, raising diagnostic result confidence level.

Brief description of the drawings

Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description Accompanying drawing is briefly described, it should be apparent that, for those of ordinary skills, do not paying creative work Property on the premise of, other accompanying drawings can also be obtained according to these accompanying drawings.

Fig. 1 is the structural representation of the transformer performance overall analysis system based on multi-model provided in an embodiment of the present invention Figure.

Specific embodiment

A kind of transformer performance overall analysis system based on multi-model provided in an embodiment of the present invention, solves by list One problem that algorithm model result of calculation is unilateral, confidence level is not high.

In order that those skilled in the art more fully understand the technical scheme in the embodiment of the present invention, and make of the invention real Applying the above-mentioned purpose of example, feature and advantage can be more obvious understandable, below in conjunction with the accompanying drawings to the technology in the embodiment of the present invention Scheme is described in further detail.

Refer to the attached drawing 1, the figure shows the transformer performance comprehensive analysis based on multi-model provided in an embodiment of the present invention The structure of system, the system mainly includes:Basic database 1, model analysis module 2 and characteristics analysis module 3.

Basic database 1, for the storage of equipment account, for the acquisition and storage of oil colours modal data.Unit account of plant Mainly include transformer machine account information, for recording the model of transformer, installing and using place and installing and using situation.Oil colours Modal data mainly includes hydrogen, methane, ethane, ethene, acetylene, carbon monoxide and carbon dioxide, is for diagnosing change in model The parameter of depressor performance fault.In the embodiment of the present invention, by hydrogen, methane, ethane, ethene, second in analysis acquisition transformer Alkynes, carbon monoxide and carbon dioxide, carry out the analysis of transformer performance.

Model analysis module 2, for by characteristic gas method, David's trigonometry, TD figures method and three-ratio method to oil chromatography The analysis that data are carried out, obtains analysis result.Model analysis module 2 gathered characteristic gas method, David's trigonometry, TD figures method and Three-ratio method carries out operational analysis to the hydrogen, methane, ethane, ethene, acetylene, carbon monoxide and the carbon dioxide that obtain.

Characteristic gas method, detection parameter and transformer state corresponding relation, refer to table one:

Table one:

David's trigonometry, based on the respective proportion of CH4, C2H4, C2H2, the three kind of concentration of gas, and combines figure and determines Property failure judgement type, calculating process is easy directly perceived, and corresponding relation correspondence is shown in Table two.

Table two:

TD figure methods, when inside transformer has hyperthermia and superheating and discharging fault, C2H4/C2H6 ratios are larger, therefore Using C2H2/C2H4, two ratios of CH4/H2 form TD figures respectively as transverse and longitudinal coordinate, and analysis result includes:Overheat, corona Electric discharge, spark discharge and overheat, arc discharge and out of service.

Three-ratio method, takes hydrogen, acetylene, total hydrocarbon content, respectively with normal value threshold values (hydrogen:150μL/L;Acetylene:1μL/ L;Total hydrocarbon:150 μ L/L) contrast;With hydrogen upper one day, acetylene, total hydrocarbon content contrast, obtain rate of change, and with rate of change threshold values (hydrogen:10%;Acetylene:10%;Total hydrocarbon:10%) compare;Hydrogen, acetylene, total hydrocarbon are obtained with respect to gas production rate, and is produced with relative Gas velocity rate threshold values (hydrogen:10%;Acetylene:10%;Total hydrocarbon:10%) compare;If the content of any a certain gas is three more than Step compares all abnormal, then think the gas yield exception, output abnormality signal results.

By the analysis of characteristic gas method, David's trigonometry, TD figures method and three-ratio method, analysis result is respectively obtained.

Characteristics analysis module 3, for the analysis result of the model analysis module 2 to be carried out into signature analysis, obtains feature Analysis result.Characteristics analysis module 3 is to characteristic gas method, David's trigonometry, TD figures method and three-ratio method in model analysis module 2 Analysis result, carry out signature analysis.For same gas parameter algorithms of different model and identical category State- output result , retain output result;For same gas parameter algorithms of different model and different classes of State- output result, so as to be divided Analysis result.

To ensure the confidence level of analysis result, basic database is additionally operable to the storage of historical failure data.Historical failure is Refer to that transformer has broken down information history data.Historical failure data is stored, it is Transformer State Assessment to help Foundation is provided.Preferably, the transformer performance overall analysis system based on multi-model provided in an embodiment of the present invention also includes testing Card module 4, it is used to, by the signature analysis result and the historical failure data contrast verification, obtain the result.Judge Whether signature analysis result is identical with historical failure data, and carries out the checking of signature analysis result, improves signature analysis result Accuracy.

For ease of the preservation and inquiry of storage analysis result, signature analysis result and the result, in the embodiment of the present invention, The system also include model analysis database 5, model analysis database 5 be used for store analysis result, signature analysis result and The storage of the result.

It is further optimisation technique scheme, in the embodiment of the present invention, also including data-pushing module 6 and application service module 7.Data-pushing module 6, for the data in basic database 1 and model analysis database 5 to be pushed;Application service mould Block 7, for receiving the data that the data-pushing module is pushed.Data-pushing module 6 realizes application service module 7 with basic number According to the interaction of storehouse 1 and model analysis database 5, data reach application service module 7 in the way of active push and response are pushed. Preferably, application service module 7 is additionally operable to the displaying of data.

The transformer performance overall analysis system based on multi-model that the present invention is provided, incorporates various transformer performances point Analysis algorithm model, including oil chromatography characteristic gas method, David's trigonometry, TD figures method and three-ratio method, by algorithm above mould Type |input paramete, computation rule are encoded and integrated, and export transformer equipment status information.The method successfully combines many Individual algorithm model feature, and difference, advantage between each algorithm model are rationally make use of, optimize and formed a set of brand-new algorithm Model, comprehensive and accurate transformer equipment status information can be obtained by the brand-new algorithm model.It is logical so as to solve Cross the single problem that algorithm model result of calculation is unilateral, confidence level is not high.The transformer based on multi-model that the present invention is provided Can overall analysis system, raising transformer performance diagnostic accuracy, reduction rate of false alarm, raising diagnostic result confidence level.

Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment Divide mutually referring to what each embodiment was stressed is the difference with other embodiments.

Invention described above implementation method, is not intended to limit the scope of the present invention..It is any in the present invention Spirit and principle within modification, equivalent and the improvement made etc., should be included within the scope of the present invention.

Claims (6)

1. a kind of transformer performance overall analysis system based on multi-model, it is characterised in that the system includes:
Basic database, for the storage of equipment account, for the acquisition and storage of oil colours modal data;
Model analysis module, for being entered to oil colours modal data by characteristic gas method, David's trigonometry, TD figures method and three-ratio method Capable analysis, obtains analysis result;
Characteristics analysis module, for the analysis result of the model analysis module to be carried out into signature analysis, obtains signature analysis knot Really.
2. the transformer performance overall analysis system based on multi-model according to claim 1, it is characterised in that the base Plinth database is additionally operable to the storage of historical failure data.
3. the transformer performance overall analysis system based on multi-model according to claim 2, it is characterised in that the system System also includes:
Authentication module, for by the signature analysis result and the historical failure data contrast verification, obtaining the result.
4. the transformer performance overall analysis system based on multi-model according to claim 3, it is characterised in that the system System also includes:
Model analysis database, for storing the analysis result, signature analysis result and the result.
5. the transformer performance overall analysis system based on multi-model according to claim 4, it is characterised in that the system System also includes:
Data-pushing module, for the data in the basic database and model analysis database to be pushed;
Application service module, for receiving the data that the data-pushing module is pushed.
6. the transformer performance overall analysis system based on multi-model according to claim 5, it is characterised in that
The application service module, is additionally operable to the displaying of data.
CN201611047360.2A 2016-11-23 2016-11-23 Multi-model based comprehensive transformer performance analysis system CN106682081A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611047360.2A CN106682081A (en) 2016-11-23 2016-11-23 Multi-model based comprehensive transformer performance analysis system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611047360.2A CN106682081A (en) 2016-11-23 2016-11-23 Multi-model based comprehensive transformer performance analysis system

Publications (1)

Publication Number Publication Date
CN106682081A true CN106682081A (en) 2017-05-17

Family

ID=58866580

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611047360.2A CN106682081A (en) 2016-11-23 2016-11-23 Multi-model based comprehensive transformer performance analysis system

Country Status (1)

Country Link
CN (1) CN106682081A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107884647A (en) * 2017-11-06 2018-04-06 南京力通达电气技术有限公司 Transformer fault early warning system based on data mining
CN108717153A (en) * 2018-04-11 2018-10-30 大唐东北电力试验研究所有限公司 A kind of resultant fault diagnostic system suitable for wind power plant 35kV transformers

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102360474A (en) * 2011-10-27 2012-02-22 上海同城信息科技有限公司 Method and system for discriminating data in regulatory adjustment
CN103150633A (en) * 2013-03-18 2013-06-12 云南电网公司 Power equipment state real-time evaluation and auxiliary decision-making system
CN103308805A (en) * 2013-06-18 2013-09-18 重庆市电力公司万州供电局 Overhauling method and overhauling system for state of distribution transformer
CN103630768A (en) * 2012-08-23 2014-03-12 天津市电力公司 Method for diagnosing transformer fault in transformer station
CN104062524A (en) * 2014-06-09 2014-09-24 国家电网公司 Transformer insulating medium performance monitoring and analyzing method and system
CN104571099A (en) * 2015-01-26 2015-04-29 北京国能日新系统控制技术有限公司 Photovoltaic fault diagnosis system and method based on theoretical calculation and data analysis
CN104748838A (en) * 2015-03-27 2015-07-01 国家电网公司 Transformer winding loose determination system and method based on finite element analysis
CN105044499A (en) * 2015-07-01 2015-11-11 国家电网公司 Method for detecting transformer state of electric power system equipment
CN105446328A (en) * 2016-01-15 2016-03-30 廖金能 A generating set remote fault diagnosis and health monitor system and a data capture method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102360474A (en) * 2011-10-27 2012-02-22 上海同城信息科技有限公司 Method and system for discriminating data in regulatory adjustment
CN103630768A (en) * 2012-08-23 2014-03-12 天津市电力公司 Method for diagnosing transformer fault in transformer station
CN103150633A (en) * 2013-03-18 2013-06-12 云南电网公司 Power equipment state real-time evaluation and auxiliary decision-making system
CN103308805A (en) * 2013-06-18 2013-09-18 重庆市电力公司万州供电局 Overhauling method and overhauling system for state of distribution transformer
CN104062524A (en) * 2014-06-09 2014-09-24 国家电网公司 Transformer insulating medium performance monitoring and analyzing method and system
CN104571099A (en) * 2015-01-26 2015-04-29 北京国能日新系统控制技术有限公司 Photovoltaic fault diagnosis system and method based on theoretical calculation and data analysis
CN104748838A (en) * 2015-03-27 2015-07-01 国家电网公司 Transformer winding loose determination system and method based on finite element analysis
CN105044499A (en) * 2015-07-01 2015-11-11 国家电网公司 Method for detecting transformer state of electric power system equipment
CN105446328A (en) * 2016-01-15 2016-03-30 廖金能 A generating set remote fault diagnosis and health monitor system and a data capture method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107884647A (en) * 2017-11-06 2018-04-06 南京力通达电气技术有限公司 Transformer fault early warning system based on data mining
CN108717153A (en) * 2018-04-11 2018-10-30 大唐东北电力试验研究所有限公司 A kind of resultant fault diagnostic system suitable for wind power plant 35kV transformers

Similar Documents

Publication Publication Date Title
CN105074598B (en) The system and method predicted and diagnosed for transmission and disttrbution Asset State
Kamwa et al. Development of rule-based classifiers for rapid stability assessment of wide-area post-disturbance records
CN102368634B (en) Unified information platform system for state monitoring of intelligent transformer substation
CN103163420B (en) Power transformer intelligent online state judgment method
US8751421B2 (en) Machine learning for power grid
CN103678765B (en) Based on the running state of transformer comprehensive estimation method of on-line monitoring
Wang et al. A combined ANN and expert system tool for transformer fault diagnosis
CN104020754B (en) Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system
Zhang et al. An artificial neural network approach to transformer fault diagnosis
CN103136587B (en) Based on the power distribution network running status classifying identification method of support vector machine
CN101614775B (en) Evaluation system of transformer state based on multisource information integration and evaluation method thereof
CN102122823B (en) Method for positioning oscillation disturbance source in power system
CN105891629B (en) A kind of discrimination method of transformer equipment failure
Rudin et al. Machine learning for the New York City power grid
CN102289590B (en) Method for estimating operating state of SF6 high-voltage circuit breaker and intelligent system
CN104407268A (en) Abnormal electricity utilization judgment method based on abnormal analysis of electric quantity, voltage and current
CN101660969B (en) Intelligent fault diagnosis method for gear box
CN103901314B (en) Electrical transformer cores are grounded on-Line Monitor Device and its on-line monitoring method
AU2013201595B2 (en) Method and apparatus for harmonic state estimation in power system
CN102997838B (en) Transformer winding deformation fault diagnosis method based on frequency sweep short circuit characteristics
CN101789596B (en) Automatic detection method of power grid failure
CN102662113B (en) Comprehensive diagnosis method of oil-immersed transformer based on fault tree
CN103001328A (en) Fault diagnosis and assessment method of intelligent substation
CN103199514B (en) Method of eliminating ferromagnetic resonances
CN102928720B (en) Defect rate detecting method of oil immersed type main transformer

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: 20170517