CN110174499A - A kind of prediction technique and device of sulfur hexafluoride electrical equipment Air Leakage Defect - Google Patents
A kind of prediction technique and device of sulfur hexafluoride electrical equipment Air Leakage Defect Download PDFInfo
- Publication number
- CN110174499A CN110174499A CN201910620434.4A CN201910620434A CN110174499A CN 110174499 A CN110174499 A CN 110174499A CN 201910620434 A CN201910620434 A CN 201910620434A CN 110174499 A CN110174499 A CN 110174499A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- defect
- air leakage
- electrical equipment
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 211
- 229910018503 SF6 Inorganic materials 0.000 title claims abstract description 82
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 title claims abstract description 78
- 229960000909 sulfur hexafluoride Drugs 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013480 data collection Methods 0.000 claims abstract description 25
- 239000013598 vector Substances 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 6
- 238000001556 precipitation Methods 0.000 claims description 4
- 239000007789 gas Substances 0.000 description 25
- 238000010586 diagram Methods 0.000 description 12
- 239000000203 mixture Substances 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000009413 insulation Methods 0.000 description 4
- 229910052760 oxygen Inorganic materials 0.000 description 4
- 239000001301 oxygen Substances 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- 239000005864 Sulphur Substances 0.000 description 2
- 238000010891 electric arc Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- WRQGPGZATPOHHX-UHFFFAOYSA-N ethyl 2-oxohexanoate Chemical compound CCCCC(=O)C(=O)OCC WRQGPGZATPOHHX-UHFFFAOYSA-N 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 231100000252 nontoxic Toxicity 0.000 description 2
- 230000003000 nontoxic effect Effects 0.000 description 2
- 230000009965 odorless effect Effects 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 230000001988 toxicity Effects 0.000 description 2
- 231100000419 toxicity Toxicity 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
- G01N33/0044—Sulphides, e.g. H2S
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0063—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a threshold to release an alarm or displaying means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Combustion & Propulsion (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Biochemistry (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The application discloses the prediction technique and device of a kind of sulfur hexafluoride electrical equipment Air Leakage Defect, and method includes: to obtain the Air Leakage Defect related data of sulfur hexafluoride electrical equipment;Air Leakage Defect related data is merged, obtains space-time data collection, it includes multiple data, the corresponding feature of the data that space-time data, which is concentrated,;Clock synchronization null data set carries out feature selecting, obtains the first data subset;Defect time prediction model is constructed using xgboost algorithm or lightgbm algorithm;According to the prediction object set of the time data configuration defect time prediction model in the first data subset;Defect time prediction model is trained using the first data subset and prediction object set;The time of origin of sulfur hexafluoride electrical equipment Air Leakage Defect is predicted using the defect time prediction model after training.This method and device can reduce the incidence of electrical equipment Air Leakage Defect, ensure the normal operation of electrical equipment.
Description
Technical field
This application involves sulfur hexafluoride electrical equipment technical fields, and in particular to a kind of sulfur hexafluoride electrical equipment gas leakage is scarce
Sunken prediction technique and device.
Background technique
Sulfur hexafluoride (SF6), it is a kind of colourless, odorless, nontoxic, non-ignitable stabilizing gas, dielectric strength is same air pressure
2-3 times of lower air, arc extinguishing ability are 100 times of air, are typically used as the dielectric of electrical equipment.But it is electrically setting
Under standby large power electric arc electric discharge either high temperature action, SF6Gas is very easy to decompose.When sulfur hexafluoride electrical equipment occurs
When Air Leakage Defect, SF6A small amount of oxygen, moisture and the solid insulation being mixed in the decomposition product and sulfur hexafluoride electrical equipment of gas are situated between
The reaction of the further occurrences such as matter, generates SO2, HF and H2The products such as S, these products largely have toxicity and strong corrosive.
So Air Leakage Defect will seriously reduce the insulating properties of electrical equipment, while also polluting surrounding enviroment.Therefore, to sulfur hexafluoride electricity
The prediction of gas equipment Air Leakage Defect is extremely important.
Currently, in the prior art, by SF in sulfur hexafluoride electrical equipment6Oxygen in gas decomposition product and equipment
Gas and water point and the product of solid dielectric insulation reaction are monitored, and when Air Leakage Defect occurs for electrical equipment, are made corresponding
Leakage alarm reaction.This method can only can just make corresponding alarm after electrical equipment has occurred and that Air Leakage Defect, and
Look-ahead cannot be carried out to the Air Leakage Defect of electrical equipment.
So how to realize the look-ahead to the Air Leakage Defect of electrical equipment, have become those skilled in the art urgently
Technical problem to be solved.
Summary of the invention
This application provides the prediction techniques and device of a kind of sulfur hexafluoride electrical equipment Air Leakage Defect, to solve existing skill
In art, corresponding alarm can only can be just made after electrical equipment has occurred and that Air Leakage Defect, it can not be to electrical equipment
Air Leakage Defect carries out the problem of look-ahead.
In a first aspect, the application provides a kind of prediction technique of sulfur hexafluoride electrical equipment Air Leakage Defect, comprising:
The Air Leakage Defect related data of sulfur hexafluoride electrical equipment is obtained, the related data includes at least generation gas leakage and lacks
Sunken time data, device data, meteorological data and geodata;
The Air Leakage Defect related data is merged, space-time data collection is obtained, it includes multiple data that the space-time data, which is concentrated,
The corresponding feature of one data;
Feature selecting is carried out to the space-time data collection, obtains the first data subset;
Defect time prediction model is constructed using xgboost algorithm or lightgbm algorithm;
According to the prediction object set of defect time prediction model described in the time data configuration in first data subset;
The defect time prediction model is trained using first data subset and the prediction object set;
Using the defect time prediction model after training to the time of origin of the sulfur hexafluoride electrical equipment Air Leakage Defect
It is predicted.
Optionally, the defect time prediction model using after training is to the sulfur hexafluoride electrical equipment Air Leakage Defect
Time of origin predicted, comprising:
The operation related data of sulfur hexafluoride electrical equipment is obtained, the related data includes at least the time of equipment operation
Data, device data, meteorological data and geodata;
The operation related data is merged, obtains operation data collection, the operation data collection includes at least one data, and one
A corresponding feature of the data;
Feature selecting is carried out to the operation data collection, obtains the second data subset;
Second data subset is input in the defect time prediction model after the training, is predicted described lithium
The time of origin of sulphur electrical equipment Air Leakage Defect.
Optionally, described to use first data subset and the prediction object set to the defect time prediction model
It is trained, comprising:
Using first data subset as the input of the defect time prediction model, using the prediction object set as
The output of the defect time prediction model is trained the defect time prediction model.
It is optionally, described using the first data subset as the input of the defect time prediction model, comprising:
ONE-HOT coding is carried out to each data in first data subset, the vector after encoding is described in
The input of defect time prediction model.
Optionally, defect time prediction model described in the time data configuration according in first data subset
Predict object set, comprising:
According to each group of time data in first data subset, according to the following formula, calculate and the time data pair
The prediction target T answered:
T=D2-D1,
Wherein, D2To call time on the Air Leakage Defect, D1It puts into operation the time for the sulfur hexafluoride electrical equipment.
Optionally, described that second data subset is input in the defect time prediction model, it predicts described lithium
The time of origin of sulphur electrical equipment Air Leakage Defect, comprising:
ONE-HOT coding is carried out to each data in second data subset;
Vector after coding is input in the defect time prediction model;
The defect time prediction model exports the time of origin of the sulfur hexafluoride electrical equipment Air Leakage Defect.
Optionally, the time data include the time when Air Leakage Defect occurs, time when equipment investment uses
With equipment operation duration, the time includes date and hour;
The device data includes the device parameter data and equipment Air Leakage Defect positional number when the Air Leakage Defect occurs
According to;
The meteorological data includes maximum temperature, lowest temperature in 24 hours of equipment location when the Air Leakage Defect occurs
Degree, highest humidity, minimum humidity, maximum wind velocity, minimum windspeed and precipitation data;
The geodata includes the longitude and latitude data and elevation data of the Air Leakage Defect spot.
Second aspect, the application provide a kind of prediction meanss of sulfur hexafluoride electrical equipment Air Leakage Defect, comprising:
Data acquisition module, for obtaining the Air Leakage Defect related data of sulfur hexafluoride electrical equipment, the related data
Including at least time data, device data, meteorological data and the geodata that Air Leakage Defect occurs;
Data fusion module obtains space-time data collection, the space-time data for merging the Air Leakage Defect related data
Concentrating includes multiple data, the corresponding feature of the data;
Feature selection module obtains the first data subset for carrying out feature selecting to the space-time data collection;
Model buildings module, for constructing defect time prediction model using xgboost algorithm or lightgbm algorithm;
Data configuration module, for the defect time prediction according to the time data configuration in first data subset
The prediction object set of model;
Model training module, for pre- to the defect time using first data subset and the prediction object set
Model is surveyed to be trained;
Prediction module, for using the defect time prediction model after training to lack the sulfur hexafluoride electrical equipment gas leakage
Sunken time of origin is predicted.
From the above technical scheme, the prediction technique of a kind of sulfur hexafluoride electrical equipment Air Leakage Defect provided by the present application
Method and and device, which comprises obtain the Air Leakage Defect related data of sulfur hexafluoride electrical equipment, the related data
Including at least time data, device data, meteorological data and the geodata that Air Leakage Defect occurs;Merge the Air Leakage Defect phase
Data are closed, obtain space-time data collection, it includes multiple data, the corresponding feature of the data that the space-time data, which is concentrated,;
Feature selecting is carried out to the space-time data collection, obtains the first data subset;Use xgboost algorithm or lightgbm algorithm structure
Build defect time prediction model;According to defect time prediction model described in the time data configuration in first data subset
Predict object set;The defect time prediction model is instructed using first data subset and the prediction object set
Practice;It is carried out using time of origin of the defect time prediction model after training to the sulfur hexafluoride electrical equipment Air Leakage Defect pre-
It surveys.By the application method, the Air Leakage Defect that electrical equipment may occur can be predicted in advance, then can make corresponding prevention
Measure, therefore can reduce the incidence of sulfur hexafluoride electrical equipment Air Leakage Defect, it is provided more for the normal operation of electrical equipment
Big guarantee.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without any creative labor,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is the prediction technique of the application sulfur hexafluoride electrical equipment Air Leakage Defect shown according to an exemplary embodiment
Flow chart;
Fig. 2 is the detailed step schematic diagram of step S7 in Fig. 1;
Fig. 3 is a kind of composition schematic diagram of the prediction meanss of sulfur hexafluoride electrical equipment Air Leakage Defect provided by the present application;
Fig. 4 is the composition schematic diagram of prediction module 700 in Fig. 3;
Fig. 5 is the composition schematic diagram of model training module 600 in Fig. 3;
Fig. 6 is the composition schematic diagram that submodule 720 is predicted in Fig. 4;
Fig. 7 is the composition schematic diagram of data acquisition module 100 in Fig. 3.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiment of the application, instead of all the embodiments.Base
Embodiment in the application, those of ordinary skill in the art are obtained all without making creative work
Other embodiments shall fall in the protection scope of this application.
Sulfur hexafluoride (SF6), it is a kind of colourless, odorless, nontoxic, non-ignitable stabilizing gas, dielectric strength is same air pressure
2-3 times of lower air, arc extinguishing ability are 100 times of air, are typically used as the dielectric of electrical equipment.But it is electrically setting
Under standby large power electric arc electric discharge either high temperature action, SF6Gas is very easy to decompose.When sulfur hexafluoride electrical equipment occurs
When Air Leakage Defect, SF6A small amount of oxygen, moisture and the solid insulation being mixed in the decomposition product and sulfur hexafluoride electrical equipment of gas are situated between
The reaction of the further occurrences such as matter, generates SO2, HF and H2The products such as S, these products largely have toxicity and strong corrosive.
So Air Leakage Defect will seriously reduce the insulating properties of electrical equipment, while also polluting surrounding enviroment.Therefore, to sulfur hexafluoride electricity
The prediction of gas equipment Air Leakage Defect is extremely important.
Currently, in the prior art, by SF in sulfur hexafluoride electrical equipment6Oxygen in gas decomposition product and equipment
Gas and water point and the product of solid dielectric insulation reaction are monitored, and when Air Leakage Defect occurs for electrical equipment, are made corresponding
Leakage alarm reaction.This method can only can just make corresponding alarm after electrical equipment has occurred and that Air Leakage Defect, and
Look-ahead cannot be carried out to the Air Leakage Defect of electrical equipment.
In view of this, the application provides the prediction technique and device of a kind of sulfur hexafluoride electrical equipment Air Leakage Defect, with solution
Certainly in the prior art, corresponding alarm can only can be just made after electrical equipment has occurred and that Air Leakage Defect, it can not be to electricity
The Air Leakage Defect of gas equipment carries out the problem of look-ahead.
In a first aspect, Fig. 1 is the application sulfur hexafluoride electrical equipment Air Leakage Defect shown according to an exemplary embodiment
Prediction technique flow chart, as shown in Figure 1, the application provides a kind of prediction technique of sulfur hexafluoride electrical equipment Air Leakage Defect,
Include the following steps:
S1: obtaining the Air Leakage Defect related data of sulfur hexafluoride electrical equipment, and related data includes at least generation gas leakage and lacks
Sunken time data, device data, meteorological data and geodata;
S2: fusion Air Leakage Defect related data obtains space-time data collection, and it includes multiple data that space-time data, which is concentrated, and one
Data correspond to a feature;
S3: clock synchronization null data set carries out feature selecting, obtains the first data subset;
S4: defect time prediction model is constructed using xgboost algorithm or lightgbm algorithm;
S5: according to the prediction object set of the time data configuration defect time prediction model in the first data subset;
S6: defect time prediction model is trained using the first data subset and prediction object set;
S7: using the defect time prediction model after training to the time of origin of sulfur hexafluoride electrical equipment Air Leakage Defect into
Row prediction.
Optionally, time data include time when Air Leakage Defect occurs, and time and equipment when equipment investment uses transport
Row duration, time include date and hour;
Device data includes the device parameter data and equipment Air Leakage Defect position data when Air Leakage Defect occurs;
Meteorological data includes maximum temperature, minimum temperature, highest in 24 hours of equipment location when Air Leakage Defect occurs
Humidity, minimum humidity, maximum wind velocity, minimum windspeed and precipitation data;
Geodata includes the longitude and latitude data and elevation data of the Air Leakage Defect spot.
It should be noted that related data provided by the present application include at least time data, device data, meteorological data and
Geodata, related data can also include other data associated with electrical equipment gas leakage, and the application is not especially limited.
It should also be noted that, the data class that time data, device data, meteorological data and geodata are included respectively shows
Meaning property for example, can also include other and time, equipment, meteorology and geographically relevant data, the application not make to have
Body limits.
Method provided in this embodiment carries out analysis by the historical data to sulfur hexafluoride electrical equipment Air Leakage Defect and grinds
Study carefully, establish defect time prediction model and carry out repetition training, uses the defect time prediction model prediction six after repetition training
The time that sulfur fluoride electrical equipment Air Leakage Defect occurs.The method can according to the actual situation, at any time to the generation of Air Leakage Defect
Time is predicted, convenient and efficient.Also, for predict come Air Leakage Defect time of origin, relevant staff or
Correlation machine can make corresponding improvement movement or the precautionary measures in advance.Therefore, this method can reduce sulfur hexafluoride electricity
The incidence of gas equipment Air Leakage Defect provides bigger guarantee for the normal operation of equipment.
Optionally, Fig. 2 is the detailed step schematic diagram of step S7 in Fig. 1, as shown in Fig. 2, when using the defect after training
Between prediction model the time of origin of sulfur hexafluoride electrical equipment Air Leakage Defect is predicted, include the following steps:
S71: obtaining the operation related data of sulfur hexafluoride electrical equipment, and related data includes at least the time of equipment operation
Data, device data, meteorological data and geodata;
S72: fusion operation related data obtains operation data collection, operation data collection includes at least one data, an institute
State the corresponding feature of data;
S73: feature selecting is carried out to operation data collection, obtains the second data subset;
S74: the second data subset is input in the defect time prediction model after the training, prediction sulfur hexafluoride electricity
The time of origin of gas equipment Air Leakage Defect.
It should be noted that being the crucial letter for concentrating operation data to operation data and the effect for carrying out feature selecting
Breath extracts, and so the second data subset is input in the defect time prediction model after training, the defect hair predicted
The raw time can be more accurate, can remove influence of noise.
Optionally, defect time prediction model is trained using first data subset and prediction object set, is wrapped
It includes:
Using the first data subset as the input of defect time prediction model, to predict object set as defect time prediction
The output of model is trained defect time prediction model.
It is to the algorithm in defect time prediction model it should be noted that being trained to defect time prediction model
A continuous modified process.
Optionally, using the first data subset as the input of the defect time prediction model, comprising:
ONE-HOT coding is carried out to each data in the first data subset, using the vector after encoding as the defect time
The input of prediction model.
It is easily understood that there are several data in the first data subset, just there are several corresponding vectors after coding, with coding
Input of institute's directed quantity as defect time prediction model afterwards.
Optionally, according to the prediction target of the time data configuration defect time prediction model in first data subset
Collection, comprising:
According to each group of time data in first data subset, according to the following formula, calculate and the time data pair
The prediction target T answered:
T=D2-D1,
Wherein, D2To call time on Air Leakage Defect, D1It puts into operation the time for sulfur hexafluoride electrical equipment.
It should be noted that each Air Leakage Defect corresponds to one group of time data, every group of time number in the first data subset
According to all including calling time to put into operation the time with sulfur hexafluoride electrical equipment on Air Leakage Defect, lacked by each gas leakage is calculated
Fall into corresponding prediction target, all prediction target predicted composition object sets.Predict that object set is a known standard, institute
With using the first data subset as the input of defect time prediction model, to predict object set as defect time prediction model
Output, defect time prediction model is trained, training after defect time prediction model then can be to running six
The time of origin of sulfur fluoride electrical equipment Air Leakage Defect is predicted.
Optionally, the second data subset is input in defect time prediction model, prediction sulfur hexafluoride electrical equipment leakage
The time of origin of gas defect, comprising:
ONE-HOT coding is carried out to each data in the second data subset;
Vector after coding is input in defect time prediction model;
The time of origin of defect time prediction model output sulfur hexafluoride electrical equipment Air Leakage Defect.
Method provided by the present application carries out analysis by the historical data to sulfur hexafluoride electrical equipment Air Leakage Defect and grinds
Study carefully, establish defect time prediction model and carries out repetition training, the operation data of running sulfur hexafluoride electrical equipment is defeated
Enter in the defect time prediction model to after repetition training, defect time prediction model exports sulfur hexafluoride electrical equipment gas leakage and lacks
Fall into the time occurred.The method can according to the actual situation at any time predict the time of origin of Air Leakage Defect, convenient fast
It is prompt.Also, for predict come Air Leakage Defect time of origin, relevant staff or correlation machine can be made in advance
Corresponding improvement movement or the precautionary measures.Therefore, this method can reduce the generation of sulfur hexafluoride electrical equipment Air Leakage Defect
Rate provides bigger guarantee for the normal operation of equipment.
Second aspect, Fig. 3 are a kind of group of the prediction meanss of sulfur hexafluoride electrical equipment Air Leakage Defect provided by the present application
At schematic diagram, as shown in figure 3, the application provides a kind of prediction meanss 0000 of sulfur hexafluoride electrical equipment Air Leakage Defect, comprising:
Data acquisition module 100, for obtaining the Air Leakage Defect related data of sulfur hexafluoride electrical equipment, the dependency number
According to time data, device data, meteorological data and the geodata for including at least generation Air Leakage Defect;
Data fusion module 200 obtains space-time data collection, the space-time for merging the Air Leakage Defect related data
It include multiple data, the corresponding feature of the data in data set;
Feature selection module 300 obtains the first data subset for carrying out feature selecting to the space-time data collection;
Model buildings module 400, for constructing defect time prediction mould using xgboost algorithm or lightgbm algorithm
Type;
Data configuration module 500, for the defect time according to the time data configuration in first data subset
The prediction object set of prediction model;
Model training module 600, when for using first data subset and the prediction object set to the defect
Between prediction model be trained;
Prediction module 700, for using the defect time prediction model after training to leak the sulfur hexafluoride electrical equipment
The time of origin of gas defect is predicted.
Optionally, Fig. 4 is the composition schematic diagram of prediction module 700 in Fig. 3, as shown in figure 4, prediction module includes:
Operation data submodule 710 is obtained, for obtaining the operation related data of sulfur hexafluoride electrical equipment, related data
Including at least time data, device data, meteorological data and the geodata of equipment operation;
Data fusion module 200 is also used to merge the operation related data, obtains operation data collection, the operation number
It include at least one data, the corresponding feature of the data according to collection;
Feature selection module 300 is also used to carry out feature selecting to operation data collection, obtains the second data subset;
Predict submodule 720, for the second data subset to be input in the defect time prediction model after training, prediction
The time of origin of the sulfur hexafluoride electrical equipment Air Leakage Defect.
It should be noted that data fusion module 200 and feature selection module 300 are multiplexed in prediction module 700, institute
To be shown by the dashed box in Fig. 4.
Optionally, Fig. 5 is the composition schematic diagram of model training module 600 in Fig. 3, as shown in figure 4, model training module
600, comprising:
Input submodule 610, for the first data subset to be input in defect time prediction model;
Output sub-module 620, for that will predict output of the object set as defect time prediction model;
Training submodule 630, for being trained to defect time prediction model.
Optionally, input submodule, comprising:
Coding unit, for carrying out ONE-HOT coding to each data in the first data subset, with the vector after coding
Input as defect time prediction model.
Optionally, data configuration module, comprising:
Target formation submodule is predicted, for according to the following formula, counting according to each group of time data in the first data subset
Calculate prediction target T corresponding with time data:
T=D2-D1,
Wherein, D2To call time on the Air Leakage Defect, D1It puts into operation the time for the sulfur hexafluoride electrical equipment.
Optionally, Fig. 6 is the composition schematic diagram that submodule 720 is predicted in Fig. 4, as shown in fig. 6, prediction submodule 720, packet
It includes:
Coding unit 721 is also used to carry out ONE-HOT coding to each data in the second data subset;
Subelement 722 is inputted, for the vector after coding to be input in defect time prediction model;
Subelement 723 is exported, the generation for defect time prediction model output sulfur hexafluoride electrical equipment Air Leakage Defect
Time.
It should be noted that the coding unit in coding unit 721 and input submodule is multiplexing, so using in Fig. 6
Dotted line frame is shown.
Optionally, Fig. 7 is the composition schematic diagram of data acquisition module 100 in Fig. 3, as shown in fig. 7, data acquisition module
100, it includes at least:
Time data acquisition submodule 110, for obtain Air Leakage Defect occur when time, equipment investment use when
Between and equipment operation duration, the time includes date and hour;
Device data acquisition submodule 120, for obtaining device parameter data and equipment gas leakage when Air Leakage Defect occurs
Defective locations data;
Meteorological data acquisition submodule 130, highest in 24 hours of equipment location when for obtaining Air Leakage Defect generation
Temperature, minimum temperature, highest humidity, minimum humidity, maximum wind velocity, minimum windspeed and precipitation data;
Geodata acquisition submodule 140, for obtaining the longitude and latitude data and elevation data of Air Leakage Defect spot.
The method and device that the application of this reality provides, is carried out by the historical data to sulfur hexafluoride electrical equipment Air Leakage Defect
Analysis and research, establish defect time prediction model and carry out repetition training, by the operation of running sulfur hexafluoride electrical equipment
Data are input in the defect time prediction model after repetition training, and defect time prediction model exports sulfur hexafluoride electrical equipment
The time that Air Leakage Defect occurs.The method can according to the actual situation at any time predict the time of origin of Air Leakage Defect, square
Just quick.Also, for predict come Air Leakage Defect time of origin, relevant staff or correlation machine can shift to an earlier date
Make corresponding improvement movement or the precautionary measures.Therefore, this method can reduce sulfur hexafluoride electrical equipment Air Leakage Defect
Incidence provides bigger guarantee for the normal operation of equipment.
It is required that those skilled in the art can be understood that the technology in the embodiment of the present invention can add by software
The mode of general hardware platform realize.Based on this understanding, the technical solution in the embodiment of the present invention substantially or
Say that the part that contributes to existing technology can be embodied in the form of software products, which can deposit
Storage is in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that computer equipment (can be with
It is personal computer, server or the network equipment etc.) execute certain part institutes of each embodiment of the present invention or embodiment
The method stated.
Same and similar part may refer to each other between each embodiment in this specification.Especially for embodiment
Speech, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to saying in embodiment of the method
It is bright.
Claims (8)
1. a kind of prediction technique of sulfur hexafluoride electrical equipment Air Leakage Defect, which is characterized in that the described method includes:
The Air Leakage Defect related data of sulfur hexafluoride electrical equipment is obtained, the related data, which includes at least, occurs Air Leakage Defect
Time data, device data, meteorological data and geodata;
The Air Leakage Defect related data is merged, obtains space-time data collection, it includes multiple data that the space-time data, which is concentrated, and one
The corresponding feature of the data;
Feature selecting is carried out to the space-time data collection, obtains the first data subset;
Defect time prediction model is constructed using xgboost algorithm or lightgbm algorithm;
According to the prediction object set of defect time prediction model described in the time data configuration in first data subset;
The defect time prediction model is trained using first data subset and the prediction object set;
It is carried out using time of origin of the defect time prediction model after training to the sulfur hexafluoride electrical equipment Air Leakage Defect
Prediction.
2. the method according to claim 1, wherein the defect time prediction model using after training is to institute
The time of origin for stating sulfur hexafluoride electrical equipment Air Leakage Defect is predicted, comprising:
The operation related data of sulfur hexafluoride electrical equipment is obtained, the related data includes at least the time that Air Leakage Defect occurs
Data, device data, meteorological data and geodata;
The operation related data is merged, operation data collection is obtained, the operation data collection includes at least one data, an institute
State the corresponding feature of data;
Feature selecting is carried out to the operation data collection, obtains the second data subset;
Second data subset is input in the defect time prediction model after the training, predicts the sulfur hexafluoride electricity
The time of origin of gas equipment Air Leakage Defect.
3. the method according to claim 1, wherein described use first data subset and the prediction mesh
Mark collection is trained the defect time prediction model, comprising:
Using first data subset as the input of the defect time prediction model, using the prediction object set described in
The output of defect time prediction model is trained the defect time prediction model.
4. according to the method described in claim 3, it is characterized in that, described pre- using the first data subset as the defect time
Survey the input of model, comprising:
ONE-HOT coding is carried out to each data in first data subset, using the vector after encoding as the defect
The input of time prediction model.
5. the method according to claim 1, wherein the time data according in first data subset
Construct the prediction object set of the defect time prediction model, comprising:
According to each group of time data in first data subset, according to the following formula, calculate corresponding with the time data
Predict target T:
T=D2-D1,
Wherein, D2To call time on the Air Leakage Defect, D1It puts into operation the time for the sulfur hexafluoride electrical equipment.
6. according to the method described in claim 2, it is characterized in that, described be input to the defect time for the second data subset
In prediction model, the time of origin of the sulfur hexafluoride electrical equipment Air Leakage Defect is predicted, comprising:
ONE-HOT coding is carried out to each data in second data subset;
Vector after coding is input in the defect time prediction model;
The defect time prediction model exports the time of origin of the sulfur hexafluoride electrical equipment Air Leakage Defect.
7. the method according to claim 1, wherein the time data include when the Air Leakage Defect occurs
Time, time and equipment operation duration, the time when equipment investment uses include date and hour;
The device data includes the device parameter data and equipment Air Leakage Defect position data when the Air Leakage Defect occurs;
The meteorological data include maximum temperature in 24 hours of equipment location when the Air Leakage Defect occurs, minimum temperature,
Highest humidity, minimum humidity, maximum wind velocity, minimum windspeed and precipitation data;
The geodata includes the longitude and latitude data and elevation data of the Air Leakage Defect spot.
8. a kind of prediction meanss of sulfur hexafluoride electrical equipment Air Leakage Defect, which is characterized in that described device includes:
Data acquisition module, for obtaining the Air Leakage Defect related data of sulfur hexafluoride electrical equipment, the related data is at least
Time data, device data, meteorological data and geodata including Air Leakage Defect occurs;
Data fusion module obtains space-time data collection, the space-time data is concentrated for merging the Air Leakage Defect related data
Comprising multiple data, the corresponding feature of the data;
Feature selection module obtains the first data subset for carrying out feature selecting to the space-time data collection;
Model buildings module, for constructing defect time prediction model using xgboost algorithm or lightgbm algorithm;
Data configuration module, for the defect time prediction model according to the time data configuration in first data subset
Prediction object set;
Model training module, for using first data subset and the prediction object set to the defect time prediction mould
Type is trained;
Prediction module, for using the defect time prediction model after training to the sulfur hexafluoride electrical equipment Air Leakage Defect
Time of origin is predicted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910620434.4A CN110174499B (en) | 2019-07-10 | 2019-07-10 | Method and device for predicting air leakage defect of sulfur hexafluoride electrical equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910620434.4A CN110174499B (en) | 2019-07-10 | 2019-07-10 | Method and device for predicting air leakage defect of sulfur hexafluoride electrical equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110174499A true CN110174499A (en) | 2019-08-27 |
CN110174499B CN110174499B (en) | 2022-04-08 |
Family
ID=67699950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910620434.4A Active CN110174499B (en) | 2019-07-10 | 2019-07-10 | Method and device for predicting air leakage defect of sulfur hexafluoride electrical equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110174499B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259953A (en) * | 2020-01-15 | 2020-06-09 | 云南电网有限责任公司电力科学研究院 | Equipment defect time prediction method based on capacitive equipment defect data |
CN112525438A (en) * | 2020-10-15 | 2021-03-19 | 国网浙江省电力有限公司杭州供电公司 | SF (sulfur hexafluoride)6Air leakage monitoring method and system for density relay |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104319900A (en) * | 2014-11-17 | 2015-01-28 | 国网河南省电力公司南阳供电公司 | Method and system for monitoring intelligent transformer substation sulfur hexafluoride breaker characteristics |
CN104535277A (en) * | 2014-11-25 | 2015-04-22 | 国家电网公司 | Pressure monitoring method and system for SF6 gas |
US20150308938A1 (en) * | 2014-04-29 | 2015-10-29 | Karl Frederick Scheucher | Gas insulated switchgear monitoring apparatus and method |
CN105891684A (en) * | 2016-01-13 | 2016-08-24 | 武汉大学 | Gas insulated switchgear insulation state evaluation index system construction method |
CN107561425A (en) * | 2017-10-31 | 2018-01-09 | 国网重庆市电力公司电力科学研究院 | Characteristics of Partial Discharge recognition methods based on sulfur hexafluoride gas resolution characteristic |
CN109102171A (en) * | 2018-07-24 | 2018-12-28 | 上海欣影电力科技股份有限公司 | A kind of substation equipment condition intelligent evaluation system and method based on big data |
-
2019
- 2019-07-10 CN CN201910620434.4A patent/CN110174499B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150308938A1 (en) * | 2014-04-29 | 2015-10-29 | Karl Frederick Scheucher | Gas insulated switchgear monitoring apparatus and method |
CN104319900A (en) * | 2014-11-17 | 2015-01-28 | 国网河南省电力公司南阳供电公司 | Method and system for monitoring intelligent transformer substation sulfur hexafluoride breaker characteristics |
CN104535277A (en) * | 2014-11-25 | 2015-04-22 | 国家电网公司 | Pressure monitoring method and system for SF6 gas |
CN105891684A (en) * | 2016-01-13 | 2016-08-24 | 武汉大学 | Gas insulated switchgear insulation state evaluation index system construction method |
CN107561425A (en) * | 2017-10-31 | 2018-01-09 | 国网重庆市电力公司电力科学研究院 | Characteristics of Partial Discharge recognition methods based on sulfur hexafluoride gas resolution characteristic |
CN109102171A (en) * | 2018-07-24 | 2018-12-28 | 上海欣影电力科技股份有限公司 | A kind of substation equipment condition intelligent evaluation system and method based on big data |
Non-Patent Citations (3)
Title |
---|
杨芮等: "全封闭组合电器室SF6气体泄漏分布规律与气体检测布置策略", 《科学技术与工程》 * |
费韬等: "灰色理论在预测SF6组合电器漏气情况中的应用", 《四川电力技术》 * |
金海望等: "SF6渗漏类缺陷预警与处理的新技术", 《华北电力技术》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111259953A (en) * | 2020-01-15 | 2020-06-09 | 云南电网有限责任公司电力科学研究院 | Equipment defect time prediction method based on capacitive equipment defect data |
CN111259953B (en) * | 2020-01-15 | 2023-10-20 | 云南电网有限责任公司电力科学研究院 | Equipment defect time prediction method based on capacitive equipment defect data |
CN112525438A (en) * | 2020-10-15 | 2021-03-19 | 国网浙江省电力有限公司杭州供电公司 | SF (sulfur hexafluoride)6Air leakage monitoring method and system for density relay |
Also Published As
Publication number | Publication date |
---|---|
CN110174499B (en) | 2022-04-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Giri et al. | The situation room: Control center analytics for enhanced situational awareness | |
CN110174499A (en) | A kind of prediction technique and device of sulfur hexafluoride electrical equipment Air Leakage Defect | |
CN105100789B (en) | A kind of method for evaluating video quality | |
Jeong et al. | Establishment of wave information network of Korea (WINK) | |
CN110059356A (en) | A kind of bulk power grid intelligent control system and method based on big data and artificial intelligence | |
CN106295911B (en) | A kind of grid branch parameter evaluation method based on chromatographic assays | |
CN111582551A (en) | Method and system for predicting short-term wind speed of wind power plant and electronic equipment | |
Bertoni et al. | IRI-2001 model predictions compared with ionospheric data observed at Brazilian low latitude stations | |
CN111028633A (en) | Virtual reality-based power grid system training method and device and computer equipment | |
NL2032264A (en) | HASM-Based XCO2 Data Fusion Method And System | |
CN109541725B (en) | A kind of electricity power engineering weather monitoring method for early warning based on GIS | |
CN116523152B (en) | Float drift prediction method, device, equipment and medium | |
Drisya et al. | Deterministic prediction of surface wind speed variations | |
CN110348657A (en) | A kind of power grid typhoon disaster feature correlation analysis method and system | |
US20230176942A1 (en) | Fault detection and monitoring | |
CN111985087A (en) | Ocean circulation simulation system and method based on big data | |
CN115394029A (en) | Forest fire early warning system and method | |
Katada et al. | Integrated simulation of tsunami hazards | |
CN114387768A (en) | Tower inclination early warning method and device, computer equipment and storage medium | |
CN114114001A (en) | GIS equipment disconnecting switch mechanical state monitoring method and system | |
CN109447309A (en) | A kind of method for digging that waving data and system | |
CN110910968A (en) | Calculation method for space distribution condition of discharge decomposition product of high-voltage electrical equipment | |
Tao et al. | Sharing Overhead Transmission Line System Based on Public Perceptual Information | |
Vincent et al. | Hybrid Machine Learning Models for Storm Surge Prediction | |
Gunson et al. | Investigating conditions for rogue wave events from spectral wave observations and models |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |