CN112000831B - Abnormal data identification optimization method based on substation graph transformation - Google Patents
Abnormal data identification optimization method based on substation graph transformation Download PDFInfo
- Publication number
- CN112000831B CN112000831B CN202010811862.8A CN202010811862A CN112000831B CN 112000831 B CN112000831 B CN 112000831B CN 202010811862 A CN202010811862 A CN 202010811862A CN 112000831 B CN112000831 B CN 112000831B
- Authority
- CN
- China
- Prior art keywords
- abnormal data
- identification
- substation
- model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 74
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 230000009466 transformation Effects 0.000 title claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims abstract description 28
- 238000009826 distribution Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000004065 semiconductor Substances 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000005070 sampling Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/56—Information retrieval; Database structures therefor; File system structures therefor of still image data having vectorial format
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an abnormal data identification optimization method based on substation graph transformation, which comprises the steps of collecting basic information of substation related equipment and adding private attributes to perform graph transformation; constructing an anomaly identification model based on a least square strategy, and carrying out anomaly identification on the processed data in the graphic conversion process; if the abnormal data are identified, marking the abnormal data, eliminating the marked abnormal data by combining three-parameter distribution and gray prediction strategies, and outputting the optimized graph conversion result. According to the method, the abnormal data in the graphic conversion process is identified through the constructed abnormal identification model, the marked abnormal data is removed by combining the three-parameter distribution and the gray prediction strategy, the optimized graphic conversion result is output, the graphic conversion quality and efficiency are improved, the abnormal data is accurately positioned and removed, repeated work and error leakage of operation and maintenance personnel are avoided, and the danger coefficient of safe operation of equipment is reduced.
Description
Technical Field
The invention relates to the technical field of substation and graphic conversion, in particular to an abnormal data identification optimization method based on substation graphic conversion.
Background
The secondary system devices in the transformer substation are numerous in equipment and various cables, and the secondary system devices comprise a relay protection device, a safety automatic device, a fault wave recording device, a relay protection fault information system substation, a merging unit device, a network switch, an intelligent terminal device and the like. Secondary wiring in a transformer substation is very complex, and whether the secondary wiring is accurate or not is related to the operation safety of a power grid, so that the secondary wiring has a very important position. Such complex external wiring also presents significant challenges for installation and maintenance. In the daily work of secondary overhaul of the transformer, in order to ensure the safety of the power grid, equipment and personnel, secondary safety measures are often required to be taken before the work. Aiming at important protection screens such as a main transformer protection screen and a differential protection screen, the following safety measures are needed to be correspondingly adopted: opening the wiring on the inner side of the terminal strip, making safety isolation measures, and recovering in time after the work is finished. Because the secondary wiring of these protection screens is comparatively more, often meet the condition that is difficult for the hand down when recovering terminal strip inner line, perhaps can't see the wiring hole site. In practice, it is necessary to confirm the number of persons repeatedly, and sometimes the operator must grasp the plug by a tool such as a nipper pliers to perform the connection. The potential safety hazards such as misplacement are easy to generate, and the problems of high operation difficulty, low working efficiency and the like are caused.
At present, most of electric loops in a transformer substation are stored in the form of drawings, an electric graph cannot be associated with actual equipment (such as a device, electric equipment and the like), a large amount of drawing information is required to be read by operation and inspection debugging personnel during on-site maintenance, and the electric loop information related to certain equipment (such as the device, the electric equipment and the like) cannot be quickly searched, so that the working efficiency of the on-site operation and inspection debugging personnel is greatly reduced, and the working difficulty and the learning cost are increased; meanwhile, the problem of data errors is very easy to occur in the graphic conversion process, operation and maintenance personnel cannot find out, so that great potential safety hazards exist for substation equipment, and the unique positioning identification of equipment information cannot be realized if the accuracy of graphic conversion is not high.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present invention has been made in view of the above-described problems occurring in the prior art.
Therefore, the invention provides an abnormal data identification optimization method based on substation graph conversion, which can solve the problem that abnormal data errors exist in the existing graph conversion process but cannot be found, and the normal operation of equipment is affected.
In order to solve the technical problems, the invention provides the following technical scheme: collecting basic information of related equipment of a transformer substation and adding private attributes to perform graphic conversion; constructing an anomaly identification model based on a least square strategy, and carrying out anomaly identification on the processed data in the graphic conversion process; if the abnormal data are identified, marking the abnormal data, eliminating the marked abnormal data by combining three-parameter distribution and gray prediction strategies, and outputting the optimized graph conversion result.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: the graphic conversion comprises the steps of collecting the basic information of the transformer substation related equipment and storing the basic information into a database according to the actual physical hierarchy relation of the transformer substation; constructing an analysis model based on a linear programming criterion, and reading an electrical graph and a topological relation graph of an electrical loop in the basic information for analysis to obtain an electrical graph object; extracting text information of the electrical graphic object by utilizing a random forest strategy, and carrying out matching binding on the text information and the data in the database; correlating the matched information with the electrical graphic object to construct a secondary topological relation diagram; and extracting information of the electrical graphic object and the secondary topological relation diagram by using the random forest strategy, and adding a private attribute into the SVG text to generate a new SVG text.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: the database needs to be established with a basic information model in advance, including establishing a cell information model, a screen cabinet information model, a device information model and an electrical equipment information model in the transformer substation.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: establishing a cell information model, wherein the cell information model comprises a unique number of a cell in a database and a name of the cell in the transformer substation; the screen cabinet information model is established and comprises a unique number of a screen cabinet in the database, a name of the screen cabinet in the transformer substation and a number of a cell in which the screen cabinet is located; establishing the device information model, wherein the device information model comprises a unique number of a device in the database, a name of the device in the transformer substation, a device type and a number of a screen cabinet where the device is located; the electrical equipment information model is built to comprise a unique number of electrical equipment in the database, a name of the electrical equipment in the transformer substation, an electrical equipment type and a number of a screen cabinet where the electrical equipment is located.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: constructing the analytical model includes establishing an objective function using the linear programming criterion, as follows,
Where μ is the input storage device, η is the identification output device,To evaluate the linear combination coefficients of the DMU, b + is the relaxation variable, b - is the residual variable, α is the analytical optimal solution of the objective function, and β is the penalty function.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: constructing the anomaly identification model includes selecting a radial basis function as an objective function of the LSSVM, as follows
Wherein d= { d 1;d2;···;d14 } is a characteristic matrix composed of amplitude-frequency characteristic vectors of historical data affecting the identification factors in the basic information, ζ is an amplitude-frequency characteristic vector affecting the identification factors in the basic information, and κ is a target vector, namely the distribution or range characteristic of the basic information.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: the recognition model needs to be trained in advance, comprising initializing punishment parameters and the target vector, training the LSSVM by using the basic information, and testing by using the generated SVG file; if the recognition model does not meet the accuracy threshold requirement, carrying out assignment optimization on the punishment parameters and the target vector according to errors; and forming the recognition model and outputting a recognition result until the accuracy threshold requirement is met.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: the identification result comprises normal data and abnormal data; the normal data comprises standard attributes, types, formats and characters; the anomaly data includes the attribute, the type, the format, and the character that exceed or fail the criterion.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: the three parameter distribution and gray prediction strategy includes calculating an optimization index using a three parameter cumulative distribution function, as follows,
Wherein sigma is a scale parameter, gamma is a shape parameter, and θ is a position parameter.
As a preferable scheme of the abnormal data identification optimization method based on substation graph transformation, the invention comprises the following steps: also included is a method of manufacturing a semiconductor device,
Wherein y and z are marked abnormal data prediction rejection parameters, and o is a solution factor.
The invention has the beneficial effects that: according to the method, the abnormal data in the graphic conversion process is identified through the constructed abnormal identification model, the marked abnormal data is removed by combining the three-parameter distribution and the gray prediction strategy, the optimized graphic conversion result is output, the graphic conversion quality and efficiency are improved, the abnormal data is accurately positioned and removed, repeated work and error leakage of operation and maintenance personnel are avoided, and the danger coefficient of safe operation of equipment is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a schematic flow chart of an abnormal data identification optimization method based on substation graph transformation according to an embodiment of the invention;
Fig. 2 is a schematic diagram of an electrical graphic object of an abnormal data identification optimization method based on substation graphic transformation according to an embodiment of the invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1 and fig. 2, for a first embodiment of the present invention, there is provided an abnormal data identification optimization method based on substation graph transformation, including:
S1: basic information of relevant equipment of the transformer substation is collected, and private attributes are added to perform graphic conversion. It should be noted that, the graphic transformation includes:
Basic information of relevant equipment of the transformer substation is collected and stored in a database according to the actual physical hierarchy relation of the transformer substation;
constructing an analysis model based on a linear programming criterion, and reading an electrical graph and a topological relation graph of an electrical loop in basic information for analysis to obtain an electrical graph object;
extracting text information of the electrical graphic object by utilizing a random forest strategy, and carrying out matching binding on the text information and data in a database;
correlating the matched information with the electric graph object to construct a secondary topological relation graph;
and extracting information of the electrical graphic object and the secondary topological relation diagram by using a random forest strategy, and adding private attributes into the SVG text to generate a new SVG text.
Specifically, the database needs to establish a basic information model in advance, including:
Establishing a cell information model, a screen cabinet information model, a device information model and an electrical equipment information model in a transformer substation;
establishing a cell information model, wherein the cell information model comprises a unique number of a cell in a database and a name of the cell in a transformer substation;
The method comprises the steps of establishing a screen cabinet information model, wherein the screen cabinet information model comprises a unique number of a screen cabinet in a database, a name of the screen cabinet in a transformer substation and a number of a cell in which the screen cabinet is located;
The method comprises the steps of establishing a device information model, wherein the device information model comprises a unique number in a database, a name of the device in a transformer substation, a device type and a number of a screen cabinet where the device is located;
the method comprises the steps of establishing an electrical equipment information model, wherein the electrical equipment information model comprises a unique number in a database, a name of the electrical equipment in a transformer substation, a type of the electrical equipment and a number of a screen cabinet where the electrical equipment is located.
Further, constructing the analysis model includes:
the objective function is established using a linear programming criterion, which, as follows,
Where μ is the input storage device, η is the identification output device,To evaluate the linear combination coefficients of the DMU, b + is the relaxation variable, b - is the residual variable, α is the analytical optimal solution of the objective function, and β is the penalty function.
Still further, referring to fig. 2, the electrical graphic object includes:
primitive types include text and vector graphics;
The vector graphics comprise basic graphics and combined graphics;
basic figures include straight lines, rectangles, circles, ellipses, and arcs;
the combined graph comprises a screen cabinet, a device, an electric port, a terminal strip, a node and a transformer.
S2: and constructing an anomaly identification model based on a least square strategy, and carrying out anomaly identification on the processed data in the graphic conversion process. The step is to be noted, the constructing of the anomaly identification model includes:
The radial basis function is selected as the objective function of the LSSVM as follows
Wherein d= { d 1;d2;···;d14 } is a characteristic matrix composed of amplitude-frequency characteristic vectors of historical data affecting the identification factors in the basic information, ζ is an amplitude-frequency characteristic vector affecting the identification factors in the basic information, and κ is a target vector, namely the distribution or range characteristic of the basic information.
Preferably, the recognition model needs to be trained in advance, including:
Initializing punishment parameters and target vectors, training LSSVM by using basic information, and testing by using the generated SVG file;
If the recognition model does not meet the accuracy threshold requirement, carrying out assignment optimization on the punishment parameters and the target vector according to the error;
and forming an identification model and outputting an identification result until the accuracy threshold requirement is met.
Specifically, the recognition result includes:
Normal data and abnormal data;
Normal data includes, standard attributes, types, formats, and characters;
the exception data includes attributes, types, formats, and characters that exceed or fall short of the standard.
S3: if the abnormal data is identified, marking the abnormal data, eliminating the marked abnormal data by combining three-parameter distribution and gray prediction strategies, and outputting an optimized graph conversion result. It should be further noted that the three-parameter distribution and gray prediction strategy includes:
The optimization index is calculated using a three-parameter cumulative distribution function, as follows,
Wherein sigma is a scale parameter, gamma is a shape parameter, and θ is a position parameter.
Specifically, the method further comprises the following steps:
Wherein y and z are marked abnormal data prediction rejection parameters, and o is a solution factor.
In popular terms, the digitalization degree of the transformer substation is higher and higher, the main medium of information exchange in the transformer substation is changed into optical fibers from cables, the transmitted signals are also changed into digital values from analog values, the electronic transformer and the merging unit are applied in a large number in the digitalization transformer substation, primary voltage and current signals are collected by the electronic transformer and converted into digital signals, and the digital signals are collected and synchronized by the merging unit and then transmitted to a subsequent measuring and protecting device for processing; in this process, the transmitted electrical quantity signal may be distorted due to interference of the external electromagnetic environment and instability of the electronic device itself, specifically, a sudden change of one or more data points, which are called abnormal data points, the abnormal data are not correctly reflected by the primary electrical signal, but the quality factor digit in the data frame is normal, and the measurement and protection device processes according to the normal data, which may cause a great influence on the result, and may cause malfunction of protection in serious cases.
Preferably, the embodiment also needs to explain that, the first, existing three-point continuous and effective distinguishing abnormal data identification method based on the sampling value indicates that the waveform is continuously conductive at any point except a plurality of break points and the derivative is also continuous in sections, and whether the sampling value is abnormal is judged by utilizing the characteristic, but the method has insufficient sensitivity when the deviation between the abnormal data and the normal data is smaller, and can not identify the continuous abnormal data with small fluctuation amplitude; 2. the existing transformer substation flying spot data identification method judges whether the target sampling point data is abnormal by comparing the absolute values of the target sampling point data and the adjacent two sampling point data, and processes the abnormal data by utilizing a curve fitting method, wherein the method fails when the absolute value of the abnormal data is smaller or continuous abnormal data appears; 3. the existing sampling data validity identification method is that the rapid amplitude of the fundamental component current is calculated through continuous three-point sampling values, and whether the data is abnormal or not is judged by utilizing the mutual comparison of the rapid amplitudes at the calculation positions of different sampling points and the comparison of the amplitudes and a fixed threshold value; it should be noted that the method of the invention is not only used for identifying abnormal data in the graphic conversion process, but also suitable for identifying abnormal data of each sampling point operated by related equipment of the transformer substation, and can solve the problems of difficult identification of continuous multipoint abnormal data, difficult dependence on threshold value and difficult identification of abnormal data with smaller value in the existing method.
Example 2
In order to better verify and explain the technical effects adopted in the method, the embodiment selects the traditional three-point continuous and effective abnormal data identification method based on sampling values, the traditional transformer substation flying spot data identification method and the traditional sampling data validity identification method to respectively carry out comparison test with the method, and the test results are compared by a scientific demonstration means to verify the true effects of the method.
The identification sensitivity of the traditional sampling value three-point continuous effective abnormal data identification method (method one) is low, the identification effectiveness of the traditional transformer substation flying spot data identification method (method two) is low, the value judgment of the traditional sampling data effectiveness identification method (method three) is low, and in order to verify that the method has higher identification sensitivity and identification efficiency compared with the traditional method, the three traditional methods and the method respectively carry out real-time measurement and comparison on the operation of related equipment of a transformer substation in the south area.
Test conditions: (1) Selecting the same operation data of the same equipment in the same period to perform abnormality identification;
(2) Collecting basic information of partial related equipment of a transformer substation, starting automatic test equipment and performing system simulation by using MATLAB;
(3) And configuring operation calculation parameters of each method, and respectively obtaining accuracy result data output by each method.
Table 1: the comparative data table is tested.
In the embodiment, four types of substation operation equipment are used for testing, three traditional methods and the method provided by the invention are used for identifying and testing abnormal data in the same data transmission time, and referring to table 1, the identification accuracy of the abnormal data of the three traditional methods can be intuitively seen, and compared with the traditional methods, the method provided by the invention improves the accuracy by 10%, and based on the identification accuracy, the method provided by the invention verifies the true effect.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (7)
1. The abnormal data identification optimization method based on substation graph transformation is characterized by comprising the following steps of: comprising the steps of (a) a step of,
Basic information of relevant equipment of the transformer substation is collected, and private attributes are added to perform graphic conversion;
constructing an anomaly identification model based on a least square strategy, and carrying out anomaly identification on the processed data in the graphic conversion process;
If the abnormal data is identified, marking the abnormal data, eliminating the marked abnormal data by combining three-parameter distribution and gray prediction strategies, and outputting an optimized graph conversion result;
The conversion of the pattern may include the steps of,
Collecting the basic information of the transformer substation related equipment and storing the basic information into a database according to the actual physical hierarchy relation of the transformer substation;
constructing an analysis model based on a linear programming criterion, and reading an electrical graph and a topological relation graph of an electrical loop in the basic information for analysis to obtain an electrical graph object;
extracting text information of the electrical graphic object by utilizing a random forest strategy, and carrying out matching binding on the text information and the data in the database;
correlating the matched information with the electrical graphic object to construct a secondary topological relation diagram;
Extracting information of the electrical graphic object and the secondary topological relation diagram by utilizing the random forest strategy, and adding a private attribute into the SVG text to generate a new SVG text;
the three parameter distribution and gray prediction strategy includes,
Calculating an optimization index by using a three-parameter cumulative distribution function,
Wherein sigma is a scale parameter, gamma is a shape parameter, and θ is a position parameter;
Also included is a method of manufacturing a semiconductor device,
Wherein y and z are marked abnormal data prediction rejection parameters, and o is a solution factor.
2. The substation graph transformation-based abnormal data identification optimization method according to claim 1, wherein the method comprises the following steps of: the database needs to establish a basic information model in advance, including,
And establishing a cell information model, a screen cabinet information model, a device information model and an electrical equipment information model in the transformer substation.
3. The substation graph transformation-based abnormal data identification optimization method as claimed in claim 2, wherein: establishing a cell information model, wherein the cell information model comprises a unique number of a cell in a database and a name of the cell in the transformer substation;
the screen cabinet information model is established and comprises a unique number of a screen cabinet in the database, a name of the screen cabinet in the transformer substation and a number of a cell in which the screen cabinet is located;
The device information model is built and comprises a unique number of a device in the database, a name of the device in the transformer substation, a device type and a number of a screen cabinet where the device is located;
The electrical equipment information model is built to comprise a unique number of the electrical equipment in the database, a name of the electrical equipment in the transformer substation, a type of the electrical equipment and a number of a screen cabinet where the electrical equipment is located.
4. The abnormal data identification optimization method based on substation graph conversion according to claim 3, wherein: the construction of the analysis model may include,
The objective function is established using a linear programming criterion, which, as follows,
Where μ is the input storage device, η is the identification output device,To evaluate the linear combination coefficients of the DMU, b + is the relaxation variable, b - is the residual variable, α is the analytical optimal solution of the objective function, and β is the penalty function.
5. The abnormal data identification optimization method based on substation graph transformation according to any one of claims 1 to 4, wherein the abnormal data identification optimization method is characterized in that: constructing the anomaly identification model includes,
The radial basis function is selected as the objective function of the LSSVM as follows
Wherein d= { d 1;d2;···;d14 } is a characteristic matrix composed of amplitude-frequency characteristic vectors of historical data affecting the identification factors in the basic information, ζ is an amplitude-frequency characteristic vector affecting the identification factors in the basic information, and κ is a target vector, namely the distribution or range characteristic of the basic information.
6. The abnormal data identification optimization method based on substation graph conversion according to claim 5, wherein the abnormal data identification optimization method comprises the following steps: the anomaly identification model is trained in advance, including,
Initializing punishment parameters and the target vector, training the LSSVM by using the basic information, and testing by using the generated SVG file;
if the abnormal recognition model does not meet the accuracy threshold requirement, carrying out assignment optimization on the punishment parameters and the target vector according to errors;
And forming the abnormal recognition model and outputting a recognition result until the accuracy threshold requirement is met.
7. The substation graph transformation-based abnormal data identification optimization method as set forth in claim 6, wherein: the identification result comprises normal data and abnormal data;
The normal data comprises standard attributes, types, formats and characters;
The anomaly data includes the attribute, the type, the format, and the character that exceed or fail the criterion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010811862.8A CN112000831B (en) | 2020-08-13 | 2020-08-13 | Abnormal data identification optimization method based on substation graph transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010811862.8A CN112000831B (en) | 2020-08-13 | 2020-08-13 | Abnormal data identification optimization method based on substation graph transformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112000831A CN112000831A (en) | 2020-11-27 |
| CN112000831B true CN112000831B (en) | 2024-04-19 |
Family
ID=73462502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010811862.8A Active CN112000831B (en) | 2020-08-13 | 2020-08-13 | Abnormal data identification optimization method based on substation graph transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112000831B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167327B (en) * | 2022-09-05 | 2022-11-18 | 安徽省产品质量监督检验研究院 | Control method and system for new energy automobile part production equipment |
| CN117076991B (en) * | 2023-10-16 | 2024-01-02 | 云境商务智能研究院南京有限公司 | Power consumption abnormality monitoring method and device for pollution control equipment and computer equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867021A (en) * | 2012-08-08 | 2013-01-09 | 中国电力科学研究院 | Conversion method for vector graphics of transformer substation |
| CN103698637A (en) * | 2013-12-25 | 2014-04-02 | 云南电力调度控制中心 | Electric power key indicator abnormity rapid detecting method and device |
| CN104682560A (en) * | 2015-02-27 | 2015-06-03 | 国家电网公司 | Graphical verifying method for power distribution network model transaction |
| CN105184011A (en) * | 2015-09-28 | 2015-12-23 | 云瑞科技（天津）有限公司 | Automatic transformer substation WEB primary connection diagram forming method and device |
| CN106127614A (en) * | 2016-08-30 | 2016-11-16 | 西南交通大学 | A kind of electricity exception data identification method based on three parameter Weir distributions |
| CN107026508A (en) * | 2017-06-06 | 2017-08-08 | 国网山东省电力公司济南市章丘区供电公司 | A kind of Dispatching Management System of Distribution Network |
| CN107730123A (en) * | 2017-10-20 | 2018-02-23 | 国网江苏省电力公司南京供电公司 | A kind of consistent property check method of dispatching automation artwork |
| CN109086793A (en) * | 2018-06-27 | 2018-12-25 | 东北大学 | A kind of abnormality recognition method of wind-driven generator |
| CN109523042A (en) * | 2018-12-04 | 2019-03-26 | 国网山东省电力公司汶上县供电公司 | Shorten the method for Substation secondary circuit corrective maintenance time using planar bar code technology |
-
2020
- 2020-08-13 CN CN202010811862.8A patent/CN112000831B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867021A (en) * | 2012-08-08 | 2013-01-09 | 中国电力科学研究院 | Conversion method for vector graphics of transformer substation |
| CN103698637A (en) * | 2013-12-25 | 2014-04-02 | 云南电力调度控制中心 | Electric power key indicator abnormity rapid detecting method and device |
| CN104682560A (en) * | 2015-02-27 | 2015-06-03 | 国家电网公司 | Graphical verifying method for power distribution network model transaction |
| CN105184011A (en) * | 2015-09-28 | 2015-12-23 | 云瑞科技（天津）有限公司 | Automatic transformer substation WEB primary connection diagram forming method and device |
| CN106127614A (en) * | 2016-08-30 | 2016-11-16 | 西南交通大学 | A kind of electricity exception data identification method based on three parameter Weir distributions |
| CN107026508A (en) * | 2017-06-06 | 2017-08-08 | 国网山东省电力公司济南市章丘区供电公司 | A kind of Dispatching Management System of Distribution Network |
| CN107730123A (en) * | 2017-10-20 | 2018-02-23 | 国网江苏省电力公司南京供电公司 | A kind of consistent property check method of dispatching automation artwork |
| CN109086793A (en) * | 2018-06-27 | 2018-12-25 | 东北大学 | A kind of abnormality recognition method of wind-driven generator |
| CN109523042A (en) * | 2018-12-04 | 2019-03-26 | 国网山东省电力公司汶上县供电公司 | Shorten the method for Substation secondary circuit corrective maintenance time using planar bar code technology |
Non-Patent Citations (2)
| Title |
|---|
| 基于SE-DEA的电网企业资源配置效率评价;王宁;牛东晓;;电力需求侧管理(第03期);全文 * |
| 基于数据包络分析的梯级水电站发电效率优化模型;吴杰康;严进;;中国电机工程学报(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112000831A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112000831B (en) | Abnormal data identification optimization method based on substation graph transformation | |
| CN112560888B (en) | Method and system for evaluating short circuit resistance of transformer winding based on octyl geometric transformation | |
| CN106383958A (en) | Intelligent check and acceptance system of substation anti-misoperation locking logic | |
| CN106770652A (en) | High-tension transformer health status monitoring device and monitoring method based on acoustic characteristic | |
| CN110208647A (en) | A kind of one-phase earthing failure in electric distribution network Section Location based on random matrix | |
| CN109657872A (en) | A kind of prediction technique of network distribution transformer operating status | |
| CN103440497A (en) | GIS insulation defect partial discharge atlas pattern recognition method | |
| CN116520068B (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN114169631A (en) | Oil field power load management and control system based on data analysis | |
| CN114414955A (en) | Method and system for monitoring and evaluating state of switch cabinet | |
| CN117748507A (en) | Distribution network harmonic access uncertainty assessment method based on Gaussian regression model | |
| CN113848471B (en) | Intelligent fault positioning method and system for relay protection system | |
| CN116488332A (en) | Automatic verification method for monitoring information of auxiliary control system of transformer substation | |
| CN111999591B (en) | Method for identifying abnormal state of primary equipment of power distribution network | |
| CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
| CN110895321A (en) | Secondary equipment time mark alignment method based on recording file reference channel | |
| CN112215482A (en) | Method and device for identifying user variable relationship | |
| CN117057666A (en) | Distribution quality evaluation method and system for digital distribution network | |
| CN116561638A (en) | Protective pressing plate non-correspondence checking method based on neural network learning and state evaluation | |
| CN116540015A (en) | Power distribution network fault early warning method and system based on transient waveform signals | |
| CN114089067B (en) | Electrical secondary circuit visualization system of transformer substation | |
| CN116243230A (en) | On-line fault diagnosis method for voltage transformer | |
| CN102541052A (en) | Real-time test method for computer control system | |
| CN114235181A (en) | A installation positioning system for RFID wireless passive temperature measurement chip | |
| CN110717725B (en) | Power grid project selection method based on big data analysis |
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 |