CN112101422A - Typical case self-learning method for power system fault case - Google Patents
Typical case self-learning method for power system fault case Download PDFInfo
- Publication number
- CN112101422A CN112101422A CN202010839126.3A CN202010839126A CN112101422A CN 112101422 A CN112101422 A CN 112101422A CN 202010839126 A CN202010839126 A CN 202010839126A CN 112101422 A CN112101422 A CN 112101422A
- Authority
- CN
- China
- Prior art keywords
- case
- characteristic value
- actual
- value
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000011159 matrix material Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 34
- 238000012423 maintenance Methods 0.000 description 17
- 238000004458 analytical method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 238000013500 data storage Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012258 culturing Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The typical case self-learning method for the power system fault case comprises the following steps: defining a matching characteristic value, wherein the matching characteristic value is a case characteristic value of which the characteristic value credibility is greater than or equal to a first threshold value; defining an eigenvalue matrix, wherein the eigenvalue matrix is a matrix of the matched eigenvalues contained in each typical case; after an actual case occurs, acquiring a state value of the actual case; matching the state value with the characteristic value matrix of each typical case, and calculating the case matching degree of the actual case and each typical case to obtain the maximum case matching degree; when the maximum case matching degree is smaller than a second threshold value, performing first processing on the actual case; and when the maximum case matching degree is larger than or equal to the second threshold value, performing second processing on the actual case. The method can automatically generate and divide corresponding typical cases, and provides abundant learning materials for power system workers.
Description
Technical Field
The invention relates to the field of power systems, in particular to a typical case self-learning method for a power system fault case.
Background
An electric power system is a system in which a large number of power stations, substations, distribution stations, users, and the like are connected by transmission and distribution lines. It is usually composed of generator, transformer, bus, transmission and distribution line and electric equipment. Electrical components, equipment and systems are normally in normal operation, but may also be in fault or abnormal operation.
The power system fault refers to a state that the electrical elements and equipment cannot work according to expected indexes, that is, the electrical elements and equipment do not reach the functions which the electrical elements and equipment should achieve, and the faults include generator set faults, transformer faults, transmission line faults, substation faults, bus faults and the like.
As the scale of the power system becomes larger and larger, the structure becomes more and more complex, and the occurrence of a fault is inevitable. The power system fault processing process may be that a topology change is detected from an operating state of the system, fault symptom information is detected from an area (unit) associated with the topology change, and after analyzing and processing the information, a specific area and a specific position (such as a fault range or a fault point) where a fault occurs are determined according to a signal of a protection action. After the fault range or fault point is determined, the fault area (unit) is ensured to be reliably cut off or isolated, then the power supply recovery of the power-off load is completed, and finally fault reason checking and fault elimination processing are carried out.
The special system for power system diagnosis is a corresponding power system fault diagnosis expert system.
In an electric power system, the types of signal acquisition equipment used for operation and maintenance of the electric power system are more, and system maintenance personnel cannot skillfully use the signal acquisition equipment, so that the problems of low maintenance efficiency, poor maintenance effect and the like of the electric power system can be caused. Therefore, electric power enterprises often develop some professional case training activities and publish case training manuals. Although the method can help operation and maintenance personnel to improve the business quality to a certain extent, case training activities and published case training manuals cannot meet the requirements of operation and maintenance of the power system due to the fact that the power system relates to a large number of power equipment.
Disclosure of Invention
The invention solves the problem of providing a typical case self-learning method of the power system fault case to automatically generate and divide the corresponding typical case and provide abundant learning materials for power system workers.
In order to solve the problems, the invention provides a typical case self-learning method for a power system fault case, which comprises the following steps: defining a matching characteristic value, wherein the matching characteristic value is a case characteristic value of which the characteristic value credibility is greater than or equal to a first threshold value; defining an eigenvalue matrix, wherein the eigenvalue matrix is a matrix of the matched eigenvalues contained in each typical case; after an actual case occurs, acquiring a state value of the actual case; matching the state value with the characteristic value matrix of each typical case, and calculating the case matching degree of the actual case and each typical case to obtain the maximum case matching degree; when the maximum case matching degree is smaller than a second threshold value, performing first processing on the actual case; and when the maximum case matching degree is larger than or equal to the second threshold value, performing second processing on the actual case.
Optionally, the first processing includes: and generating a new typical case by using the actual case.
Optionally, the first processing includes: and generating the state value of the new typical case into a new case characteristic value, and calculating the characteristic value credibility of the new case characteristic value.
Optionally, the second processing includes: defining the typical case corresponding to the maximum case matching degree as the most similar case of the actual case; defining the state value meeting the matching characteristic value condition in the state values of the actual case as the actual case state value of the actual case; calculating the characteristic value credibility of the actual case state value as the actual characteristic value credibility; and calculating the case reliability of the actual case as the most similar case according to the actual characteristic value reliability and the maximum case matching degree.
Optionally, the second processing further includes: after the credibility of the actual case as the most similar case is calculated, updating the data of the most similar case, and then recalculating the credibility of the state value of the actual case; and updating the reliability of the recalculated actual characteristic value to the characteristic value matrix of the most similar case.
Optionally, in the state values of the actual case, the state value that is not satisfied as the matching feature value is defined as a sample state value of the actual case, and the sample state value is subjected to feature value cultivation.
Optionally, the performing characteristic value cultivation on the sample state value includes: when the actual case occurs more than N times, if the proportion of the sample state value appearing in the times is not less than K%, converting the sample state value into a case characteristic value of the actual case, calculating the characteristic value credibility of the case characteristic value, and judging whether the case characteristic value can be used as a matching characteristic value; wherein N is an integer of 3 or more, and K is a number of 50 to 100.
Optionally, the case characteristic values and the case state values are generated in panoramic data of a user power grid, where the panoramic data includes at least one of the following data: substation SCADA system data; electric power centralized control SCADA system data; power dispatching SCADA system data; protecting information system data; relay protection device data; safety, stability and automatic control device data; intelligent measurement and control device data; fault recorder data; power equipment state monitoring data; production process data.
Optionally, the case feature values have associated attributes.
In one aspect of the technical scheme of the invention, a matching characteristic value is defined, wherein the matching characteristic value is a case characteristic value of which the reliability of the characteristic value is greater than or equal to a first threshold value; defining an eigenvalue matrix, wherein the eigenvalue matrix is a matrix of the matched eigenvalues contained in each typical case; after an actual case occurs, acquiring a state value of the actual case; matching the state value with the characteristic value matrix of each typical case, and calculating the case matching degree of the actual case and each typical case to obtain the maximum case matching degree; when the maximum case matching degree is smaller than a second threshold value, performing first processing on the actual case; and when the maximum case matching degree is larger than or equal to the second threshold value, performing second processing on the actual case. The method can automatically generate and divide corresponding typical cases, namely, the operations of generating, matching, warehousing and the like of the typical cases can be realized, and various rich and accurate typical cases are provided for the case learning of workers, namely, rich learning materials are provided for the workers of the power system, so that the workers can master better fault processing and analyzing capability of the power system.
Drawings
Fig. 1 is a schematic structural diagram of an arrangement of a diagnosis system master station and a scheduling center (or a centralized control center) in a fault diagnosis expert system of an electric power system according to a first embodiment;
FIG. 2 is a schematic diagram of a configuration of a diagnostic system master station of an expert system for fault diagnosis of a power system according to a first embodiment;
FIG. 3 is a schematic diagram of a second embodiment of a deployment structure of a diagnostic system master station of an expert system for fault diagnosis of a power system;
fig. 4 is a schematic view of a scenario step corresponding to a typical case self-learning method for a power system fault case according to a third embodiment of the present invention.
Detailed Description
For a more clear presentation, the invention is described in detail below with reference to the accompanying drawings.
Example one
Referring to fig. 1 and fig. 2, a fault diagnosis expert system for an electric power system according to the present invention is shown.
The power system fault diagnosis expert system comprises a diagnosis system main station, and the diagnosis system main station of the embodiment is directly arranged by using a network of a scheduling main station (or called a centralized control main station) (hereinafter, referred to as the scheduling main station).
In fig. 1, the left side of the dotted line is the structure of the scheduling master station, and the right side of the dotted line is the diagnostic system master station of the fault diagnosis expert system.
As can be seen from fig. 1, the master station of the diagnostic system of this embodiment is hung in the network structure of the scheduling master station.
As shown in fig. 1, the corresponding scheduling master station may include: the system comprises a scheduling main station data storage structure, an engineer station, an operator station, a telecontrol forwarding/scheduling communication unit, a scheduling main station server and the like.
The telecontrol forwarding/scheduling communication unit of the scheduling master station can be accessed to the power scheduling network. And the server of the dispatching master station is accessed to the SCADA information of each transformer substation in the centralized control area.
The diagnosis system main station can directly access the power system by using the communication equipment of the scheduling main station.
Figure 2 shows a particular deployment configuration of the diagnostic system master station.
As shown in fig. 2, the diagnostic system master station includes: a data storage structure (shown as a dashed box in fig. 2), an expert knowledge base, a front-end server, an analysis engine, and a running workstation.
The data storage structure is used for storing data. The expert knowledge base is used for storing the expert knowledge. The front-end server is used for collecting the operation parameters of the power system and executing data preprocessing. The analysis engine is used as a real-time inference engine, acquires observation information required by cache inference from the front-end server, searches appropriate expert knowledge from the expert knowledge base, completes inference and stores inference processes and inference results. The workstation is operative to act as a user client for displaying information and the like.
As shown in fig. 2, in this embodiment, the data storage structure may include a data server and a disk array. The data storage structure of the present embodiment includes two data servers. The two data servers can be used as historical data servers to store historical cases, historical reports, and statics analysis historical data. The redundant configuration of the two data servers can ensure the safety of data existence. The disk array may be used for separate preservation of long-term historical data. The number of the magnetic disks can be selected according to needs. In other embodiments, other data storage structures may be used, for example, a disk array may be omitted, or only one data server may be used.
As shown in fig. 2, in this embodiment, the expert knowledge base is used to store and update expert knowledge for diagnosing faults of various power systems, and the corresponding expert knowledge may be stored according to a certain rule for easy calling. The expert knowledge base is adapted for independent configuration.
As shown in fig. 2, in this embodiment, the front-end server may collect the operating parameters of the power system in real time and perform the relevant data preprocessing. The front-end server is adapted to employ a standalone deployment.
As shown in fig. 2, in this embodiment, the analysis engine is used as a real-time inference engine, and can collect each observation information required for cache inference from the corresponding front-end server, and can search for appropriate expert knowledge from the expert knowledge base, thereby completing inference, and storing inference processes and intermediate conclusions in real time (i.e., the inference result of the analysis engine may include diagnosis intermediate conclusions). The analysis engine is preferably deployed independently to make the analytical reasoning process of the diagnostic system more efficient and reliable.
As shown in fig. 2, in the present embodiment, the operation workstation serves as a user client, and the displayed information includes operation information of a user system (client system). The operation workstation can specifically display real-time operation information of a user system, can also be used for displaying expert early warning information and expert diagnosis reports, and can also be used for starting functions such as diagnosis tracking, case inversion and the like. And the operation workstation can be used for starting the remote inquiry cloud expert system function. The operation workstation is arranged in a manner of being separately deployed from the server.
It should be noted that, with reference to fig. 1 and fig. 2, the diagnostic system arrangement scheme of the present embodiment is a station-side deployment scheme (disposed at a station side of a station control layer). However, in other embodiments, the diagnostic system arrangement may be deployed in other structural locations.
With continued reference to FIG. 2, the diagnostic system master station may also include a maintenance workstation. The maintenance workstation is used for realizing the maintenance of the diagnosis system. The maintenance workstation may be used for a user engineer (knowledge engineer) to perform maintenance on the diagnostic system. For example, modeling configuration of the power system and expert base knowledge maintenance are realized. In this embodiment, the maintenance workstations are independently deployed, which is beneficial to better implement their maintenance functions. In other embodiments, the maintenance workstation may also be incorporated with the operational workstation of the diagnostic system.
With continued reference to fig. 2, the diagnostic system master station may also include an emergency command center interface server. And the emergency command center interface server is used for being in communication connection with the enterprise emergency command center. The emergency command center interface server may be specifically responsible for real-time communication with the enterprise emergency command center. In this embodiment, the emergency command center interface server is deployed independently, and this structure can exert its effect more. In other embodiments, the emergency command center interface server may also be incorporated with the analysis engine or the operation workstation.
With continued reference to FIG. 2, the diagnostic system master site may also include a WEB server. The WEB server is used for realizing WEB publishing of information and short message (mobile information) pushing. The WEB server may specifically issue a report of the electronic system fault through WEB, and may notify relevant personnel of the corresponding fault information in time through a short message (mobile information) push mode or the like. In other embodiments, the WEB server may not be necessary, i.e., omitted.
With continued reference to fig. 2, the diagnostic system host may further include a cloud expert system interface server. And the cloud expert system interface server is used for being in communication connection with the cloud expert system. When the cloud expert system interface server is communicated with the cloud expert system, the fault diagnosis capability of the diagnosis system is expanded, and the fault cloud diagnosis is guaranteed. In the embodiment, the independent server is adopted, namely, the independent deployment structure is adopted, so that the cloud diagnosis is more efficient, safe, reliable and timely. In other embodiments, the cloud expert system interface server may also be merged with the WEB server.
With continued reference to fig. 2, the diagnostic system master station may also include a firewall. The WEB server and the cloud expert system interface server are isolated outside the firewall. Firewall is used for the safe subregion of system, and other parts of WEB server and high in the clouds expert system interface server and system are separated to this embodiment, reach the better protection to other structures, make the system more stable.
With continued reference to fig. 2, the diagnostic system master station may also include various network devices. These network devices are used to ensure communication of the system. As shown in fig. 2, the network device is specifically implemented by using a switch, and the main station of the diagnostic system shown in fig. 2 includes a first front-end switch, a second switch, and a third switch. For the first front-end switch of the main station of the diagnostic system, an optical fiber interface can be adopted according to the specific situation of an access system, and a switch with gigabit bandwidth is preferably selected. The second switch and the third switch can adopt the switch with the gigabit bandwidth.
With continued reference to fig. 2, the diagnostic system master station may also include an output device. The output device may specifically be a printer, as shown in fig. 2. The printer is used for printing corresponding fault reports, diagnosis reports and the like at any time.
Referring to fig. 2, in this embodiment, the system for accessing the master station of the diagnostic system includes a synchronous clock (system), an SCADA system, an IED (system), a security system, a security management and control platform system, and the like, through the front-end server. The synchronous clock is a power system synchronous clock and is used for ensuring the clock synchronization of data. The information protection system is a relay protection information processing system and is used for managing relay protection setting values, fault message information and the like.
As shown in fig. 2, the present embodiment uses a single front-end server, so this structure can be referred to as a single front-end single network structure. The single-preposition single-network structure enables the internal network structure of the diagnosis system main station to be a single-network structure, and the structure is simpler, so the system cost can be reduced.
It should be noted that, as can be seen from the above contents in fig. 1 and fig. 2, each node in fig. 2 is a logic function defining node, and when actually deployed, the logic function nodes and the physical nodes may be completely in one-to-one correspondence according to the scheme in the figure, or the functional nodes may be tailored, the physical nodes may be merged, and the like according to needs. For example, as described above, for two logical function nodes, namely the operation workstation and the maintenance workstation, in the physical implementation, one workstation computer can be used for implementation.
As can be seen from fig. 1 and fig. 2, in this embodiment, a station end of an expert system for power system fault diagnosis is deployed at a station control layer, and a diagnosis system master station may be specifically deployed at a scheduling center station end, a centralized control center station end, or a substation station end. A forwarding channel between the SCADA system and the expert system station side is opened, and real-time information required by the expert system in each substation of the whole plant can be forwarded to the expert system station side by an IEC 60870-5-104 or IEC61850 standard protocol. The deployment scheme can fully reuse resources and has good practicability for both new projects and existing project reconstruction.
Example two
Referring to fig. 3, another power system fault diagnosis expert system provided by the present invention is shown.
Most of the structure of the expert system for fault diagnosis provided by the present embodiment is the same as that of the foregoing embodiment, and therefore, reference may be made to the corresponding content of the foregoing embodiment.
These same parts comprise a diagnostic system master station, in particular a diagnostic system master station comprising: the system comprises a data storage structure, an expert knowledge base, a front server, an analysis engine and an operation workstation; the data storage structure can comprise a data server and a disk array; in addition, the system also comprises a maintenance workstation, an emergency command center interface server, a WEB server, a cloud expert system interface server, a firewall, network equipment, output equipment (the output equipment can be specifically a printer) and the like; and the diagnosis system master station is accessed to the synchronous clock, the SCADA system, the IED system, the security system, the safety control platform system and the like through the front-end server. The nature, character and advantages of these structures can be understood with reference to the corresponding aspects of the embodiments described above.
Unlike the diagnostic systems shown in fig. 1 and 2, the diagnostic system master station in the diagnostic system shown in fig. 3 has two front-end servers.
Although the diagnosis system master station has two front-end servers, in the diagnosis system master station of the present embodiment, the network structure inside the front-end servers is still a single-network structure, and therefore, this deployment structure may be referred to as a dual front-end single-network structure.
In the structure, the two prepositive servers can acquire the operating parameters of the power system in real time and execute related data preprocessing more quickly and effectively, and the redundant deployment of the two servers is adopted, so that the load balance can be better realized.
Another structure different from the diagnostic system shown in fig. 1 and 2 is that a diagnostic system sub-station is further included in the diagnostic system shown in fig. 3.
In fig. 3, the diagnostic system substation is arranged in connection with the front-end server. The setting of the diagnosis system substation enables the application range of the whole fault diagnosis expert system to be further expanded, and the application area to be further expanded.
In addition, due to the arrangement of the slave stations, the fault diagnosis expert system of the power system provided in this embodiment can further configure and deploy the system or the main part of the system (diagnosis system master station) in a scheduling center, a centralized control center, or a substation without necessarily being configured at a station end of the scheduling master station or the like, and thus has a stronger applicability.
EXAMPLE III
The embodiment of the invention provides a typical case self-learning method for a power system fault case, which comprises the following steps:
defining a matching characteristic value, wherein the matching characteristic value is a case characteristic value of which the characteristic value credibility is greater than or equal to a first threshold value; in this embodiment, the first threshold may be, for example, 80%, or may also be, for example, 50%, and the first threshold is usually 60% or more;
defining an eigenvalue matrix, wherein the eigenvalue matrix is a matrix of the matched eigenvalues contained in each typical case; in this embodiment, each typical case may be located in a typical case library;
after an actual case occurs, acquiring a state value of the actual case;
matching the state value with the characteristic value matrix of each typical case, and calculating the case matching degree of the actual case and each typical case to obtain the maximum case matching degree;
when the maximum case matching degree is smaller than a second threshold value, performing first processing on the actual case; in this embodiment, the second threshold may be, for example, 25%, or 30%;
and when the maximum case matching degree is larger than or equal to the second threshold value, performing second processing on the actual case.
In this embodiment, the calculation of the case matching degree between the actual case and each typical case may be performed by using various methods. One of the methods may be: when an actual disturbance case occurs to a user power grid (namely, when an actual power grid system fault case occurs), various types of state data of the actual case are obtained through various data sources in the panoramic data, and state values (namely, state data) of the actual case are matched with matching characteristic values in characteristic value matrixes of various typical cases in a typical case library according to predefined categories, so that matching ratios of the state values (state data) of the actual case and the matching characteristic values of various categories in the characteristic value matrixes of various typical cases are calculated, and further, a matched category average value is calculated and used as a case matching degree of the actual case and the corresponding typical case, wherein the characteristic value matrixes are expressed by M, and the case matching degree is expressed by MP.
According to the above contents, the maximum case matching degree can be obtained as follows: after traversing the eigenvalue matrix M of all the typical cases in the typical case library, the maximum value maximum case matching degree is determined in all case matching degrees, i.e., MP, and the maximum case matching degree is recorded as MPmax.
In the above, the state value is generated from panoramic data of the user power grid, where the panoramic data includes at least one of the following data: substation SCADA system data; electric power centralized control SCADA system data; power dispatching SCADA system data; protecting information system data; relay protection device data; safety, stability and automatic control device data; intelligent measurement and control device data; fault recorder data; power equipment state monitoring data; production process data. It should be noted that corresponding case characteristic values are also generated in the panoramic data, so as to ensure consistency of the corresponding values.
The panoramic data can also be used for defining that the case characteristic values have a category attribute, and the specific categories can be divided into attribute values such as a topological relation category, a relay protection information category, an self-security information category, an analog quantity category, a state monitoring category and a process information category, and the category is divided.
The above-mentioned "category" attribute in the present invention is only used as an illustrative example and is not to be construed as a limitation of the present invention. This is in turn a calculation corresponding to the degree of matching of the previous cases.
In this embodiment, the first processing may include: and generating a new typical case by using the actual case.
Further, the first processing may include: and generating the state value of the new typical case into a new case characteristic value, and calculating the characteristic value credibility of the new case characteristic value.
In the above process, for example, for a perturbation case with the maximum case matching degree still lower than 25%, a new case different from each typical case currently existing in the typical case library can be treated. At this time, the system can give a new typical case interface, and the user can decide whether to create the case as a new typical case or manually perform typical case matching. I.e. the first processing may comprise providing a definition interface or an information interaction interface for the new typical new case.
In this embodiment, the second processing may include:
defining the typical case corresponding to the maximum case matching degree as the most similar case of the actual case; the most similar case is the case with the highest similarity to the actual case;
defining the state value meeting the matching characteristic value condition in the state values of the actual case as the actual case state value of the actual case;
calculating the characteristic value credibility of the actual case state value as the actual characteristic value credibility;
calculating the case reliability of the actual case as the most similar case according to the actual characteristic value reliability and the maximum case matching degree:
CF＝f(CFi,MPmax)…………(1)
in the above formula 1, CF is case reliability, CFi is actual feature value reliability, and MPmax is the maximum case matching degree.
If the maximum case matching degree MPmax exceeds 25%, for example, it can be determined that the similarity between the current fault case (the actual case) and the typical case corresponding to the maximum case matching degree MPmax is the highest, i.e., the typical case is determined to be the most similar case. The reliability CF of the typical case similar to the fault case can be calculated according to the matched characteristic value reliability CFi and MPmax of the typical case, and a conclusion is finally given.
In this embodiment, further, the second processing may further include:
after the credibility of the actual case as the most similar case is calculated, updating the data of the most similar case, and then recalculating the credibility of the state value of the actual case;
and updating the reliability of the actual eigenvalue recalculated to the eigenvalue matrix M of the most similar case (namely, synchronizing the latest calculation result to the eigenvalue matrix M of the typical case).
And defining the state value which is not satisfied as the matching characteristic value in the state values of the actual case as a sample state value of the actual case, and performing characteristic value culture on the sample state value.
The characteristic value culture of the sample state value comprises the following steps:
when the actual case occurs more than N times, if the proportion of the sample state value appearing in the times is not less than K%, converting the sample state value into a case characteristic value of the actual case, calculating the characteristic value credibility of the case characteristic value, and judging whether the case characteristic value can be used as a matching characteristic value; wherein N is an integer of 3 or more, and K is a number of 50 to 100.
In the process, the case characteristic value sample culture is continued for the state value of the unmatched typical case corresponding to the maximum case matching degree MPmax of the current perturbation case. Firstly, screening out the state value related to the disturbance case as a culture sample. For example, when the similar typical case occurs more than 5 times, statistical analysis is performed on historical big data, when the proportion of a certain culture sample appearing in the historical case is not less than 80%, the culture sample can be converted into the characteristic value of the typical case, the characteristic value of the case is calculated according to the subsequent method of the invention, and whether the characteristic value is stored in the characteristic value matrix M as the matching characteristic value of the typical case is determined according to the conclusion of the method. And if the culture sample does not meet the case characteristic value transformation condition through historical data analysis, continuing culturing. And for the state values which are not specific to the disturbing case, the state values can be selected and stored in a history library, and prompt information is given at the same time to determine whether to further check and process.
Determining the feature value confidence level comprises:
Cf＝f(Cf0,Kach,N,m)…………(2)
in the above formula 2, Cf is the feature value reliability of the case feature value, Cf0 is the feature value reliability prior value of the case feature value, Kach is the acquisition mode attribute weight, N is the occurrence frequency of the case corresponding to the case feature value, and m is the occurrence frequency of the case feature value.
Kach is an acquisition mode attribute weight, that is, in this embodiment, the case feature value has an "acquisition mode" attribute in addition to an "association" attribute and a "category" attribute. After the actual case occurs, the case characteristic values can be reliably acquired from all data sources defined in the panoramic data in real time through network communication, and the attribute of the acquisition mode is defined as 'automatic'. On the contrary, if the feature value that can be automatically acquired from the above-mentioned panoramic data cannot be definitely guaranteed, the "acquisition mode" attribute thereof is defined as "non-automatic". Different 'acquisition modes', the attribute weight Kach of the acquisition mode is different when the confidence level of the characteristic value is calculated, and the weight of the characteristic value of 'automatic acquisition' is higher.
As can be seen from formula 2, in this embodiment, the contents of obtaining the prior value of the reliability of the case characteristic value (which can be determined by the staff according to the assignment mode), confirming the attribute of the obtaining mode, obtaining the occurrence frequency of the case corresponding to the case characteristic value, and obtaining the occurrence frequency of the case characteristic value, and the like are included. Through the calculation of formula 2, when Cf of a certain characteristic value (case characteristic value) is not lower than, for example, 50%, the characteristic value can be regarded as a matching characteristic value of the present case and stored in the matching characteristic value matrix M of the present typical case.
In this embodiment, the case characteristic values may be set to have associated attributes. The correlation attribute is related to the preprocessing. Therefore, the method provided by the embodiment may further include pre-storing a plurality of typical cases into a case library, and pre-defining a plurality of case characteristic values.
Specifically, the power system fault expert diagnosis system can be internally provided with a typical case library. For a new project, several typical case warehouses may be predefined. Such as "transformer body internal fault case", "line-in-range fault case" and "bus voltage loss case", etc. For each type of typical case, corresponding case characteristic values may be defined. The optimal case characteristic value is exclusive, i.e. is specific to the case, and is not common to a plurality of cases. However, for systematic fault cases, such as the "busbar voltage loss case", the characteristic value may be common to multiple cases, for example, the busbar voltage loss due to the incoming line protection action, and the characteristic value of the "incoming line protection action" is common to the "busbar voltage loss case" and the "line-wide fault case". Accordingly, the characteristic value is assigned to the attribute of "relevance", and the value of the attribute can be set as the attribute value of "case-specific" or "system relevance".
The above-mentioned "relevance" attribute of the present invention is only used as an illustrative example and is not to be construed as a limitation of the present invention.
It should be noted that for the different attributes, the corresponding assignment of the different case characteristic values may be "0/1" (digital type) or may be an analog magnitude type. For the former, it is sufficient to define a certain state of "0" or "1" as a feature value, that is, the corresponding case feature value may be binarized; for the latter, a value interval is defined as a characteristic value. Thus, when a certain actually collected data satisfies the corresponding "0/1" state or falls within the defined value range, the collected data is considered to be matched with the characteristic value corresponding to the typical case, that is, the collected data conforms to the definition of the characteristic value of the corresponding case.
A specific scenario corresponding to the embodiment of the present invention is as follows, please refer to fig. 4 in combination:
step 100: actual cases occur; the actual case is the disturbance event and the like described above;
step 10, step 1: acquiring a case state value; as previously described, case state values may be derived from the corresponding perturbation event panoramic data;
step 102: similarity matching is carried out between the (case state value) and M (characteristic value matrix) of each typical case in the (typical) case library; the calculation method of similarity matching can be various, and the foregoing contents can be referred to;
step 103: calculating the matching degree of the case state value and each typical case, namely MP; the calculation method refers to the corresponding content;
step 104: obtaining the highest case matching degree MPmax;
step 105: judging whether MPmax is greater than or equal to 25%, namely whether MPmax exceeds a corresponding second threshold value;
step 106: when the judgment result in the step 105 is 'N' (No), generating a new case; step 106 corresponds to the first process, and the first process selects the generation of the actual case as a new typical case;
step 107: pushing a typical case definition interface to interact with a user to define a new typical case; step 107, further content of the first processing, so that the user can define and operate more new typical cases;
step 108: defining a typical case; step 108, i.e., after step 107, the completed operation can be considered as one way to implement defining a typical case; of course, as mentioned above, it is also possible to perform corresponding defining typical case operation when a new project is encountered;
step 109: generating case characteristic values, wherein the corresponding generation process can be a definition of direct storage in advance, and also refer to the corresponding processes from step 116 to step 120 mentioned later;
step 110: calculating the reliability Cf of the characteristic value; reference may be made to the corresponding content of the foregoing formula 2;
step 111: determining (based on the calculation of 110) whether Cf is greater than or equal to 50%;
step 112: when Cf is greater than or equal to 50%, namely the judgment result of 111 is Y (yes), writing the characteristic value into the case characteristic value matching matrix; on the contrary, when the judgment result in the step 111 is "N" (no), the process returns to the step 110;
step 113: presetting case characteristic value initial values Cf0 (namely prior values); this step acts on step 110;
step 114: when the judgment result in the step 105 is "Y" (yes), calculating the occurrence reliability CF of the case corresponding to M from the matched characteristic value in M (characteristic value matrix) corresponding to MPmax (highest case matching degree);
step 115: according to the step 114, the conclusion of the scheme is obtained;
step 116: carrying out characteristic value sample culture (corresponding to the further process of the second processing) on the unmatched state values of the scheme;
step 117: judging whether the corresponding state value is the characteristic state value of the scheme; if step 117 is "N" (NO), proceed to step 118;
step 118: storing the database for checking, namely storing the corresponding state value in the corresponding database for subsequent processing;
conversely, if step 117 is "Y" (YES), step 119 is entered; step 119: judging whether the number of sample cases (containing corresponding state values) is greater than or equal to 5;
if the judgment result in the step 119 is "no", returning to the step 116;
if the determination result in the step 119 is "Y" (yes), step 120 is entered, i.e., it is continuously determined whether the occurrence ratio of the culture state values is greater than or equal to 80%; if the judgment result of the step 120 is "N" (NO), returning to the step 116; if the judgment in step 120 is "Y" (YES), the process proceeds to step 109.
According to the scene, the method provided by the embodiment can realize the operations of generating, matching, warehousing and the like of the typical cases, and provides various rich and accurate typical cases for case learning of workers, so that the workers can master better fault processing and analyzing capability of the power system.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A typical case self-learning method for a power system fault case is characterized by comprising the following steps:
defining a matching characteristic value, wherein the matching characteristic value is a case characteristic value of which the characteristic value credibility is greater than or equal to a first threshold value;
defining an eigenvalue matrix, wherein the eigenvalue matrix is a matrix of the matched eigenvalues contained in each typical case;
after an actual case occurs, acquiring a state value of the actual case;
matching the state value with the characteristic value matrix of each typical case, and calculating the case matching degree of the actual case and each typical case to obtain the maximum case matching degree;
when the maximum case matching degree is smaller than a second threshold value, performing first processing on the actual case;
and when the maximum case matching degree is larger than or equal to the second threshold value, performing second processing on the actual case.
2. The method of typical case self-learning for power system fault cases as set forth in claim 1, wherein the first process comprises: and generating a new typical case by using the actual case.
3. The method of typical case self-learning for power system fault cases as set forth in claim 2, wherein the first process comprises: and generating the state value of the new typical case into a new case characteristic value, and calculating the characteristic value credibility of the new case characteristic value.
4. The method for typical case self-learning of power system fault cases as claimed in claim 1, 2 or 3, wherein the second process comprises:
defining the typical case corresponding to the maximum case matching degree as the most similar case of the actual case;
defining the state value meeting the matching characteristic value condition in the state values of the actual case as the actual case state value of the actual case;
calculating the characteristic value credibility of the actual case state value as the actual characteristic value credibility;
and calculating the case reliability of the actual case as the most similar case according to the actual characteristic value reliability and the maximum case matching degree.
5. The method of typical case self-learning for power system fault cases of claim 4, wherein the second process further comprises:
after the credibility of the actual case as the most similar case is calculated, updating the data of the most similar case, and then recalculating the credibility of the state value of the actual case;
and updating the reliability of the recalculated actual characteristic value to the characteristic value matrix of the most similar case.
6. The method as claimed in claim 5, wherein the state values that are not satisfied as the matching characteristic values among the state values of the actual case are defined as sample state values of the actual case, and the sample state values are subjected to characteristic value training.
7. The method of claim 6, wherein the characteristic value training of the sample state values comprises:
when the actual case occurs more than N times, if the proportion of the sample state value appearing in the times is not less than K%, converting the sample state value into a case characteristic value of the actual case, calculating the characteristic value credibility of the case characteristic value, and judging whether the case characteristic value can be used as a matching characteristic value; wherein N is an integer of 3 or more, and K is a number of 50 to 100.
8. The method for typical case self-learning of power system fault cases as claimed in claim 1, wherein the case characteristic values and the case status values are generated in a panoramic data of a customer grid, the panoramic data comprising at least one of the following data: substation SCADA system data; electric power centralized control SCADA system data; power dispatching SCADA system data; protecting information system data; relay protection device data; safety, stability and automatic control device data; intelligent measurement and control device data; and fault recorder data.
9. The method of claim 8, wherein the panoramic data further comprises power equipment condition monitoring data and production process data.
10. The method of typical case self-learning for power system fault cases of claim 1 wherein the case characteristic values have associated attributes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839126.3A CN112101422B (en) | 2020-08-19 | 2020-08-19 | Typical case self-learning method for power system fault case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839126.3A CN112101422B (en) | 2020-08-19 | 2020-08-19 | Typical case self-learning method for power system fault case |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101422A true CN112101422A (en) | 2020-12-18 |
| CN112101422B CN112101422B (en) | 2024-02-13 |
Family
ID=73754605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010839126.3A Active CN112101422B (en) | 2020-08-19 | 2020-08-19 | Typical case self-learning method for power system fault case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101422B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759876A (en) * | 2021-09-14 | 2021-12-07 | 西安交通大学 | Wind turbine generator fault diagnosis method and system based on case reasoning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080168018A1 (en) * | 2005-03-18 | 2008-07-10 | Rohlfing David M | Fault Diagnostics |
| CN102284517A (en) * | 2011-06-30 | 2011-12-21 | 东北大学 | Post-rolling cooling long-termed self-learning method based on case-based reasoning |
| CN104573062A (en) * | 2015-01-23 | 2015-04-29 | 桂林电子科技大学 | Intelligent learning method based on description logic and case-based reasoning |
| CN108040036A (en) * | 2017-11-22 | 2018-05-15 | 江苏翼企云通信科技有限公司 | A kind of industry cloud Webshell safety protecting methods |
| CN108090567A (en) * | 2018-01-19 | 2018-05-29 | 国家电网公司 | Power communication system method for diagnosing faults and device |
| CN109977146A (en) * | 2019-05-07 | 2019-07-05 | 山东省科学院激光研究所 | Method for diagnosing faults, device and electronic equipment |
| CN111553380A (en) * | 2020-03-22 | 2020-08-18 | 中润普达(十堰)大数据中心有限公司 | Auxiliary diagnosis system for automobile fault symptoms and using method thereof |
-
2020
- 2020-08-19 CN CN202010839126.3A patent/CN112101422B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080168018A1 (en) * | 2005-03-18 | 2008-07-10 | Rohlfing David M | Fault Diagnostics |
| CN102284517A (en) * | 2011-06-30 | 2011-12-21 | 东北大学 | Post-rolling cooling long-termed self-learning method based on case-based reasoning |
| CN104573062A (en) * | 2015-01-23 | 2015-04-29 | 桂林电子科技大学 | Intelligent learning method based on description logic and case-based reasoning |
| CN108040036A (en) * | 2017-11-22 | 2018-05-15 | 江苏翼企云通信科技有限公司 | A kind of industry cloud Webshell safety protecting methods |
| CN108090567A (en) * | 2018-01-19 | 2018-05-29 | 国家电网公司 | Power communication system method for diagnosing faults and device |
| CN109977146A (en) * | 2019-05-07 | 2019-07-05 | 山东省科学院激光研究所 | Method for diagnosing faults, device and electronic equipment |
| CN111553380A (en) * | 2020-03-22 | 2020-08-18 | 中润普达(十堰)大数据中心有限公司 | Auxiliary diagnosis system for automobile fault symptoms and using method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 刘芳: "基于案例库的电力通信故障诊断算法研究", 河北电力技术, vol. 38, no. 04, pages 38 - 41 * |
| 赵辉: "案例推理的动态学习模型及其在TE 过程", 中国博士学位论文全文数据库信息科技辑, no. 03, pages 1688 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759876A (en) * | 2021-09-14 | 2021-12-07 | 西安交通大学 | Wind turbine generator fault diagnosis method and system based on case reasoning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101422B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709580B (en) | Transformer substation secondary system operation and maintenance cloud platform | |
| CN105790441B (en) | A kind of intelligent substation relay protection cruising inspection system | |
| EP3913555A1 (en) | Power distribution network operation aided decision-making analysis system and method | |
| CN103501047B (en) | Intelligent fault wave recording main station information management system | |
| CN104753178A (en) | Power grid fault handling system | |
| CN103902816A (en) | Electrification detection data processing method based on data mining technology | |
| CN104657913A (en) | Intelligent warning system based on all-data model | |
| CN104463696A (en) | Power grid operating risk recognition and prevention method and system | |
| CN108446396B (en) | Power data processing method based on improved CIM model | |
| CN112072642B (en) | Method for estimating abnormal operation state of power system | |
| CN108206522B (en) | Power equipment state monitoring method and system | |
| CN103765469A (en) | Dynamic infrastructure administration system | |
| CN111276929B (en) | Information recording method for fault expert diagnosis of power system | |
| CN114138982A (en) | Construction method of knowledge graph for dry-type transformer fault diagnosis | |
| CN112054510B (en) | Method for estimating abnormal operation state of power system | |
| CN108596450B (en) | Power grid risk early warning method and system | |
| CN111327474B (en) | Power system fault diagnosis method based on topology analysis | |
| CN112101422B (en) | Typical case self-learning method for power system fault case | |
| CN106776750B (en) | Graph-mode integrated digital preplan system for power distribution network | |
| CN112054511A (en) | Correlation generation method for accident handling measures and standard tickets of power system | |
| CN117118062A (en) | Secondary system data fusion monitoring method and system for power dispatching automation | |
| CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
| CN112614017B (en) | Power failure information management system, power failure information management method, and storage medium | |
| CN115267616A (en) | Transformer running state monitoring system and method based on enterprise data middling station | |
| CN112104073B (en) | Real-time information calibration method for power system |
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 |