CN113435689A - Labeled multi-bin modeling automation equipment state evaluation method and system - Google Patents
Labeled multi-bin modeling automation equipment state evaluation method and system Download PDFInfo
- Publication number
- CN113435689A CN113435689A CN202110527684.0A CN202110527684A CN113435689A CN 113435689 A CN113435689 A CN 113435689A CN 202110527684 A CN202110527684 A CN 202110527684A CN 113435689 A CN113435689 A CN 113435689A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- data
- automation equipment
- metadata
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 168
- 230000036541 health Effects 0.000 claims abstract description 34
- 238000012423 maintenance Methods 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 238000002372 labelling Methods 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 39
- 238000005259 measurement Methods 0.000 claims description 31
- 238000004891 communication Methods 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 17
- 230000007547 defect Effects 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 9
- 238000011157 data evaluation Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 241000272814 Anser sp. Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004092 self-diagnosis Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A tagged bin modeling automation equipment state evaluation method and system comprises the following steps: step 1, collecting metadata of a power system, and labeling the metadata based on the data type of the metadata; step 2, based on preset correlation influence factors of the automation equipment, evaluating metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model, and establishing a comprehensive evaluation data warehouse of the automation equipment based on evaluation; and 3, filtering the corresponding information of the automation equipment in the comprehensive evaluation data warehouse, and acquiring the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment. The technical scheme of the invention has the advantages of simple and quick algorithm, accurate result and good effect.
Description
Technical Field
The invention relates to the field of automatic scheduling of power systems, in particular to a method and a system for evaluating states of automatic equipment for tagged bin modeling.
Background
At present, with the rapid development of the intelligent technology of the transformer substation, the operation management content of equipment in the transformer substation is also changing day by day. The conventional periodic regular inspection of the original electric power automation equipment as a preventive maintenance mode of the electric power equipment cannot meet the development requirement of the intelligent substation due to various problems of the conventional periodic regular inspection.
Firstly, the intelligent substation cannot flexibly determine the equipment maintenance time based on the actual operation condition of the power equipment, which causes the equipment scheduled maintenance period to be determined usually according to actual experience, and the maintenance requirement of the power equipment cannot be fully met. Secondly, the periodic outage of the power equipment can be caused by the regular inspection of the equipment, so that the continuity of the operation of the power grid is damaged, the power grid dispatching frequency is greatly increased to support the outage and recovery of the power grid, and the economic operation efficiency of the power grid is further influenced. Thirdly, the equipment is inspected regularly and needs to consume a large amount of manpower and physics, and the efficiency is low and the cost is high.
For the above reasons, the status maintenance method based on the operation data of the power automation equipment is increasingly emphasized and applied. In recent years, the wide application of substation automation technology has led to significant improvement in self-detection and self-diagnosis capabilities of substation equipment. The electric power automation equipment can find self abnormity through self-checking, and preliminarily has the basis of carrying out state maintenance according to equipment self-checking alarm information.
However, the state maintenance realized according to the self-checking alarm information of the equipment is still a passive working mode of after-maintenance, and cannot detect and eliminate hidden equipment troubles in time before the equipment fails, and the electric power automation system still has a large amount of running risks and potential accidents. In addition, although the power automation system can collect the operation data of the automation devices in real time and in large quantities, the operation data of the automation devices still cannot be effectively utilized and sufficiently mined. The power automation system in the prior art still has the problems that the operation data of the automation equipment cannot be effectively utilized, the operation condition cannot be comprehensively analyzed and evaluated from the perspective of the system, the state maintenance of the automation equipment cannot be supported, and the like.
Therefore, a labeled multi-bin modeling method and system for evaluating the state of an automation device are needed.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a labeled warehouse modeling automated equipment state evaluation method and system, wherein the labeled warehouse modeling automated equipment state evaluation method and system are used for performing labeling operation on metadata of a power system and evaluating by adopting associated influence factors based on the metadata and labels thereof so as to obtain an operation and maintenance decision of automated equipment.
The invention adopts the following technical scheme.
The invention relates to a labeled multi-bin modeling automatic equipment state evaluation method, wherein: step 1, collecting metadata of a power system, and labeling the metadata based on the data type of the metadata; step 2, based on preset correlation influence factors of the automation equipment, evaluating metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model, and establishing a comprehensive evaluation data warehouse of the automation equipment based on evaluation; and 3, filtering corresponding information of the automation equipment in the comprehensive evaluation data warehouse, and acquiring health condition evaluation of the automation equipment and operation and maintenance decisions of the automation equipment.
Preferably, the power system metadata includes equipment base data, routing inspection data, alarm attribute data, and historical case data of automation equipment in the power system.
Preferably, the automation equipment at least comprises a power measurement and control device, a power system communication gateway, a power system monitoring host, a power system switch and a power system clock synchronization device.
Preferably, the data types of the metadata include: and measuring out-of-limit data and alarm state data.
Preferably, the tagging of the metadata according to the data type of the metadata comprises: judging the abnormal degree of the measurement out-of-limit data according to the preset numerical range of the measurement out-of-limit data, and labeling the measurement out-of-limit data according to the abnormal degree; or, according to the alarm type of the alarm state data, marking the alarm state data with a label.
Preferably, the preset associated influence factors of the automation equipment comprise device communication rate, device defect condition, familial data and device operating life.
Preferably, step 2 further comprises: step 2.1, collecting all metadata corresponding to the current automation equipment, and dividing or calculating all metadata according to the associated influence factors; 2.2, calculating all divided metadata to obtain the evaluation of the automation equipment based on the evaluation indexes and the evaluation standards corresponding to the associated influence factors; and 2.3, storing the evaluation of the automation equipment into a comprehensive evaluation data warehouse of the automation equipment.
Preferably, the health condition evaluation of the automation equipment is obtained by using an analysis evaluation algorithm model with the associated influence factors as evaluation items and the current period data and the historical period data as evaluation sub-items; the calculation formula of the analysis and evaluation algorithm is as follows:
wherein S is the state score of the health condition evaluation of the automation equipment,
ajis the weighting factor for the jth evaluation term,
akthe weighting factor for the kth evaluation sub-term,
Pkas the score of the kth evaluation sub-item,
m is the total number of evaluation items, and l is the total number of evaluation sub-items.
Preferably, the operation and maintenance decision of the automation equipment is determined based on the health condition evaluation of the automation equipment; the health evaluation of the automation equipment and the operation and maintenance decision of the automation equipment are displayed in a visual mode.
In a second aspect, the present invention relates to a tagged bin modeling automated equipment state assessment system, wherein: the system comprises a label generation unit, a data evaluation unit and an analysis decision unit; the tag generation unit is used for acquiring metadata of the power system and performing tagging operation on the metadata based on the data type of the metadata; the data evaluation unit is used for evaluating the metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model based on preset correlation influence factors of the automation equipment and establishing a comprehensive evaluation data warehouse of the automation equipment based on evaluation; and the analysis decision unit is used for filtering the corresponding information of the automation equipment in the comprehensive evaluation data warehouse, acquiring the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment.
Compared with the prior art, the method and the system for evaluating the state of the labeled automation equipment for modeling by the warehouse have the advantages that the metadata of the power system can be labeled, the comprehensive evaluation data warehouse is generated for the labeled metadata by adopting the associated influence factors, and meanwhile, the health condition of the automation equipment is evaluated based on the corresponding data in the data warehouse and the operation and maintenance decision is generated. The technical scheme of the invention has the advantages of simple and quick algorithm, accurate result and good effect.
The beneficial effects of the invention also include:
1. the invention collects and uses various types of metadata such as equipment basic data, routing inspection data, alarm attributes, historical cases and the like, so that the evaluation result of the automatic equipment generated by the invention is more comprehensive and more accurate. In addition, the reason why a large amount of metadata of various types can be used in the present invention is that the evaluation method adopted in the present invention has simple steps, few calculation processes, and no redundant data is generated.
2. The invention selects the communication rate of the device, the defect condition of the device, familial data, the operation age and the like as the relevant influence factors of the automation equipment. The selection of the influence factors is based on years of analysis and processing experience of operation data in the electric power automation equipment, and the potential fault condition of the electric power automation equipment can be accurately represented. Therefore, it is necessary and accurate to classify and sort the metadata by using the above related influencing factors and to perform preliminary evaluation on the metadata.
3. Because the method comprehensively judges the plurality of items of metadata based on the associated influence factors to generate the state evaluation, the method can still accurately judge the fault state of the equipment under the condition that a certain item or an individual item of metadata has transmission or generation errors. Therefore, the method of the invention effectively improves the fault diagnosis accuracy and reduces the diagnosis error.
4. The method and the system split the step of establishing the comprehensive evaluation data warehouse and the step of generating the automatic equipment health condition evaluation and operation and maintenance decision. By the method, a data warehouse can be formed in advance, and a condition evaluation and decision scheme can be generated in a targeted manner according to operation and maintenance requirements or power grid monitoring requirements. Therefore, the running speed of data processing is improved, the pertinence of the method is improved, the repeated redundancy process of data operation is prevented, and the overall efficiency is improved.
5. In the invention, the metadata is classified into the measurement out-of-limit data and the alarm state data, so that the labeling process is quicker and more accurate.
6. The evaluation method and the data warehouse establishment method can be well compatible and suitable for various different electric power automation devices, and have better universality compared with a fault evaluation method specially provided for the current devices based on the types, functions and effects of the devices, so that the method can be suitable for substation devices and smart power grids which are continuously updated and developed.
Drawings
FIG. 1 is a schematic flow chart illustrating the steps of a tagged bin modeling method for evaluating the state of an automated device according to the present invention;
FIG. 2 is a schematic diagram of a data processing procedure in an automated device state evaluation method for tagged bin modeling according to the present invention;
FIG. 3 is a schematic diagram illustrating a health evaluation and operation and maintenance decision of an automation device visually in an embodiment of an automation device state evaluation method for tagged bin modeling according to the present invention;
fig. 4 is a schematic diagram illustrating a health evaluation and operation and maintenance decision of an automation device in another embodiment of the labeled warehouse modeling automation device state evaluation method of the present invention in a visualized manner.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
FIG. 1 is a schematic flow chart illustrating steps of an automated device state assessment method for tagged bin modeling according to the present invention. FIG. 2 is a schematic diagram of a data processing procedure in an automated device state evaluation method for tagged bin modeling according to the present invention. As shown in fig. 1-2, an automated equipment state evaluation method for labeled bin modeling includes steps 1 to 3.
Step 1, collecting metadata of a power system, and labeling the metadata based on the data type of the metadata.
It is understood that the metadata of the power system collected in the present invention may include various types of data collected directly or indirectly from the automation devices of the power system, and since the data can evaluate the operation status of the automation devices in the power system, the data can be collected and summarized.
Preferably, the power system metadata includes equipment base data, routing inspection data, alarm attribute data, and historical case data of automation equipment in the power system.
Specifically, the device basic data may include basic attribute data and operation data of each automation device, and the like, for example, the operation age of the automation device, and the investment rate or usage rate of the CPU, the memory, the disk, and the like. The inspection data can comprise voltage, current data, meter reading data and the like on each line in the power grid acquired by a timer in the power inspection process. Alarm attribute data refers to alarm levels (e.g., critical, severe, general), alarm classifications (e.g., loop exception, channel exception, open-in exception, open-out exception, power plug-in exception, etc.) of automatic equipment alarm signals, and the like. The historical case data may include historical summaries of data collected by the automation devices when the grid is operating in typical conditions, such as historical faults of a large area of the grid, alarm information of the automation devices outside or inside the fault, and operation data of the automation devices. Based on these relevant data, the possible operating data of the automation device when the power grid is operating in a specific state can be summarized, i.e. the operating data of the future automation device can be predicted.
Preferably, the automation equipment at least comprises a power measurement and control device, a power system communication gateway, a power system monitoring host, a power system switch and a power system clock synchronization device.
It is understood that the related evaluation devices for performing the state evaluation of the automation device in the present invention may include the above five types of automation devices. Specifically, the information model of the national grid "four unification, four standardization" device can be used as a basis to collect corresponding data in the above devices.
Tables 1 to 5 show the corresponding rating information of the above five types of devices. The specific contents are as follows:
TABLE 1 Equipment information table of electric power measurement and control device
As shown in table 1, the information collected by the power measurement and control device may include various types of device self-check alarms, operation abnormality alarms, Goose link abnormality alarms, SV alarms, device operation condition information, and the like. The information such as GO01-A, GO02-B can sequentially correspond to the numbers of different information points in the power grid, and the information such as GO01 and GO02 correspond to the numbers of different Goose links in the power grid. Likewise, SV01, SV02, etc. correspond to the numbers of the various SV links in the grid. According to different models of specific measurement and control devices, the number of internal working voltages, the number of optical ports and the number of objects are different. In an embodiment of the present invention, a certain specific type of measurement and control device may be selected, and corresponding data of each port of the measurement and control device may be collected, for example, collecting the transceiving power of an optical port. The operation condition data of the measurement and control device is different from the content of the alarm data generated by the measurement and control device, and the data can be directly acquired by the measurement and control device or indirectly measured by external elements such as an external sensor and the like. And, this part of data is a data item having an actual collection value, and its attribute is different from other alarm data.
Preferably, the data types of the metadata include: and measuring out-of-limit data and alarm state data. For example, in table 1 of the embodiment of the present invention, in the data collected by the power measurement and control device, the contents of the device self-check alarm, the operation abnormality alarm, the link alarm, and the like all belong to alarm data, and the operation condition of the measurement and control device belongs to measurement out-of-limit data. Therefore, in the last column of table 1, different information names can be classified into specific evaluation information.
Alarm data, typically obtained based on self-test alarms for the equipment, typically includes device anomalies and other device operational alarm information. Such data may be classified as critical alarms, and general alarms based on the importance of each self-test alarm. The magnitude threshold-crossing data is data obtained by real-time monitoring of the operating conditions of the device. Specifically, the data may include various data such as a magnetic disk, an internal memory, a CPU, a temperature, a light intensity, a power supply voltage, a time setting state, and the like. For the magnitude threshold-crossing data, whether the magnitude threshold-crossing data exceeds the threshold value corresponding to each item of data or exceeds a few orders of magnitude can be determined. In particular, different tagging operations may be provided for different types of data content, depending on the type of data.
This will be described in detail below.
Table 2 equipment information table of power system monitoring host
As shown in table 2, the power system monitoring host may include information such as device operating condition, abnormal time setting state, CPU state monitoring, memory online detection, hard disk online monitoring, and process online monitoring. Most data in the content can be obtained according to monitoring information directly generated by the monitoring host after the monitoring host is connected to the power system, and the state of the equipment can be judged according to specific collected values of a small part of content, such as CPU load rate, memory utilization rate and disk utilization rate. Therefore, the three items of data are data information of magnitude out-of-limit class.
In addition, the contents of process 1, process 2, etc. may represent only some of the critical processes running on the monitoring host. An alarm may occur, for example, when the corresponding process crashes or exits.
As a specific measurement and control device, the power grid of the present invention may further include some telemechanical measurement and control devices.
Table 3 equipment information table of remote power system
As shown in table 3, the telemechanical system as a measurement and control device can also be used to collect the contents of operation conditions, online approach monitoring, other operation alarm information, and the like. The CPU load rate, the memory utilization rate and the disk utilization rate are also of the type of quantity value out-of-limit, and the others are alarm information. A. B is different network numbers, and XX1, XX9, etc. are device numbers of the measurement and control devices accessed by the remote mobile.
Table 4 equipment information table of electric power system exchanger
As shown in table 4, the device information of the switch may include device self-check alarm, time tick status exception, port status exception, device operation condition, and other information. The device self-check alarm may include alarms caused by power loss, device configuration change, and the like. The device operation condition may include the CPU load factor, the operating voltage, the board temperature, the CPU temperature, and the like.
Table 5 equipment information table of clock synchronizing device of power system
As shown in table 5, the clock synchronization apparatus may include self-test alarm information of the apparatus. Specifically, the clock synchronization device may include information such as an external source signal state, an antenna state, a receiving module state, and a time transition detection state according to a synchronization principle of the clock synchronization device. The above information is alarm data.
Preferably, the tagging of the metadata according to the data type of the metadata comprises: judging the abnormal degree of the measurement out-of-limit data according to the preset numerical range of the measurement out-of-limit data, and labeling the measurement out-of-limit data according to the abnormal degree; or, according to the alarm type of the alarm state data, marking the alarm state data with a label.
It will be appreciated that the alarm data described above is often referred to in the art as a state quantity, while the measurement violation data is often referred to as an analog quantity.
For example, if the current value of the analog quantity point of a certain device is 3.7, the data is the metadata of a measurement violation data in the current equipment. To implement the tagging operation for the data, a threshold range of the data needs to be obtained. As a rule of thumb, three sets of thresholds for this data can be set to-2 and 2, -4 and 4, -6 and 6. When the data falls between [ -2, 2], then the current data is in the "normal" range, when it falls between [ -4, -2) or (2, 4], then the current data is in the "general alert" range, when it falls between [ -6, -4) or (4, 6], then the current data is in the "severe alert" range, when it falls between (- ∞, -6) or (6, ∞), then the current data is in the "critical alert" range. I.e. the data can be tagged according to general, severe and critical alarms.
On the other hand, as described above, the alarm data is classified into a critical alarm, a serious alarm or a general alarm according to the specific content of the alarm, and labeled accordingly.
And 2, evaluating metadata corresponding to the automation equipment based on a preset correlation influence factor of the automation equipment and an analysis and evaluation algorithm model, and establishing a comprehensive evaluation data warehouse of the automation equipment based on the evaluation.
After the process of classifying and labeling each item of data in step 1 is completed, the metadata corresponding to the automation device can be evaluated.
Preferably, the preset relevant influence factors of the automation equipment comprise device communication rate, device defect condition, familial data and operation age.
Table 6 is a table of the relevant influence factor information of the automation devices preset in the present invention. As shown in table 6, the influencing factors include the communication rate of the device, the defect status of the device, familial data, and the operating life.
TABLE 6 table of associated influence factor information of automation devices set in advance
The device communication rate data may be calculated by dividing the normal communication duration of the device in the current period by the duration of the current period. The device defect condition can be obtained according to the alarm data in tables 1 to 5. The method for judging the defect condition of the device is shown in the table, and corresponding scores can be deducted respectively under the condition that a common alarm, a serious alarm or a critical alarm occurs once respectively, so that final defect data can be obtained.
Specifically, in tables 1 to 5 of step 1, the basis for determining that each type of alarm information is a general alarm, a serious alarm, or a critical alarm may be determined according to the cause and the influence degree of occurrence of different alarms. In the invention. Critical alarms refer to operating defects of equipment that cause problems in automation equipment and circuits, that result in loss of primary functionality, that directly threaten safe operation, and that must be immediately addressed. The serious alarm means that the automatic equipment and the loop have problems to cause partial loss of protection function or performance reduction, but the equipment can still operate within a short time and needs to be processed as soon as possible. The general alarm is the equipment operation defect which does not directly influence the safe operation and the power supply capacity of the equipment except the critical and serious alarm, the function of the automation device is not substantially influenced, the property is general, the degree is light, the influence on the safe operation is not large, and the equipment operation defect can be temporarily processed.
As shown in table 6, the data of each item of automation equipment acquired in step 1 and subjected to tagging processing may be divided according to the associated influence factors in table 6, and after the division is completed, the evaluation score may be obtained according to the content of each evaluation item and each evaluation sub-item and according to the content of the data.
Specifically, based on the evaluation experience of the actual automation device, for example, the accuracy of the evaluation history index, or based on the evaluation requirement of the automation device, the evaluation score in table 6, or even the evaluation item and the evaluation sub-item in table 6, or the weighting factors of the evaluation item and the evaluation sub-item may be modified, so as to obtain different results of the evaluation score according to different requirements or evaluation accuracies.
According to the metadata subjected to labeling processing obtained in the step 1 and the associated influence factors of the automation equipment obtained in the step 2, a comprehensive evaluation data warehouse of the automation equipment can be generated. The data warehouse may organize and store metadata, automation devices corresponding to the metadata, tags corresponding to the metadata, associated influencing factors corresponding to the metadata, and the like in a certain form. Accordingly, according to different requirements such as evaluation, operation and display, slice data of a certain device, certain labels and a certain associated influence factor can be quickly called from a data warehouse at any time, and calculation and analysis are carried out.
Preferably, step 2 further comprises: step 2.1, collecting all metadata corresponding to the current automation equipment, and dividing or calculating all metadata according to the associated influence factors; 2.2, calculating all divided metadata to obtain the evaluation of the automation equipment based on the evaluation indexes and the evaluation standards corresponding to the associated influence factors; and 2.3, storing the evaluation of the automation equipment into a comprehensive evaluation data warehouse of the automation equipment.
Specifically, the current demand to be evaluated is obtained, for example, a certain automation device is selected, and all metadata of the current automation device is retrieved from a data warehouse. All metadata of this device is divided according to the association impact index. For example, if the current automation device is the power system measurement and control device described in table 1, the device self-check, abnormal operation alarm, and device operation conditions of the device may be classified into the device defect condition. In addition, according to the communication condition of the device in the period, the device communication rate of the current period of the communication rate of the computing device is equal to the time length of normal communication of the device in the current period/the time length of the current period.
After the division is finished, each evaluation item can be scored according to the evaluation mode of the evaluation item, and the final score is the evaluation of the automatic equipment. The evaluation of the automation device can also be stored in a data repository as historical data for providing a basis for the subsequent evaluation steps.
Table 7 is an example of a data information table in the comprehensive evaluation data warehouse of the automation device obtained in the present invention. As shown in table 7, a comprehensive evaluation data warehouse of the automation device can be obtained according to the metadata obtained in step 1 and the associated influencing factors obtained in step 2. In the repository, not only the content of each rating item, but also the type, identity, and whether the item of data is stored in the live repository. Because the evaluation item is the final calculation result of the metadata, the content is less, the calling speed is high, and the characteristics of the data can be accurately represented, the evaluation item can be stored in a real-time library for quick calling, and the equipment state can be judged in real time.
TABLE 7 example data information tables in a comprehensive evaluation data warehouse of an automation device
Specifically, data items such as the protection device id, the history evaluation communication rate score, the history evaluation defect score, the history evaluation family defect score, the history evaluation operating life score, the previous cycle communication rate, the present cycle communication rate, and the like described in table 7 can be obtained according to the contents of the relevant influence factors.
The status scores in table 7, as a total score of all the related influencing factors, may be combined to reflect the status of an automation device.
Preferably, the health condition evaluation of the automation equipment is obtained by using an analysis evaluation algorithm model with the associated influence factors as evaluation items and the current period data and the historical period data as evaluation sub-items; the calculation formula of the analysis and evaluation algorithm is as follows:
wherein S is the state score of the health condition evaluation of the automation equipment,
ajis the weighting factor for the jth evaluation term,
akthe weighting factor for the kth evaluation sub-term,
Pkas the k-th evaluationThe score of the sub-item(s),
m is the total number of evaluation items, and l is the total number of evaluation sub-items.
It is understood that the scores of the evaluation items and the evaluation sub-items and the weighting factors are multiplied and then summed to obtain the total evaluation score. Since each data item has a score between 0 and 100 points and a total weight of 1, the total evaluation score obtained according to the present formula is also between 0 and 100 points.
Table 7 also includes an online evaluation state quantity score and an online evaluation analog quantity score. The two data are alternative algorithms which can be adopted when the algorithm has poor real-time degree, can simply divide each item of data of the current device into analog quantity and state quantity, and adopts a simpler evaluation method to evaluate the equipment state. In addition, table 7 also includes the state levels, which can also be obtained from simple estimation of the state quantities and the analog quantities, and since the state levels are not obtained based on states obtained by complicated calculation, the calculation method is faster and the calculation process is reduced. On the other hand, because the state grades and the algorithms behind the state grades are different, the method is applicable to different device health condition monitoring requirements, and can be more accurately and more widely applied to different profile condition monitoring methods.
Specifically, the analog quantity of the current equipment is quantity value out-of-limit data, and the state quantity of the current equipment is alarm state data; and generating the health condition of the automation equipment according to the communication state of the equipment, the alarm state data and the quantity value out-of-limit data.
When the communication state of the equipment is normal, the alarm state data in the device are all in a non-alarm state, and the quantity value out-of-limit data in the device are all in a normal non-out-of-limit state, the health condition of the current device can be judged to be normal. When the communication state of the equipment is normal, the alarm state data in the device is no alarm, and the general out-of-limit state exists in the quantity value out-of-limit data in the device, the health condition of the current device can be judged to be attention. When the communication state of the device is normal, a general alarm item exists in the alarm state data in the apparatus, for example, when the device in table 1 has a time tick state abnormality, but no serious alarm item exists, it is determined that the current health condition of the apparatus is in a serious out-of-limit state. When the communication state of the equipment is normal, a critical alarm item exists in alarm state data in the device, for example, power failure occurs in table 1, and the health condition of the current device is judged to be the critical alarm item. According to the mode, the state of the device can be divided into four types of normal alarm, general alarm, serious alarm and emergency alarm.
In particular, the data information tables in the data warehouse with different contents can be generated in the step according to different evaluation requirements and various different actual requirements. For example, to achieve faster evaluation, a data warehouse as shown in table 8 may also be employed.
Table 8 yet another example data information table in a consolidated evaluation data warehouse of an automation device
And 3, filtering corresponding information of the automation equipment in the comprehensive evaluation data warehouse, and acquiring health condition evaluation of the automation equipment and operation and maintenance decisions of the automation equipment.
Preferably, the operation and maintenance decision of the automation equipment is determined based on the health condition evaluation of the automation equipment; the health evaluation of the automation equipment and the operation and maintenance decision of the automation equipment are displayed in a visual mode.
Fig. 3 is a schematic diagram illustrating a health evaluation and operation and maintenance decision of an automation device in an embodiment of an automation device state evaluation method for tagged bin modeling according to the present invention in a visualized manner. Fig. 4 is a schematic diagram illustrating a health evaluation and operation and maintenance decision of an automation device in another embodiment of the labeled warehouse modeling automation device state evaluation method of the present invention in a visualized manner. 3-4, the operation and maintenance decisions of the automated equipment may be generated from the data warehouse as visualized.
Fig. 3 is a display screen of the evaluation result at the substation level, and the left side of the display screen is a model tree, and a corresponding substation can be consulted or quickly searched, for example: the Langfeng changes, the upper half part of the right side of the picture is summary information, and the content comprises the number of serious equipment, the number of abnormal equipment, the number of attention equipment, the number of normal equipment and the number of unknown equipment; the lower half part of the right side of the picture is detailed information, and the content comprises the name of the equipment, the station to which the equipment belongs, the health state, the evaluation time and the like.
FIG. 4 is a view showing an evaluation result at a device level, the layout of which is divided into three parts, a left side, a middle part and a right side, wherein the left side is a model tree as in FIG. 3, and the device level can be referred to; the middle upper half is device information, and the middle lower half is latest evaluation time selection and evaluation result information including evaluation time, equipment health state, communication state and the like. The upper half part of the rightmost picture is equipment state information displayed in a mode of combining a disc graph and a curve graph, the lower half part of the rightmost picture is a detailed evaluation result, and the content comprises real-time analog quantity information, real-time state quantity information, historical analog quantity information and historical state quantity information.
The invention relates to a labeled warehouse modeling automatic equipment state evaluation system, which comprises a label generation unit, a data evaluation unit and an analysis decision unit; the tag generation unit is used for acquiring metadata of the power system and performing tagging operation on the metadata based on the data type of the metadata; the data evaluation unit is used for evaluating metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model based on preset association influence factors of the automation equipment and establishing a comprehensive evaluation data warehouse of the automation equipment based on evaluation; and the analysis decision unit is used for filtering the corresponding information of the automation equipment in the comprehensive evaluation data warehouse, acquiring the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment.
Compared with the prior art, the method and the system for evaluating the state of the labeled automation equipment for modeling by the warehouse have the advantages that the metadata of the power system can be labeled, the comprehensive evaluation data warehouse is generated for the labeled metadata by adopting the associated influence factors, and meanwhile, the health condition of the automation equipment is evaluated based on the corresponding data in the data warehouse and the operation and maintenance decision is generated. The technical scheme of the invention has the advantages of simple and quick algorithm, accurate result and good effect.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (10)
1. A tagged bin modeling automated equipment state assessment method is characterized by comprising the following steps:
step 1, collecting metadata of a power system, and labeling the metadata based on the data type of the metadata;
step 2, based on preset correlation influence factors of the automation equipment, evaluating metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model, and establishing a comprehensive evaluation data warehouse of the automation equipment based on evaluation;
and 3, filtering the corresponding information of the automation equipment in the comprehensive evaluation data warehouse, and acquiring the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment.
2. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
the metadata of the power system comprises equipment basic data, routing inspection data, alarm attribute data and historical case data of the automation equipment in the power system.
3. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
the automation equipment at least comprises a power measurement and control device, a power system communication gateway, a power system monitoring host, a power system switch and a power system clock synchronization device.
4. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
the data types of the metadata include: and measuring out-of-limit data and alarm state data.
5. The method for automated equipment state assessment for tagged bin modeling of claim 4, wherein:
the step of performing the tagging operation on the metadata according to the data type of the metadata comprises the following steps:
judging the abnormal degree of the measurement out-of-limit data according to the preset numerical range in which the measurement out-of-limit data falls, and labeling the measurement out-of-limit data according to the abnormal degree; alternatively, the first and second electrodes may be,
and labeling the alarm state data according to the alarm type of the alarm state data.
6. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
the preset relevant influence factors of the automation equipment comprise device communication rate, device defect condition, familial data and device operation age.
7. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
the step 2 further comprises the following steps:
step 2.1, collecting all metadata corresponding to the current automation equipment, and dividing or calculating all metadata according to the associated influence factors;
2.2, calculating all divided metadata to obtain the evaluation of the automation equipment based on the evaluation indexes and the evaluation standards corresponding to the associated influence factors;
and 2.3, storing the evaluation of the automation equipment into a comprehensive evaluation data warehouse of the automation equipment.
8. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
taking the associated influence factors as evaluation items, taking the current period data and the historical period data as evaluation sub-items, and obtaining the health condition evaluation of the automation equipment by adopting an analysis evaluation algorithm model; wherein the content of the first and second substances,
the calculation formula of the analysis and evaluation algorithm is as follows:
wherein S is a status score of the health condition evaluation of the automation device,
aja weighting factor for the j-th evaluation term,
aka weighting factor for the k-th evaluation sub-term,
Pkas the score of the kth evaluation sub-item,
m is the total number of evaluation items, and l is the total number of evaluation sub-items.
9. The method for automated equipment state assessment for tagged bin modeling of claim 1, wherein:
an operation and maintenance decision of the automation device is determined based on the health condition evaluation of the automation device;
the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment are displayed in a visual mode.
10. An automatic equipment state evaluation system for tagged bin modeling is characterized in that:
the system comprises a label generation unit, a data evaluation unit and an analysis decision unit; wherein the content of the first and second substances,
the tag generation unit is used for acquiring metadata of the power system and performing tagging operation on the metadata based on the data type of the metadata;
the data evaluation unit is used for evaluating the metadata corresponding to the automation equipment by adopting an analysis and evaluation algorithm model based on preset association influence factors of the automation equipment and establishing a comprehensive evaluation data warehouse of the automation equipment based on the evaluation;
and the analysis decision unit is used for filtering the corresponding information of the automation equipment in the comprehensive evaluation data warehouse, and acquiring the health condition evaluation of the automation equipment and the operation and maintenance decision of the automation equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110527684.0A CN113435689B (en) | 2021-05-14 | 2021-05-14 | Automatic equipment state evaluation method and system for labeling digital bin modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110527684.0A CN113435689B (en) | 2021-05-14 | 2021-05-14 | Automatic equipment state evaluation method and system for labeling digital bin modeling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113435689A true CN113435689A (en) | 2021-09-24 |
CN113435689B CN113435689B (en) | 2024-05-14 |
Family
ID=77802329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110527684.0A Active CN113435689B (en) | 2021-05-14 | 2021-05-14 | Automatic equipment state evaluation method and system for labeling digital bin modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113435689B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101160775B1 (en) * | 2011-05-17 | 2012-06-28 | 한국전력공사 | System and method for evaluating integrity of power transformer |
CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
CN103617561A (en) * | 2013-12-02 | 2014-03-05 | 深圳供电局有限公司 | System and method for evaluating state of secondary device of power grid intelligent substation |
CN103970899A (en) * | 2014-05-27 | 2014-08-06 | 重庆大学 | Service-oriented metadata relevance extraction management method and management system |
CN104638764A (en) * | 2015-01-22 | 2015-05-20 | 国家电网公司 | Intelligent state diagnosis and overhauling system for power distribution network equipment |
CN105320123A (en) * | 2015-09-25 | 2016-02-10 | 中国南方电网有限责任公司 | Measurement and control equipment health state evaluating system and method based on online monitored data |
CN106571627A (en) * | 2016-10-12 | 2017-04-19 | 中国南方电网有限责任公司 | Secondary device health state evaluation method based on on-line monitoring information |
CN110619467A (en) * | 2019-09-17 | 2019-12-27 | 电子科技大学 | Power equipment state evaluation method based on alarm big data information |
-
2021
- 2021-05-14 CN CN202110527684.0A patent/CN113435689B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101160775B1 (en) * | 2011-05-17 | 2012-06-28 | 한국전력공사 | System and method for evaluating integrity of power transformer |
CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
CN103617561A (en) * | 2013-12-02 | 2014-03-05 | 深圳供电局有限公司 | System and method for evaluating state of secondary device of power grid intelligent substation |
CN103970899A (en) * | 2014-05-27 | 2014-08-06 | 重庆大学 | Service-oriented metadata relevance extraction management method and management system |
CN104638764A (en) * | 2015-01-22 | 2015-05-20 | 国家电网公司 | Intelligent state diagnosis and overhauling system for power distribution network equipment |
CN105320123A (en) * | 2015-09-25 | 2016-02-10 | 中国南方电网有限责任公司 | Measurement and control equipment health state evaluating system and method based on online monitored data |
CN106571627A (en) * | 2016-10-12 | 2017-04-19 | 中国南方电网有限责任公司 | Secondary device health state evaluation method based on on-line monitoring information |
CN110619467A (en) * | 2019-09-17 | 2019-12-27 | 电子科技大学 | Power equipment state evaluation method based on alarm big data information |
Non-Patent Citations (1)
Title |
---|
李刚等: "电力设备状态评估中的数据科学问题:挑战与展望", 《电力系统自动化》, vol. 42, no. 21, pages 10 - 17 * |
Also Published As
Publication number | Publication date |
---|---|
CN113435689B (en) | 2024-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2992340B1 (en) | System and method for ups battery monitoring and data analysis | |
Catterson et al. | Online conditional anomaly detection in multivariate data for transformer monitoring | |
CN107885642A (en) | Business monitoring method and system based on machine learning | |
CN108879654B (en) | Remote diagnosis method based on abnormal remote measurement of abnormal equipment | |
CN112462734B (en) | Industrial production equipment fault prediction analysis method and model | |
CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
CN112987696A (en) | Regional power distribution network equipment management platform and operation method thereof | |
CN113592343A (en) | Fault diagnosis method, device, equipment and storage medium of secondary system | |
CN113591393A (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
CN116986246A (en) | Intelligent inspection system and method for coal conveying belt | |
CN112580858A (en) | Equipment parameter prediction analysis method and system | |
CN113112216A (en) | Prejudgment analysis method for equipment defects | |
CN113468022B (en) | Automatic operation and maintenance method for centralized monitoring of products | |
CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
CN113589098B (en) | Power grid fault prediction and diagnosis method based on big data driving | |
CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
CN111306051B (en) | Probe type state monitoring and early warning method, device and system for oil transfer pump unit | |
CN113435689B (en) | Automatic equipment state evaluation method and system for labeling digital bin modeling | |
CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
CN115730962A (en) | Big data-based electric power marketing inspection analysis system and method | |
CN117353462B (en) | Power grid operation monitoring analysis method and platform based on artificial intelligence | |
CN112001588A (en) | Accident event online pre-judging method and device based on N-1 state | |
Alghamdi et al. | Detecting fast frequency events in power system: Development and comparison of two methods | |
CN114201884B (en) | Relay protection defect diagnosis method and device based on expert rule deduction |
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 |