CN112527778B - Abnormal defect elimination management system and method based on abnormal information database increment - Google Patents
Abnormal defect elimination management system and method based on abnormal information database increment Download PDFInfo
- Publication number
- CN112527778B CN112527778B CN202011521653.6A CN202011521653A CN112527778B CN 112527778 B CN112527778 B CN 112527778B CN 202011521653 A CN202011521653 A CN 202011521653A CN 112527778 B CN112527778 B CN 112527778B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- rule
- work order
- abnormality
- reason
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- 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
- G06F16/2455—Query execution
-
- 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
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas 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
Abstract
The invention discloses an abnormal defect elimination management system and method based on abnormal information database increment, wherein the system comprises: an abnormal information processing state monitoring unit; an abnormality cause analysis unit that executes an abnormality cause analysis flow on an abnormality record of an unanalyzed cause; the invention improves the processing, analysis and processing efficiency and precision of abnormal information of the transformer substation, ensures the integrated processing of the abnormal information and the closed-loop control of abnormal problems and provides an effective transformer substation equipment maintenance and accident prevention measure for the power department by mutually combining the abnormal information processing state monitoring part, the abnormal reason analysis part and the abnormal defect elimination processing execution part.
Description
Technical Field
The invention relates to the technical field of power utilization monitoring, in particular to an abnormal defect elimination management system and method based on abnormal information database increment.
Background
The traditional metering operation monitoring and abnormity diagnosis work mainly depends on that an operator finds that a certain metering point is abnormal, and a detector carries out work such as wiring, data acquisition, detection and analysis, problem troubleshooting and recovery on site.
Disclosure of Invention
In view of the problems in the prior art, the present invention provides an exception deletion management system based on exception information database increment, which includes:
an abnormal information processing state monitoring unit which periodically inquires the database about an abnormal record of an unanalyzed reason and an abnormal record of an analyzed reason which has not entered the abnormal deletion processing execution unit;
an abnormality cause analysis unit that executes an abnormality cause analysis process for an abnormality record of an unanalyzed cause, the abnormality cause analysis process being predetermined to be executed by at least calling the abnormality rule evaluation unit;
an abnormality deletion processing execution unit that executes abnormality deletion processing for the abnormality information for which the unique abnormality cause is specified;
when executing the abnormal cause analysis process, the abnormal cause analysis part determines whether to enter the abnormal deletion processing execution part by taking the number of the abnormal causes obtained by the abnormal rule research and judgment part as the condition.
In a further preferred embodiment of the present invention, the system further includes an abnormal information manual transferring unit, and when the number of abnormal causes evaluated by the abnormal rule evaluating unit is more than one, the abnormal cause analyzing unit registers the abnormal information and the plurality of abnormal causes in the abnormal cause analysis result table and transfers the abnormal cause confirming task to the manual transferring unit to wait for manual processing.
As a further optimization of the above solution, when the abnormal rule studying and judging part is called by the abnormal cause analyzing part, the abnormal information is firstly grouped according to the studying and judging subject code as a unit, and then the same group of abnormal information is called to calculate at least one studying and judging rule corresponding to the same group of abnormal information according to the diagnosis subject, so as to obtain the matched abnormal cause.
As a further optimization of the above-described solution, the abnormality cause analysis unit registers the obtained abnormality cause analysis result in the abnormality cause analysis result table and updates the state of the abnormality information in the database when the abnormality rule evaluation unit is called.
As a further optimization of the above aspect, the abnormality elimination processing execution unit includes:
the work order primary filtering part judges whether the abnormal information work order to be processed has a general rule according to the judging rule participated in the abnormal rule judging part, and the work order primary filtering part stops the abnormal deletion processing execution process of the abnormal information work order without the general rule;
and the work order secondary filtering part is used for stopping the abnormal deletion processing execution process of the abnormal information work order in a preset white list of the object related to the abnormal reason of the work order to be processed in the work order to be processed after being filtered by the work order primary filtering part.
As a further optimization of the above scheme, when the work order primary filtering unit performs a general rule participation judgment on an abnormal information work order, the work order primary filtering unit is associated to a preset abnormal criterion record table in an abnormal information database according to the database primary key id1, and judges whether at least one id2 in at least one abnormal criterion primary key id2 associated with the abnormal information work order in the abnormal criterion record table is within a preset threshold interval range.
As a further optimization of the above aspect, the abnormality elimination processing execution unit further includes:
and the work order dispatching unit is used for dispatching the work orders after determining the grade, the processing mode and the work order template of the work orders in the work orders to be processed after being filtered by the work order secondary filtering unit, and simultaneously registering the relevant information of the work orders to the abnormal work order table of the metering device.
In a further preferred embodiment of the above-described configuration, the work order dispatch unit stops the dispatch process when the dispatch process is performed and an unfinished work order is detected in the abnormal work order table of the weighing apparatus.
As a further optimization of the above scheme, the work order dispatch section, but with the highest of all sort levels as the final result in specifying the work order level.
The invention also provides an abnormal defect elimination management method based on the abnormal information database increment, which comprises the following steps:
executing the timing query on the database for the abnormal record of the unanalyzed reason and the abnormal record of the analyzed reason which does not enter the abnormal deletion processing execution part;
executing an abnormal reason analysis flow for the abnormal record of the unanalyzed reason, wherein the abnormal reason analysis flow is predetermined to be executed by at least calling an abnormal rule study and judgment part;
executing exception deletion processing on exception information of which the unique exception cause is determined by the exception cause analysis part;
when executing the recorded abnormal cause analysis process, the abnormal cause analysis part determines whether to enter the abnormal deletion processing execution part or not by taking the number of the abnormal causes obtained by the abnormal rule research and judgment part as the condition.
The abnormal defect elimination management system and method based on the abnormal information database increment have the beneficial effects that:
1. according to the invention, through the mutual combination of the abnormal information processing state monitoring part, the abnormal reason analyzing part and the abnormal defect elimination processing executing part, the processing, analyzing and processing efficiency and precision of the abnormal information of the transformer substation are improved, the integrated processing of the abnormal information and the closed-loop control of the abnormal problem are ensured, and an effective transformer substation equipment maintenance and accident prevention measure is provided for the power department.
2. The abnormal information processing state monitoring part of the invention inquires the increment of the abnormal record database and the abnormal information which is not processed by dispatching orders in real time so as to prevent the transformer substation from being overstocked and not being processed in time.
3. The abnormal reason analysis part of the invention analyzes and processes the abnormal reasons of the abnormal information obtained by calling the abnormal rule study and judgment part for the transformer substation abnormal with the unanalyzed reasons, and realizes the detailed analysis and processing of various abnormalities of the transformer substation based on the operation of various refined abnormal diagnosis subject groups, various abnormal reason analyses, analysis formulas and parameters, thereby quickening the fault positioning speed and improving the accuracy of the fault positioning.
4. The abnormal defect elimination processing execution part filters partial work orders by arranging the work order primary filtering part and the work order secondary filtering part, different types of work orders are distributed with personnel processing with different capabilities, the work order processing efficiency is effectively improved, and the work order dispatching part of the abnormal defect elimination processing execution part dispatches the work orders after determining the work order grade, the work order template and the processing mode of the work orders, so that the work order processing efficiency and precision are improved.
Drawings
FIG. 1 is a block diagram of an exception erasure management system based on exception information database deltas according to the present invention;
FIG. 2 is a flowchart of an exception elision management method based on exception information database deltas according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
Firstly, referring to fig. 1, the abnormal defect elimination management system based on abnormal information database increment of this embodiment is mainly used for analyzing abnormal reasons based on various abnormal record data of a metering device in a transformer substation, such as abnormal status words, abnormal metering values, abnormal rates, abnormal errors, and judging how to process the links of generating, dispatching, processing, filing, and the like of a work order based on the abnormal reason analysis, wherein the generation of the work order is divided into four categories according to the processing difficulty, authority level, and the like, including the abnormality which can be automatically processed by the background of a master station, the system directly initiates the work order and automatically dispatches the work order, the processing completes the system verification, the system verification is filed after passing the system verification, the system verification is not processed by a monitoring person of a transferred master station, in this embodiment, the abnormal information mentioned below is transferred to a manual turnover part for waiting manual processing by a plurality of abnormal reasons which are permitted by the abnormal reason analysis part, that is, the monitoring personnel of the transferred main station carries out the subsequent treatment. The exception handling method which cannot be directly dispatched can be realized by dispatching or forwarding to an expert, and the like, and the application is not limited herein.
The exception deletion management system based on the exception information database increment provided by the embodiment comprises:
the abnormal information processing state monitoring part is used for executing the abnormal record of the unanalyzed reason and the abnormal record of the analyzed reason which does not enter the abnormal disappearance processing execution part on the database at regular time, for example, the abnormal record can be inquired at every 5 minutes at regular time so as to prevent the transformer substation from being overstocked and not being processed in time;
an abnormal cause analysis part which executes an abnormal cause analysis flow to the abnormal record of the unanalyzed cause, wherein the abnormal cause analysis flow is predetermined to be executed by at least calling the abnormal rule study and judgment part; when executing the abnormal cause analysis flow, the abnormal cause analysis unit determines whether to enter the abnormal deletion processing execution unit on the condition that the number of abnormal causes evaluated by the abnormal rule evaluation unit is the number of abnormal causes. If the number of the abnormal causes is more than one, that is, the abnormal causes are not clear, the process cannot enter the abnormal deletion processing execution part to perform the processes of generating the work order and the like, if the number of the abnormal causes is only one, that is, the abnormal causes are clear, the process enters the abnormal deletion processing execution part to perform the subsequent abnormal deletion processing, of course, for the management of data information and the subsequent analysis work of the abnormal causes of the transformer substation, the reason record researched and judged in the abnormal cause analysis result table needs to be registered, the abnormal record table is updated, the reason researched and judged is recorded as the suspected fault reason, and the reason is used as the basis for the abnormal deletion of the personnel who connects the work order to perform the subsequent work order.
The abnormal rule studying and judging part of the embodiment includes various abnormal rules, which are mainly divided into two types, one type is a general rule, and the other type is a user-defined rule, and certainly, the sources of the rules can be obtained according to manual experience or expert knowledge, or can be obtained through big data analysis through a neural network, so that the rules are conveniently managed, when the abnormal rules are stored in a database, each rule is numbered, each newly added rule (including the general rule and the user-defined rule) is newly added with a number record on the basis of the original basis, schematically, the number of the newly added rule can be 1-10000, and the number of the newly added rule can be 10001-20000.
In the present embodiment, the management of the exception rule includes: the method comprises the following steps of abnormal rule generation, rule numbering, rule optimization updating and the like, wherein the abnormal rules comprise rules self-defining threshold values and rules self-defining logic or expressions, and the following steps are adopted for the generation, the optimization and the updating of the rules:
monitoring and acquiring multidimensional parameters of the power system in real time, such as voltage, current, power and other electrical data, power equipment marketing records, work order maintenance records and other data and fault data;
establishing a basic rule base based on the feedback of the actual abnormal reason and abnormal phenomenon of the historical abnormal defect eliminating link;
based on historical monitoring data and fault data, deep mining comprises implicit relations among measurement data, state words, ammeter events and information historical data such as switches, secondary circuit polling instruments, customer files, work orders and the like through a machine learning algorithm, an association rule mining algorithm and the like, and more complex and accurate abnormal studying and judging rules are constructed to form a deep rule library;
the method comprises the steps of mapping and storing abnormal phenomena, abnormal reasons and abnormal reason judging methods based on all abnormal rules, carrying out priority ranking on a plurality of abnormal reasons corresponding to the abnormal phenomena, modifying and updating a custom threshold value and logic or an expression in the abnormal rules based on the feedback of the actual abnormal reasons and abnormal phenomena of a real-time abnormal defect elimination link, and reordering the priority ranking so as to avoid the conflict of results obtained by the abnormal reasons.
The implicit relationship between the deep mining data through the machine learning algorithm comprises the following steps:
inputting the monitoring data into a preset neural network based on various monitoring data;
acquiring at least one fuzzy membership function value of each input data based on a first hidden layer in a neural network;
acquiring a fusion membership function value of the normalized multiple input data based on a second hidden layer in the neural network;
acquiring an abnormal rule obtained based on a fusion membership function value of an abnormal rule parameter, input data and a plurality of input data based on a third hidden layer in the neural network, and performing iterative training on the neural network model based on comparison between an output actual abnormal rule and an actual abnormal reason fed back by an abnormal deletion loop to correct the abnormal rule parameter and the model parameter;
and judging the reason of the abnormality based on the trained neural network model and the multi-dimensional data when the abnormality occurs.
In the training process, abnormal rule parameters are fixed firstly, a network model is trained based on training set data, network model parameter correction is carried out based on errors of actual output by adopting a gradient descent algorithm, then the network model after the network model parameter correction is carried out forward propagation, the abnormal rule parameters are corrected on a third hidden layer, the trained network model is obtained through a preset iteration process, network model performances (including accuracy and the like) are obtained based on a plurality of test sample data, and the optimal abnormal rule parameters and network model parameters are obtained based on comparison of different network model performances of a plurality of trainings.
The foregoing process prioritizes and reorders the multiple abnormal causes corresponding to the abnormal phenomenon, performs statistics according to the actual abnormal cause types fed back by the abnormal disappearance link for the abnormal phenomenon, and performs ranking and updating ranking according to the statistics times of the actual abnormal causes and the expert experience, for example, for the abnormal phenomenon with wrong wiring, the ranking of the abnormal causes sequentially is as follows:
the first may be the reason for wiring failure due to work order repair;
secondly, the user may have a reversible power transmission device, and the user load has a large influence on the phase angle, which is a reason for the nature of the power load;
and finally, under the condition of eliminating wiring faults and user loads, line loss mutation before and after the abnormity occurs is the cause of meter faults.
And an abnormality elimination processing execution unit which executes abnormality elimination processing on the abnormality information for which the unique abnormality cause is clarified, the abnormality elimination processing execution unit being mainly configured to generate, dispatch, process, and archive the work order, and of course, executing the abnormality elimination processing, including an abnormality record for which the analyzed cause monitored by the abnormality information processing state monitoring unit has not yet entered the abnormality elimination processing execution unit and an abnormality record for which the abnormality cause analysis unit has already analyzed the cause.
The abnormality defect elimination management system of the present embodiment further includes an abnormality information manual turnaround unit, and when the number of the abnormality causes evaluated by the abnormality rule evaluation unit is more than one, the abnormality cause analysis unit registers the abnormality information and the plurality of abnormality causes in the abnormality cause analysis result table and transfers the abnormality cause confirmation task to the manual turnaround unit to wait for manual processing.
When the abnormal rule studying and judging part is called by the abnormal reason analyzing part, the method for studying and judging the abnormal rule comprises the following steps:
firstly, grouping abnormal information according to a research topic code as a unit, wherein the research topic can be, for example, sudden increase of power consumption of a user (topic code M001), current overcurrent (topic code M003), continuous overload lower limit (topic code M004) and the like;
and then, calling at least one corresponding judging rule for operation on the same group of abnormal information according to the diagnosis theme to obtain a matched abnormal reason, wherein the judging rule comprises at least one abnormal reason analysis, and corresponding operation through a calculation formula related to the abnormal reason analysis, input parameters and output parameters to judge an abnormal reason analysis result. Illustratively, the method takes a research topic as a sudden increase of power consumption of a user, and the analysis of the abnormal reason of the topic comprises the following steps:
(1) after the abnormity happens, the line loss changes suddenly, and the correlation between the user electric quantity and the line loss change is high, so that the user electric quantity is a fault reason of the meter;
(2) the line loss is unchanged after the abnormity occurs, and the correlation between the user electric quantity and the line loss change is low, which is the reason of the user load change.
Thus, the operational formula includes: the method for calculating the correlation between the user electric quantity and the line loss change comprises the following steps: calculating a correlation coefficient of the user electric quantity and the line loss change by referring to a Pearson algorithm model; line loss rate calculation formulas before and after the occurrence of the abnormality, particularly line loss rates of the distribution room corresponding to the hour before and the hour after the occurrence time of the abnormality, and whether mutation occurs or not is judged;
the relevant input parameters comprise electric energy meter marketing files, an hour station area line loss statistical information table, user minute electric quantity statistics and abnormal records; the output parameters comprise an abnormal record and an abnormal reason analysis result.
The above-mentioned unusual disappearance processing execution unit, considering that some transformer substation abnormalities can not be directly sent a list to handle, need expert or more professional to carry out unusual disappearance, so the unusual disappearance processing execution unit of this embodiment possesses:
the work order primary filtering part is used for judging whether the abnormal information work order to be processed has a general rule according to the judging rule participated in the abnormal rule judging part, the work order primary filtering part terminates the abnormal deletion processing execution process of the abnormal information work order without the general rule, and if the abnormal information work order does not have the general rule, the abnormal reason analysis is carried out by a user-defined rule, and the removal of the abnormal reason can be processed by professional staff, so that the work order is not directly dispatched;
and the work order secondary filtering part is used for stopping the execution process of the abnormal deletion processing of the abnormal information work order of the object related to the abnormal reason of the work order to be processed in the preset white list in the work order to be processed after being filtered by the work order primary filtering part, and the abnormal deletion of the abnormal information can be processed in a delayed way, so that the work order is not directly dispatched.
In combination with the above-mentioned serial numbers of various abnormal rules in the abnormal rule judging section, especially, for example, serial numbers 1-10000 are allocated to the general rule, and serial numbers 10001-20000 are allocated to the custom rule in the embodiment, when the general rule participation judgment is performed to the abnormal information work order, the work order primary filtering section is associated to the preset abnormal criterion record table according to the database primary key id1 in the abnormal information database, and judges whether at least one id2 exists in the preset threshold interval range which is the serial number range occupied by the general rule for at least one abnormal criterion primary key id2 associated in the abnormal criterion record table of the abnormal information work order, when the general rule participation judgment is performed to the abnormal information work order based on the above-mentioned general rule allocation serial numbers 1-10000, by judging whether at least one id key 2 of the abnormal criterion in the abnormal criterion record table managed by the abnormal information work order exists in at least one 2 id in 1-10000, if so, the abnormal information work order has the participation of the universal rule when judging the abnormal reason.
And in the process, the work order dispatching unit specifies the work order grade, the work order template and the processing mode (dispatching is carried out according to the dispatching mode classification in the dispatching strategy table) of the work order, then carries out dispatching processing, and simultaneously registers the relevant information of the work order to the abnormal work order table of the metering device.
Preferably, the work order assignment unit terminates the assignment process when an unfinished work order is detected in the abnormal work order table of the weighing device during the assignment process.
When the work order grade is clear, the work order dispatching part takes the highest grade in all kinds of grades as a final result, wherein the grade kinds can be work order strategy grade, grade which is researched and judged according to the type of the electric energy metering device and the recent electricity consumption, subjectively divided key user grade and the like.
Wherein, user work order grade includes: stage I: the electric energy metering device for trade settlement of 110kV and above is used for users with the average monthly electric energy consumption exceeding 100 ten thousand kilowatt hours in nearly 3 months; II stage: the electric energy metering device for trade settlement of 10kV to 110kV and above is used for users with the average monthly electricity consumption of more than 10 ten thousand kilowatt hours in nearly 3 months; grade III: other users.
The user-defined user grade acquisition method is that the user identification in the electric energy meter marketing archive table is found according to the electric energy meter identification, the group identification of the user group detail to which the user belongs is found, and then the work order grade field is inquired in the user group table.
For work order strategy ranking, an exemplary partial work order strategy ranking is shown in Table 1 below:
TABLE 1 partial work order strategy grade Table
Referring to fig. 2, the present embodiment further provides an exception deletion management method based on an exception information database increment, where the method includes the following steps:
executing the timing query on the database for the abnormal record of the unanalyzed reason and the abnormal record of the analyzed reason which does not enter the abnormal deletion processing execution part;
executing an abnormal reason analysis flow for the abnormal record of the unanalyzed reason, wherein the abnormal reason analysis flow is predetermined to be executed by at least calling an abnormal rule study and judgment part;
executing exception deletion processing on exception information of which the unique exception cause is determined by the exception cause analysis part;
when executing the recorded abnormal cause analysis process, the abnormal cause analysis part determines whether to enter the abnormal deletion processing execution part or not by taking the number of the abnormal causes obtained by the abnormal rule research and judgment part as the condition.
The present invention is not limited to the above-described embodiments, and those skilled in the art will be able to make various modifications without creative efforts from the above-described conception, and fall within the scope of the present invention.
Claims (10)
1. An exception erasure management system based on exception information database increments, comprising:
an abnormal information processing state monitoring unit which periodically inquires the database about an abnormal record of an unanalyzed reason and an abnormal record of an analyzed reason which has not entered the abnormal deletion processing execution unit;
an abnormality cause analysis unit that executes an abnormality cause analysis process for an abnormality record of an unanalyzed cause, the abnormality cause analysis process being predetermined to be executed by at least calling the abnormality rule evaluation unit;
an abnormality deletion processing execution unit that executes abnormality deletion processing for the abnormality information for which the unique abnormality cause is specified;
when executing the abnormal reason analysis process, the abnormal reason analysis part determines whether to enter the abnormal deletion processing execution part by taking the number of the abnormal reasons obtained by the abnormal rule research and judgment part as the condition;
the abnormal rule studying and judging part comprises an abnormal studying and judging rule obtained through the implicit relation among the mining data of the machine learning algorithm deep level, and the implicit relation among the mining data of the machine learning algorithm deep level comprises the following steps:
inputting the monitoring data into a preset neural network based on various monitoring data, wherein the monitoring data comprises: electrical data, power equipment marketing records, work order maintenance records, and fault data;
acquiring at least one fuzzy membership function value of each input data based on a first hidden layer in a neural network;
acquiring a fusion membership function value of the normalized multiple input data based on a second hidden layer in the neural network;
acquiring an abnormal rule obtained based on a fusion membership function value of an abnormal rule parameter, input data and a plurality of input data based on a third hidden layer in the neural network, performing iterative training on the neural network model based on comparison between an output actual abnormal rule and an actual abnormal reason fed back by an abnormal deletion loop, and correcting the abnormal rule parameter and the model parameter, wherein the abnormal rule parameter comprises a self-defined threshold value and a self-defined logic or expression in the abnormal rule;
and judging the reason of the abnormality based on the trained neural network model and the multi-dimensional data when the abnormality occurs.
2. The system according to claim 1, further comprising an abnormal information manual forwarding unit, wherein when the number of abnormal causes evaluated by the abnormal rule evaluation unit is more than one, the abnormal cause analysis unit registers the abnormal information and the plurality of abnormal causes in an abnormal cause analysis result table and forwards an abnormal cause confirmation task to the manual forwarding unit to wait for manual processing.
3. The system according to claim 1, wherein when the anomaly rule evaluation unit is invoked by the anomaly cause analysis unit, the anomaly information is grouped by taking a evaluation subject code as a unit, and then the same group of anomaly information is invoked with at least one evaluation rule according to a diagnosis subject to obtain the matched anomaly cause.
4. The system according to claim 3, wherein the abnormality cause analysis unit registers the obtained abnormality cause analysis result in the abnormality cause analysis result table and updates the state of the abnormality information in the database when the abnormality rule evaluation unit is called.
5. The abnormality deletion management system based on the abnormality information database increment according to claim 1, wherein the abnormality deletion processing execution unit includes:
the work order primary filtering part judges whether the abnormal information work order to be processed has a general rule according to the judging rule participated in the abnormal rule judging part, and the work order primary filtering part stops the abnormal deletion processing execution process of the abnormal information work order without the general rule;
and the work order secondary filtering part is used for stopping the abnormal deletion processing execution process of the abnormal information work order in a preset white list of the object related to the abnormal reason of the work order to be processed in the work order to be processed after being filtered by the work order primary filtering part.
6. The anomaly deletion management system based on the anomaly information database increment as claimed in claim 5, wherein the work order primary filtering part is used for associating the abnormal information work order with a preset anomaly criterion record table according to the database primary key id1 in the anomaly information database when performing the common rule participation judgment on the abnormal information work order, and judging whether at least one id2 is within a preset threshold interval range or not for at least one anomaly criterion primary key id2 associated with the abnormal information work order in the anomaly criterion record table.
7. The abnormality deletion management system based on the abnormality information database increment according to claim 5, wherein the abnormality deletion processing execution unit further includes:
and the work order dispatching unit is used for dispatching the work orders after determining the grade, the processing mode and the work order template of the work orders in the work orders to be processed after being filtered by the work order secondary filtering unit, and simultaneously registering the relevant information of the work orders to the abnormal work order table of the metering device.
8. The anomaly elimination management system according to claim 7, wherein said work order dispatch section suspends dispatch processing when an unfinished work order is detected in the metrology device anomaly work order table while the dispatch processing is being performed.
9. The anomaly elimination management system based on anomaly information database deltas of claim 7 wherein said work order dispatch section has the highest of all sorts of grades as the final result when at the explicit work order grade.
10. The abnormal defect elimination management method based on the abnormal information database increment is characterized by comprising the following steps of:
executing the timing query on the database for the abnormal record of the unanalyzed reason and the abnormal record of the analyzed reason which does not enter the abnormal deletion processing execution part;
executing an abnormal reason analysis flow for the abnormal record of the unanalyzed reason, wherein the abnormal reason analysis flow is predetermined to be executed by at least calling an abnormal rule study and judgment part;
executing exception deletion processing on exception information of which the unique exception cause is determined by the exception cause analysis part;
when the abnormal reason analysis process is executed, the abnormal reason analysis part determines whether to enter an abnormal deletion processing execution part or not by taking the number of the abnormal reasons obtained by the abnormal rule research and judgment part as a condition;
the abnormal rule studying and judging part comprises an abnormal studying and judging rule obtained through the implicit relation among the mining data of the machine learning algorithm deep level, and the implicit relation among the mining data of the machine learning algorithm deep level comprises the following steps:
inputting the monitoring data into a preset neural network based on various monitoring data, wherein the monitoring data comprises: electrical data, power equipment marketing records, work order maintenance records, and fault data;
acquiring at least one fuzzy membership function value of each input data based on a first hidden layer in a neural network;
acquiring a fusion membership function value of the normalized multiple input data based on a second hidden layer in the neural network;
acquiring an abnormal rule obtained based on a fusion membership function value of an abnormal rule parameter, input data and a plurality of input data based on a third hidden layer in the neural network, performing iterative training on the neural network model based on comparison between an output actual abnormal rule and an actual abnormal reason fed back by an abnormal deletion loop, and correcting the abnormal rule parameter and the model parameter, wherein the abnormal rule parameter comprises a self-defined threshold value and a self-defined logic or expression in the abnormal rule;
and judging the reason of the abnormality based on the trained neural network model and the multi-dimensional data when the abnormality occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521653.6A CN112527778B (en) | 2020-12-21 | 2020-12-21 | Abnormal defect elimination management system and method based on abnormal information database increment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521653.6A CN112527778B (en) | 2020-12-21 | 2020-12-21 | Abnormal defect elimination management system and method based on abnormal information database increment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112527778A CN112527778A (en) | 2021-03-19 |
| CN112527778B true CN112527778B (en) | 2022-08-02 |
Family
ID=75002256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011521653.6A Active CN112527778B (en) | 2020-12-21 | 2020-12-21 | Abnormal defect elimination management system and method based on abnormal information database increment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112527778B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837720A (en) * | 2021-09-16 | 2021-12-24 | 江苏方天电力技术有限公司 | Abnormal recovery method and system for electric power marketing archive change electric energy meter |
| CN113591813B (en) * | 2021-09-29 | 2022-02-08 | 国网江苏省电力有限公司营销服务中心 | Association rule algorithm-based abnormity studying and judging method, model construction method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636124A (en) * | 2018-11-18 | 2019-04-16 | 韩霞 | Power industry low-voltage platform area line loss analyzing method and processing system based on big data |
| CN111178855A (en) * | 2020-01-09 | 2020-05-19 | 广东卓维网络有限公司 | Electric quantity data monitoring method |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
-
2020
- 2020-12-21 CN CN202011521653.6A patent/CN112527778B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636124A (en) * | 2018-11-18 | 2019-04-16 | 韩霞 | Power industry low-voltage platform area line loss analyzing method and processing system based on big data |
| CN111178855A (en) * | 2020-01-09 | 2020-05-19 | 广东卓维网络有限公司 | Electric quantity data monitoring method |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112527778A (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| CN112527778B (en) | Abnormal defect elimination management system and method based on abnormal information database increment | |
| CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| CN107666148B (en) | Line fault studying and judging method based on distribution transformer power failure signal | |
| KR20030011921A (en) | Rotating equipment diagnostic system and adaptive controller | |
| CN113762604B (en) | Industrial Internet big data service system | |
| CN110688389A (en) | Transformer substation secondary equipment defect cloud management system | |
| CN113111955A (en) | Line loss abnormal data expert system and detection method | |
| CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
| CN109409780B (en) | Change processing method, device, computer equipment and storage medium | |
| CN111476380A (en) | Cable overhauls auxiliary test platform | |
| CN115130578A (en) | Incremental rough clustering-based online evaluation method for state of power distribution equipment | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| CN109409629B (en) | Acquisition terminal manufacturer evaluation method based on multi-attribute decision model | |
| CN114529166A (en) | Power distribution network operation safety risk early warning method and system | |
| CN117170980B (en) | Early warning method, device, equipment and storage medium for server hardware abnormality | |
| CN117013687A (en) | Electric power operation quality monitoring method and system | |
| CN109670550B (en) | Power distribution terminal maintenance decision method and device | |
| CN112288180A (en) | Comprehensive order dispatching method and system for distribution network maintenance work order | |
| CN116307844A (en) | Low-voltage transformer area line loss evaluation analysis method | |
| CN113408915B (en) | Production line bottleneck identification method and system | |
| CN114936801A (en) | Distribution network dispatching operation management method based on big data | |
| CN110727912B (en) | Method for selecting differential transformation scheme of power secondary equipment | |
| Piplani et al. | Simplification strategies for simulation models of semiconductor facilities | |
| CN107590591A (en) | A kind of environmental protection treatment station big data and its application system construction method |
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 |