CN117475593A - Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal - Google Patents
Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal Download PDFInfo
- Publication number
- CN117475593A CN117475593A CN202311799023.9A CN202311799023A CN117475593A CN 117475593 A CN117475593 A CN 117475593A CN 202311799023 A CN202311799023 A CN 202311799023A CN 117475593 A CN117475593 A CN 117475593A
- Authority
- CN
- China
- Prior art keywords
- early warning
- result
- task
- power utilization
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000005611 electricity Effects 0.000 title abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 230000007246 mechanism Effects 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims description 34
- 230000005856 abnormality Effects 0.000 claims description 32
- 238000005070 sampling Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 16
- 230000035945 sensitivity Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 5
- 238000011157 data evaluation Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 206010063385 Intellectualisation Diseases 0.000 abstract description 9
- 238000012545 processing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an advanced intelligent early warning method and device for abnormal load of an electricity utilization terminal, which are applied to the technical field of data processing, and the method comprises the following steps: and generating equipment characteristics of the power utilization terminal, and establishing node mapping of time sequence nodes and tasks. And executing data acquisition of the power utilization terminal, and establishing a risk attention mechanism. And performing anomaly identification of the data acquisition result based on the anomaly detection network. And acquiring an initial abnormal recognition result, and performing early warning prediction through equipment characteristics and execution tasks to generate a first early warning prediction result. And establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, generating a second early warning prediction result according to the continuous monitoring result, and performing advanced early warning management of the power utilization terminal by the early warning prediction result. The method solves the technical problems that in the prior art, the early warning method for the abnormal load of the power utilization terminal is low in intellectualization, and the advanced early warning of the abnormal load is difficult to realize, so that the safety of the power utilization terminal is difficult to improve.
Description
Technical Field
The invention relates to the field of data processing, in particular to an advanced intelligent early warning method and device for abnormal load of an electricity utilization terminal.
Background
Along with the development of intelligence, various power utilization terminals in production and life are improved intelligently, and the use safety of the power utilization terminals is further improved. However, in the prior art, the load early warning of the power utilization terminal can only warn the load abnormality in the current state, the early warning method of the load abnormality of the power utilization terminal is low in intellectualization, and advanced early warning of the load abnormality is difficult to realize, so that the safety of the power utilization terminal is difficult to improve.
Therefore, the early warning method for the abnormal load of the power utilization terminal in the prior art is low in intellectualization, and the advanced early warning of the abnormal load is difficult to realize, so that the technical problem that the safety of the power utilization terminal is difficult to improve is solved.
Disclosure of Invention
By providing the advanced intelligent early warning method and the device for the abnormal load of the power utilization terminal, the technical problems that in the prior art, the early warning method for the abnormal load of the power utilization terminal is low in intellectualization and difficult to realize, and the safety of the power utilization terminal is difficult to improve are solved.
The application provides an advanced intelligent early warning method for abnormal load of an electricity utilization terminal, which comprises the following steps: calling terminal data of the power utilization terminal to generate equipment characteristics of the power utilization terminal; acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, and establishing node mapping between the time sequence node and the task; executing data acquisition of the power utilization terminal according to the acquisition strategy of the node mapping configuration combination sensor; performing abnormal triggering risk fitting based on the equipment characteristics and the execution task, and establishing a risk attention mechanism; initializing network sensitivity of an anomaly detection network by using the risk attention mechanism, and executing anomaly identification of a data acquisition result; acquiring an initial abnormal recognition result, and performing early warning prediction through the equipment characteristics and the execution task to generate a first early warning prediction result; establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, and generating a second early warning prediction result according to the continuous monitoring result; and performing advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
The application also provides an advanced intelligent early warning device for abnormal load of the power utilization terminal, which comprises: the device characteristic acquisition module is used for calling terminal data of the power utilization terminal and generating device characteristics of the power utilization terminal; the task time sequence mapping module is used for acquiring the execution task of the power utilization terminal, extracting time sequence nodes for executing the task and establishing node mapping between the time sequence nodes and the task; the data acquisition module is used for configuring an acquisition strategy of the combined sensor according to the node mapping and executing data acquisition of the power utilization terminal; the risk fitting module is used for performing abnormal triggering risk fitting based on the equipment characteristics and the execution task and establishing a risk attention mechanism; the abnormality identification module is used for initializing the network sensitivity of the abnormality detection network by the risk attention mechanism and executing the abnormality identification of the data acquisition result; the first early warning module is used for acquiring an initial abnormal recognition result, carrying out early warning prediction through the equipment characteristics and the execution task and generating a first early warning prediction result; the second early warning module is used for establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space and generating a second early warning prediction result according to the continuous monitoring result; and the early warning management module is used for carrying out advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
The application also provides an electronic device, comprising:
a memory for storing executable instructions;
and the processor is used for realizing the advanced intelligent early warning method for the abnormal load of the power utilization terminal when executing the executable instructions stored in the memory.
The application provides a computer readable storage medium which stores a computer program, and when the program is executed by a processor, the advanced intelligent early warning method for the abnormal load of the power utilization terminal is realized.
The advanced intelligent early warning method and the advanced intelligent early warning device for the abnormal load of the power utilization terminal are used for generating equipment characteristics of the power utilization terminal and establishing node mapping of time sequence nodes and tasks. And executing data acquisition of the power utilization terminal, and establishing a risk attention mechanism. And performing anomaly identification of the data acquisition result based on the anomaly detection network. And acquiring an initial abnormal recognition result, and performing early warning prediction through equipment characteristics and execution tasks to generate a first early warning prediction result. And establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, generating a second early warning prediction result according to the continuous monitoring result, and performing advanced early warning management of the power utilization terminal by the early warning prediction result. The early warning of the abnormal load of the power utilization terminal is realized, the intellectualization of the load abnormality warning method is improved, and the safety of the power utilization terminal is improved. The method solves the technical problems that in the prior art, the early warning method for the abnormal load of the power utilization terminal is low in intellectualization, and the advanced early warning of the abnormal load is difficult to realize, so that the safety of the power utilization terminal is difficult to improve.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
Fig. 1 is a schematic flow chart of an advanced intelligent early warning method for abnormal load of an electricity consumption terminal according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for obtaining a second early warning prediction result by using an advanced intelligent early warning method for power consumption terminal load abnormality provided in an embodiment of the present application;
fig. 3 is a schematic flow chart of a first early warning prediction result obtained by an advanced intelligent early warning method for abnormal load of an electricity consumption terminal according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a device of an advanced intelligent early warning method for abnormal load of an electricity consumption terminal according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device of an advanced intelligent early warning method for abnormal load of an electricity consumption terminal according to an embodiment of the present invention.
Reference numerals illustrate: the device characteristic acquisition module 11, the task timing mapping module 12, the data acquisition module 13, the risk fitting module 14, the anomaly identification module 15, the first early warning module 16, the second early warning module 17, the early warning management module 18, the processor 31, the memory 32, the input device 33 and the output device 34.
Detailed Description
Example 1
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a particular ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a particular order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only.
While the present application makes various references to certain modules in an apparatus according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, the modules are merely illustrative, and different aspects of the apparatus and method may use different modules.
A flowchart is used in this application to describe the operations performed by an apparatus according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
As shown in fig. 1, an embodiment of the present application provides an advanced intelligent early warning method for abnormal load of an electricity consumption terminal, where the method includes:
calling terminal data of the power utilization terminal to generate equipment characteristics of the power utilization terminal;
acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, and establishing node mapping between the time sequence node and the task;
executing data acquisition of the power utilization terminal according to the acquisition strategy of the node mapping configuration combination sensor;
performing abnormal triggering risk fitting based on the equipment characteristics and the execution task, and establishing a risk attention mechanism;
and calling terminal data of the power utilization terminal to obtain terminal electric equipment and generating equipment characteristics of the power utilization terminal, wherein the equipment characteristics of the power utilization terminal comprise equipment types, power utilization basic attributes of the equipment and execution task data of the equipment, such as execution task data of manufacturing equipment. And then, acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, namely a time node for executing each task, and establishing a node mapping between the time sequence node and the task, wherein the node mapping is a relation between the task and the execution time node. Further, the acquisition strategy of the combined sensor is configured according to the node mapping, namely, the acquisition time strategy of the combined sensor is configured according to the time node of the equipment when the task is executed, and the data acquisition of the power utilization terminal is executed. Based on the device features and the executing task, abnormal triggering risk fitting is carried out, existing triggering risk features of the device during executing the task, such as current abnormal risk, voltage abnormal risk, temperature abnormal risk and the like, are obtained, the importance degree of each risk feature is the importance degree of the risk feature preset by the device, each device corresponds to the importance degree of each risk feature preset, a risk attention mechanism is established based on the importance degree of the triggering risk feature and the risk feature, and the higher the importance degree of the risk feature is, the higher the risk attention of the corresponding risk feature is, and the higher the network sensitivity in the subsequent processing process is.
Initializing network sensitivity of an anomaly detection network by using the risk attention mechanism, and executing anomaly identification of a data acquisition result;
acquiring an initial abnormal recognition result, and performing early warning prediction through the equipment characteristics and the execution task to generate a first early warning prediction result;
establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, and generating a second early warning prediction result according to the continuous monitoring result;
and performing advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
Initializing network sensitivity of an anomaly detection network by using the risk attention mechanisms, wherein each risk attention mechanism corresponds to the existence of specific network sensitivity, the network sensitivity is specific data analysis times, the higher the data analysis times are, the more analysis times of data acquisition results are, the more accurate the analysis results are acquired, and the anomaly identification of the data acquisition results is executed based on the network sensitivity. And then, acquiring an initial abnormal recognition result, and carrying out early warning prediction through the equipment characteristics and the execution task to generate a first early warning prediction result. And establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, and generating a second early warning prediction result according to the continuous monitoring result. And finally, carrying out comprehensive early warning value calculation according to the first early warning prediction result and the second early warning prediction result, obtaining a comprehensive early warning value calculation result, and carrying out advanced early warning management of the power utilization terminal according to the early warning value calculation result. The early warning of the abnormal load of the power utilization terminal is realized, the intellectualization of the load abnormality warning method is improved, and the safety of the power utilization terminal is improved.
The method provided by the embodiment of the application further comprises the following steps:
extracting basic attribute characteristics from the equipment characteristics;
taking the basic attribute characteristics as basic matching characteristics, and performing monitoring data matching under big data;
establishing an evaluation data set based on the monitoring data matching result, wherein the evaluation data set comprises a forward data set and a reverse data set;
classifying the evaluation data set according to preset proportion, and establishing a construction data set, a punishment data set and a test data set;
the initial construction of the anomaly detection network is carried out by the construction data set, and punishment compensation is carried out by the punishment data set;
and when the test result of the test data set on the anomaly detection network is a passing result, completing construction of the anomaly detection network.
And extracting basic attribute characteristics from the equipment characteristics. And further, taking the basic attribute characteristics as basic matching characteristics, and performing monitoring data matching under big data. And establishing an evaluation data set based on the monitoring data matching result, wherein the evaluation data set comprises a forward data set and a reverse data set, the forward data set is a normal parameter, and the reverse data set is a parameter with abnormality. And then, classifying the evaluation data sets according to a preset proportion, namely classifying the evaluation data sets according to proportion to obtain a construction data set, a punishment data set and a test data set. And performing initial construction of the anomaly detection network by using the constructed data set, performing supervised training on the neural network model by using the constructed data set, obtaining a trained model, and performing punishment compensation by using the punishment data set, namely performing secondary training on the model by using the punishment data set on the basis of the trained model, and obtaining a secondary training model. And finally, testing the model subjected to secondary training by using a test data set, and completing construction of the anomaly detection network when the test result of the test data set on the anomaly detection network is a passing result.
The method provided by the embodiment of the application further comprises the following steps:
carrying out data clustering on the evaluation data set, and determining N clustering centers;
extracting the N clustering centers as punishment data sets;
randomly classifying the evaluation data set data after eliminating the punishment data set according to a preset proportion;
and completing the establishment of the constructed data set and the test data set based on the random classification result.
And carrying out data clustering on the evaluation data set, and determining N clustering centers. And extracting the N clustering centers as a punishment data set, namely expanding the data of the N clustering centers according to a preset proportion, and extracting the data which meet the proportion and belong to the expanded data of the N clustering centers to be used as the punishment data set. And further, randomly classifying the evaluation data set data after eliminating the punishment data set according to a preset proportion, namely eliminating the punishment data set according to the preset proportion, randomly classifying according to the proportion, and completing establishment of the construction data set and the test data set based on a random classification result.
The method provided by the embodiment of the application further comprises the following steps:
invoking the mapping exception of the initial exception identification result, and extracting an exception rule of the mapping exception;
configuring a sampling period, a sampling frequency and attention feature data according to the abnormal rule;
and the establishment of the continuous early warning space is completed based on the sampling period, the sampling frequency and the attention characteristic data.
When the continuous early warning space is established, the mapping abnormality is obtained by calling the mapping abnormality of the initial abnormality identification result, namely, obtaining the corresponding abnormality characteristic data in the initial abnormality identification result, such as the abnormality identification result caused by the current characteristic data, the voltage characteristic data and the like of the equipment in the initial abnormality identification result, and extracting the abnormality rule of the mapping abnormality. The abnormal rule of mapping abnormality is a node where corresponding characteristic data generates mutation in a plurality of continuous time nodes, for example, current characteristic data increases or decreases in a plurality of continuous time nodes. And then, configuring a sampling period, a sampling frequency and the attention characteristic data according to the abnormal rule, wherein the sampling period is the total time period of a plurality of continuous time nodes, the sampling frequency is the sampling frequency corresponding to the number of the plurality of time nodes, the sampling frequency corresponding to the larger number of the plurality of time nodes is lower, and the sampling frequency corresponding to the smaller number of the plurality of time nodes is higher. The attention feature data is the corresponding abnormal feature. And finally, the establishment of a continuous early warning space is completed based on the sampling period, the sampling frequency and the attention characteristic data, so that the equipment data is sampled, and a continuous monitoring result is obtained.
As shown in fig. 2, the method provided in the embodiment of the present application further includes:
carrying out homodromous deviation evaluation of the concerned feature data based on the continuous monitoring results, wherein the homodromous deviation evaluation results are obtained by taking data acquisition results corresponding to the first early warning prediction results as reference data evaluation;
performing early warning verification based on the total deviation degree and the deviation amplitude of the homodromous deviation evaluation result;
and generating the second early warning prediction result according to the early warning verification result.
And carrying out homodromous deviation evaluation on the attention characteristic data based on the continuous monitoring result, acquiring data of a plurality of continuous time nodes generating homodromous deviation when carrying out the homodromous deviation evaluation, and acquiring total deviation degree and deviation amplitude according to the data of the plurality of continuous time nodes, wherein the total deviation degree is the total deviation value of the plurality of continuous time nodes, and the deviation amplitude is the average deviation value of each node. And the homodromous deviation evaluation result is obtained by taking a data acquisition result corresponding to the first early warning prediction result as reference data evaluation. And carrying out early warning verification based on the total deviation degree and the deviation amplitude of the homodromous deviation evaluation result, judging whether the total deviation degree and the deviation amplitude are larger than or equal to a preset total deviation degree threshold value and a preset deviation amplitude threshold value, when one data of the total deviation degree and the deviation amplitude is larger than or equal to the preset total deviation degree threshold value and the deviation amplitude threshold value, indicating that the data has deviation abnormality, acquiring the difference value between the corresponding abnormal data and the total deviation degree threshold value and the deviation amplitude threshold value, and adding the total deviation degree and the deviation amplitude to acquire an early warning verification result if the total deviation degree and the deviation amplitude are abnormal, and generating the second early warning prediction result according to the early warning verification result.
As shown in fig. 3, the method provided in the embodiment of the present application further includes:
performing task analysis on the execution task, and establishing task association based on analysis results;
comparing the tasks by taking the current node task as a reference, and generating a task association value through the task association;
performing feature association analysis of the initial anomaly identification result based on the equipment features to generate feature association values;
and performing the superposition early warning prediction of the abnormal report on the initial abnormal recognition result by using the task association value and the characteristic association value to generate a first early warning prediction result.
And carrying out task analysis on the execution task, obtaining the corresponding equipment load of the execution task, and establishing task association based on analysis results. And comparing the tasks by taking the current node task as a reference, and generating a task association value by the task association, wherein the task association value is the ratio of the current node task equipment load to the equipment load of the predicted execution task. And carrying out feature association analysis on the initial abnormal recognition result based on the equipment features, acquiring the same association features of the execution task and the current task abnormal recognition result when carrying out feature association analysis, and acquiring the same features in the execution task features and the abnormal recognition result to generate feature association values, wherein the feature association values contain all the same abnormal features. And finally, performing superposition early warning prediction of abnormal reporting on the initial abnormal recognition result by using the task association value and the characteristic association value, namely performing data average calculation on the characteristic association value in the acquired initial abnormal recognition result, acquiring a characteristic association value average of the execution task by combining the task association value, acquiring a difference value between the characteristic association value average and the data average, and generating a first early warning prediction result.
The method provided by the embodiment of the application further comprises the following steps:
performing comprehensive early warning value calculation based on the first early warning prediction result and the second early warning prediction result;
if the comprehensive early warning value calculation result meets a preset early warning threshold value, reporting an abnormality;
and controlling the task state of the execution task according to the reported abnormality, and synchronously carrying out abnormal maintenance.
And carrying out comprehensive early warning value calculation based on the first early warning prediction result and the second early warning prediction result, presetting the weight proportion of the first early warning prediction result and the second early warning prediction result when carrying out comprehensive early warning value calculation, and acquiring the weighted average value of the first early warning prediction result and the second early warning prediction result in a weighted average mode based on the weight proportion to obtain a comprehensive early warning value calculation result. Further, if the comprehensive early warning value calculation result meets the preset early warning threshold, the preset early warning threshold is the highest threshold data of the preset comprehensive early warning value calculation result, when the preset early warning threshold is larger than or equal to the preset early warning threshold, the corresponding comprehensive early warning value calculation result has higher anomaly degree, the anomaly is reported, and then the stopping operation of the execution task and the equipment upgrading maintenance can be performed. And when the preset early warning threshold value is smaller than the preset early warning threshold value, the execution task can be normally executed. And finally, controlling the task state of the execution task according to the reported abnormality, and synchronously carrying out abnormal maintenance.
According to the technical scheme provided by the embodiment of the invention, the equipment characteristics of the power utilization terminal are generated by calling the terminal data of the power utilization terminal. And acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, and establishing a node mapping of the time sequence node and the task. And executing data acquisition of the power utilization terminal according to the acquisition strategy of the node mapping configuration combination sensor. And performing abnormal triggering risk fitting based on the equipment characteristics and the execution task, and establishing a risk attention mechanism. Initializing the network sensitivity of the anomaly detection network by the risk attention mechanism, and executing anomaly identification of the data acquisition result. And acquiring an initial abnormal recognition result, and performing early warning prediction through the equipment characteristics and the execution task to generate a first early warning prediction result. And establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, and generating a second early warning prediction result according to the continuous monitoring result. And performing advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result. The early warning of the abnormal load of the power utilization terminal is realized, the intellectualization of the load abnormality warning method is improved, and the safety of the power utilization terminal is improved. The method solves the technical problems that in the prior art, the early warning method for the abnormal load of the power utilization terminal is low in intellectualization, and the advanced early warning of the abnormal load is difficult to realize, so that the safety of the power utilization terminal is difficult to improve.
Example two
Based on the same inventive concept as the advanced intelligent early warning method for abnormal load of the electricity consumption terminal in the foregoing embodiment, the present invention further provides a device for the advanced intelligent early warning method for abnormal load of the electricity consumption terminal, which may be implemented by hardware and/or software, and may be generally integrated in an electronic device, for executing the method provided by any embodiment of the present invention. As shown in fig. 4, the apparatus includes:
the device characteristic acquisition module 11 is used for calling terminal data of the power utilization terminal and generating device characteristics of the power utilization terminal;
the task time sequence mapping module 12 is used for acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, and establishing node mapping between the time sequence node and the task;
the data acquisition module 13 is used for configuring an acquisition strategy of the combined sensor according to the node mapping, and executing data acquisition of the power utilization terminal;
a risk fitting module 14, configured to perform abnormal triggering risk fitting based on the device features and the execution task, and establish a risk attention mechanism;
an anomaly identification module 15, configured to initialize a network sensitivity of an anomaly detection network with the risk attention mechanism, and perform anomaly identification of a data acquisition result;
the first early warning module 16 is configured to obtain an initial anomaly identification result, and perform early warning prediction through the device feature and the execution task, so as to generate a first early warning prediction result;
the second early warning module 17 is configured to establish a continuous early warning space according to the initial anomaly identification result, perform continuous monitoring of the combination sensor based on the continuous early warning space, and generate a second early warning prediction result according to the continuous monitoring result;
and the early warning management module 18 is used for performing advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
Further, the anomaly identification module 15 is further configured to:
extracting basic attribute characteristics from the equipment characteristics;
taking the basic attribute characteristics as basic matching characteristics, and performing monitoring data matching under big data;
establishing an evaluation data set based on the monitoring data matching result, wherein the evaluation data set comprises a forward data set and a reverse data set;
classifying the evaluation data set according to preset proportion, and establishing a construction data set, a punishment data set and a test data set;
the initial construction of the anomaly detection network is carried out by the construction data set, and punishment compensation is carried out by the punishment data set;
and when the test result of the test data set on the anomaly detection network is a passing result, completing construction of the anomaly detection network.
Further, the anomaly identification module 15 is further configured to:
carrying out data clustering on the evaluation data set, and determining N clustering centers;
extracting the N clustering centers as punishment data sets;
randomly classifying the evaluation data set data after eliminating the punishment data set according to a preset proportion;
and completing the establishment of the constructed data set and the test data set based on the random classification result.
Further, the second early warning module 17 is further configured to:
invoking the mapping exception of the initial exception identification result, and extracting an exception rule of the mapping exception;
configuring a sampling period, a sampling frequency and attention feature data according to the abnormal rule;
and the establishment of the continuous early warning space is completed based on the sampling period, the sampling frequency and the attention characteristic data.
Further, the second early warning module 17 is further configured to:
carrying out homodromous deviation evaluation of the concerned feature data based on the continuous monitoring results, wherein the homodromous deviation evaluation results are obtained by taking data acquisition results corresponding to the first early warning prediction results as reference data evaluation;
performing early warning verification based on the total deviation degree and the deviation amplitude of the homodromous deviation evaluation result;
and generating the second early warning prediction result according to the early warning verification result.
Further, the first early warning module 16 is further configured to:
performing task analysis on the execution task, and establishing task association based on analysis results;
comparing the tasks by taking the current node task as a reference, and generating a task association value through the task association;
performing feature association analysis of the initial anomaly identification result based on the equipment features to generate feature association values;
and performing the superposition early warning prediction of the abnormal report on the initial abnormal recognition result by using the task association value and the characteristic association value to generate a first early warning prediction result.
Further, the early warning management module 18 is further configured to:
performing comprehensive early warning value calculation based on the first early warning prediction result and the second early warning prediction result;
if the comprehensive early warning value calculation result meets a preset early warning threshold value, reporting an abnormality;
and controlling the task state of the execution task according to the reported abnormality, and synchronously carrying out abnormal maintenance.
The included units and modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Example III
Fig. 5 is a schematic structural diagram of an electronic device provided in a third embodiment of the present invention, and shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. The electronic device shown in fig. 5 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention. As shown in fig. 5, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device may be one or more, in fig. 5, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33 and the output device 34 in the electronic device may be connected by a bus or other means, in fig. 5, by bus connection is taken as an example.
The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to the advanced intelligent early warning method for abnormal load of the power utilization terminal in the embodiment of the invention. The processor 31 executes various functional applications and data processing of the computer device by running software programs, instructions and modules stored in the memory 32, namely, the advanced intelligent early warning method for abnormal load of the power utilization terminal is realized.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. The advanced intelligent early warning method for the abnormal load of the power utilization terminal is characterized by comprising the following steps of:
calling terminal data of the power utilization terminal to generate equipment characteristics of the power utilization terminal;
acquiring an execution task of the power utilization terminal, extracting a time sequence node for executing the task, and establishing node mapping between the time sequence node and the task;
executing data acquisition of the power utilization terminal according to the acquisition strategy of the node mapping configuration combination sensor;
performing abnormal triggering risk fitting based on the equipment characteristics and the execution task, and establishing a risk attention mechanism;
initializing network sensitivity of an anomaly detection network by using the risk attention mechanism, and executing anomaly identification of a data acquisition result;
acquiring an initial abnormal recognition result, and performing early warning prediction through the equipment characteristics and the execution task to generate a first early warning prediction result;
establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space, and generating a second early warning prediction result according to the continuous monitoring result;
and performing advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
2. The method of claim 1, wherein the method further comprises:
extracting basic attribute characteristics from the equipment characteristics;
taking the basic attribute characteristics as basic matching characteristics, and performing monitoring data matching under big data;
establishing an evaluation data set based on the monitoring data matching result, wherein the evaluation data set comprises a forward data set and a reverse data set;
classifying the evaluation data set according to preset proportion, and establishing a construction data set, a punishment data set and a test data set;
the initial construction of the anomaly detection network is carried out by the construction data set, and punishment compensation is carried out by the punishment data set;
and when the test result of the test data set on the anomaly detection network is a passing result, completing construction of the anomaly detection network.
3. The method of claim 2, wherein the method further comprises:
carrying out data clustering on the evaluation data set, and determining N clustering centers;
extracting the N clustering centers as punishment data sets;
randomly classifying the evaluation data set data after eliminating the punishment data set according to a preset proportion;
and completing the establishment of the constructed data set and the test data set based on the random classification result.
4. The method of claim 1, wherein the method further comprises:
invoking the mapping exception of the initial exception identification result, and extracting an exception rule of the mapping exception;
configuring a sampling period, a sampling frequency and attention feature data according to the abnormal rule;
and the establishment of the continuous early warning space is completed based on the sampling period, the sampling frequency and the attention characteristic data.
5. The method of claim 4, wherein the method further comprises:
carrying out homodromous deviation evaluation of the concerned feature data based on the continuous monitoring results, wherein the homodromous deviation evaluation results are obtained by taking data acquisition results corresponding to the first early warning prediction results as reference data evaluation;
performing early warning verification based on the total deviation degree and the deviation amplitude of the homodromous deviation evaluation result;
and generating the second early warning prediction result according to the early warning verification result.
6. The method of claim 1, wherein the method further comprises:
performing task analysis on the execution task, and establishing task association based on analysis results;
comparing the tasks by taking the current node task as a reference, and generating a task association value through the task association;
performing feature association analysis of the initial anomaly identification result based on the equipment features to generate feature association values;
and performing the superposition early warning prediction of the abnormal report on the initial abnormal recognition result by using the task association value and the characteristic association value to generate a first early warning prediction result.
7. The method of claim 1, wherein the method further comprises:
performing comprehensive early warning value calculation based on the first early warning prediction result and the second early warning prediction result;
if the comprehensive early warning value calculation result meets a preset early warning threshold value, reporting an abnormality;
and controlling the task state of the execution task according to the reported abnormality, and synchronously carrying out abnormal maintenance.
8. The utility model provides an unusual advanced intelligent early warning device of power consumption terminal load which characterized in that, the device includes:
the device characteristic acquisition module is used for calling terminal data of the power utilization terminal and generating device characteristics of the power utilization terminal;
the task time sequence mapping module is used for acquiring the execution task of the power utilization terminal, extracting time sequence nodes for executing the task and establishing node mapping between the time sequence nodes and the task;
the data acquisition module is used for configuring an acquisition strategy of the combined sensor according to the node mapping and executing data acquisition of the power utilization terminal;
the risk fitting module is used for performing abnormal triggering risk fitting based on the equipment characteristics and the execution task and establishing a risk attention mechanism;
the abnormality identification module is used for initializing the network sensitivity of the abnormality detection network by the risk attention mechanism and executing the abnormality identification of the data acquisition result;
the first early warning module is used for acquiring an initial abnormal recognition result, carrying out early warning prediction through the equipment characteristics and the execution task and generating a first early warning prediction result;
the second early warning module is used for establishing a continuous early warning space according to the initial abnormal recognition result, continuously monitoring the combined sensor based on the continuous early warning space and generating a second early warning prediction result according to the continuous monitoring result;
and the early warning management module is used for carrying out advanced early warning management on the power utilization terminal according to the first early warning prediction result and the second early warning prediction result.
9. An electronic device, the electronic device comprising:
a memory for storing executable instructions;
and the processor is used for realizing the advanced intelligent early warning method for the abnormal load of the power utilization terminal according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.
10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the advanced intelligent pre-warning method of load anomalies for an electrical terminal according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311799023.9A CN117475593B (en) | 2023-12-26 | 2023-12-26 | Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311799023.9A CN117475593B (en) | 2023-12-26 | 2023-12-26 | Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117475593A true CN117475593A (en) | 2024-01-30 |
| CN117475593B CN117475593B (en) | 2024-04-12 |
Family
ID=89625913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311799023.9A Active CN117475593B (en) | 2023-12-26 | 2023-12-26 | Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117475593B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117667751A (en) * | 2024-02-01 | 2024-03-08 | 道普信息技术有限公司 | Automatic testing method for low-coupling WEB service |
| CN117692345A (en) * | 2024-02-01 | 2024-03-12 | 山东厚普信息技术有限公司 | IT operation method and system based on artificial intelligence |
| CN117914003A (en) * | 2024-03-19 | 2024-04-19 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675490A (en) * | 2012-08-31 | 2014-03-26 | 国网电力科学研究院 | Electrical load monitoring device, system and method |
| CN104361452A (en) * | 2014-11-14 | 2015-02-18 | 云南电网公司 | Big consumer abnormal electricity consumption pre-warning system with multiple networks integrated |
| CN112234620A (en) * | 2020-11-05 | 2021-01-15 | 九江创新电子有限公司 | Terminal equipment and method for managing power factor and load of special transformer user |
| CN113884723A (en) * | 2021-09-08 | 2022-01-04 | 国网山东省电力公司淄博供电公司 | User power consumption behavior analysis display terminal based on power consumption information |
| CN115642706A (en) * | 2022-11-16 | 2023-01-24 | 国网山东省电力公司胶州市供电公司 | Power distribution load monitoring system in power grid |
| WO2023087525A1 (en) * | 2021-11-19 | 2023-05-25 | 中国华能集团清洁能源技术研究院有限公司 | Multi-modal deep learning power generation device anomaly integrated identification method and device |
| CN116896064A (en) * | 2023-05-31 | 2023-10-17 | 江苏易立电气股份有限公司 | Power utilization characteristic analysis system and method for power utilization load |
-
2023
- 2023-12-26 CN CN202311799023.9A patent/CN117475593B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103675490A (en) * | 2012-08-31 | 2014-03-26 | 国网电力科学研究院 | Electrical load monitoring device, system and method |
| CN104361452A (en) * | 2014-11-14 | 2015-02-18 | 云南电网公司 | Big consumer abnormal electricity consumption pre-warning system with multiple networks integrated |
| CN112234620A (en) * | 2020-11-05 | 2021-01-15 | 九江创新电子有限公司 | Terminal equipment and method for managing power factor and load of special transformer user |
| CN113884723A (en) * | 2021-09-08 | 2022-01-04 | 国网山东省电力公司淄博供电公司 | User power consumption behavior analysis display terminal based on power consumption information |
| WO2023087525A1 (en) * | 2021-11-19 | 2023-05-25 | 中国华能集团清洁能源技术研究院有限公司 | Multi-modal deep learning power generation device anomaly integrated identification method and device |
| CN115642706A (en) * | 2022-11-16 | 2023-01-24 | 国网山东省电力公司胶州市供电公司 | Power distribution load monitoring system in power grid |
| CN116896064A (en) * | 2023-05-31 | 2023-10-17 | 江苏易立电气股份有限公司 | Power utilization characteristic analysis system and method for power utilization load |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117667751A (en) * | 2024-02-01 | 2024-03-08 | 道普信息技术有限公司 | Automatic testing method for low-coupling WEB service |
| CN117692345A (en) * | 2024-02-01 | 2024-03-12 | 山东厚普信息技术有限公司 | IT operation method and system based on artificial intelligence |
| CN117667751B (en) * | 2024-02-01 | 2024-04-19 | 道普信息技术有限公司 | Automatic testing method for low-coupling WEB service |
| CN117692345B (en) * | 2024-02-01 | 2024-06-11 | 山东厚普信息技术有限公司 | IT operation method and system based on artificial intelligence |
| CN117914003A (en) * | 2024-03-19 | 2024-04-19 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
| CN117914003B (en) * | 2024-03-19 | 2024-05-24 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117475593B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117475593B (en) | Advanced intelligent early warning method and device for abnormal load of electricity utilization terminal | |
| CN110927606B (en) | Battery state monitoring method and device | |
| CN113111591B (en) | Automatic diagnosis method, device and equipment based on internal fault of modular power distribution terminal | |
| CN112083244A (en) | Integrated avionics equipment fault intelligent diagnosis system | |
| CN115514620B (en) | Anomaly detection method and cloud network platform | |
| CN106656669A (en) | Equipment parameter abnormity detection system and method based on self-adaptive setting of threshold | |
| CN113542241A (en) | Intrusion detection method and device based on CNN-BiGRU mixed model | |
| CN113313280B (en) | Cloud platform inspection method, electronic equipment and nonvolatile storage medium | |
| CN111257753A (en) | Battery system fault diagnosis method | |
| CN114745407B (en) | Security situation awareness method, device, equipment and medium of electric power Internet of things | |
| CN115729815A (en) | Fuzzy test method, device, equipment and storage medium based on weighted random | |
| CN117312807B (en) | Control state analysis method and system of circuit breaker | |
| CN110399926B (en) | Street lamp fault diagnosis method and device | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN117149486B (en) | Alarm and root cause positioning method, model training method, device, equipment and medium | |
| CN117951646A (en) | Data fusion method and system based on edge cloud | |
| CN117218405A (en) | Digital fault diagnosis method for battery production equipment | |
| Chang et al. | Fault diagnosis of lithium-ion batteries based on voltage dip behavior | |
| CN118330395B (en) | Cable fault supervision method and system based on multidimensional performance monitoring | |
| Li et al. | Abnormal recognition of massive electric power data based on RF and CNN | |
| CN112465259B (en) | Switch fault prediction method based on deep neural network | |
| CN117591876A (en) | Breaker fault diagnosis method, device, equipment and storage medium | |
| Cui et al. | A Method for Intermittent Fault Diagnosis of Electronic Equipment Based on Labeled SOM | |
| CN118688548A (en) | Transformer state detection method and device | |
| CN114928468A (en) | Network security sensing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |