CN116629709B - Intelligent analysis alarm system of power supply index - Google Patents
Intelligent analysis alarm system of power supply index Download PDFInfo
- Publication number
- CN116629709B CN116629709B CN202310896198.5A CN202310896198A CN116629709B CN 116629709 B CN116629709 B CN 116629709B CN 202310896198 A CN202310896198 A CN 202310896198A CN 116629709 B CN116629709 B CN 116629709B
- Authority
- CN
- China
- Prior art keywords
- power supply
- index data
- supply index
- data
- analysis
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 45
- 238000005065 mining Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 230000005856 abnormality Effects 0.000 claims abstract description 20
- 238000007405 data analysis Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000009469 supplementation Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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 relates to the technical field of data analysis, in particular to an intelligent analysis alarm system for power supply indexes, which comprises: and a data acquisition module: the power supply index data are used for acquiring power supply index data; and a pretreatment module: the power supply index data preprocessing method comprises the steps of preprocessing acquired power supply index data; and the intelligent digging module is used for: the abnormal power supply index data is used for mining and acquiring the preprocessed power supply index data based on a data analysis algorithm; an anomaly analysis module: the power supply system is used for carrying out anomaly analysis on the acquired anomaly power supply index data based on a Bayesian algorithm; an abnormality alarm module: and the system is used for alarming to the control center according to the abnormal analysis result. According to the invention, the power supply index data are mined through the data analysis algorithm, the classification effect of the power supply index data is ensured through a rough set processing mode, the accuracy and the execution efficiency of data clustering are improved, and the abnormal power supply index data are identified and classified through the Bayesian algorithm, so that the classification accuracy, the convergence speed and the stability of the abnormal information are improved.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to an intelligent analysis alarm system for power supply indexes.
Background
The key of the current power supply service center daily work is distribution network operation monitoring, rush repair command and user customer service problem answering, and comprehensive statistical analysis is difficult to implement on data, so that interactive sharing can not be completed among multiple types of data, and the unfolding state of each work is very passive. Under the background, for supplying higher-quality power supply service quality, a power supply service command center integrating regulation, control, monitoring, network distribution, rush repair and dispatching services is arranged, so that resources are integrated as much as possible, the power supply service command becomes a data hub, and the power supply service is more accurate, humanized and convenient. At present, the power supply index is abnormal due to the loss caused by unexpected faults of the power supply line and the like. The prior art can solve part of problems by recording or monitoring unexpected faults in a power supply network and the like, but the detection of the initial stages of the unexpected faults is not timely caused to consume a great deal of unnecessary cost. Therefore, how to realize the efficient and safe abnormal timely monitoring of the power supply index and the unexpected faults in the alarm power grid is an urgent problem to be solved for improving the economic benefit of the power supply enterprises.
Disclosure of Invention
The invention aims to solve the defects in the background technology by providing an intelligent analysis alarm system for power supply indexes.
The technical scheme adopted by the invention is as follows:
an intelligent analysis alarm system for power supply index is provided, comprising:
and a data acquisition module: the power supply index data are used for acquiring power supply index data;
and a pretreatment module: the power supply index data preprocessing method comprises the steps of preprocessing acquired power supply index data;
and the intelligent digging module is used for: the abnormal power supply index data is used for mining and acquiring the preprocessed power supply index data based on a data analysis algorithm;
an anomaly analysis module: the power supply system is used for carrying out anomaly analysis on the acquired anomaly power supply index data based on a Bayesian algorithm;
an abnormality alarm module: and the system is used for alarming to the control center according to the abnormal analysis result.
As a preferred technical scheme of the invention: and the preprocessing module performs missing value supplementation and data normalization processing on the acquired power supply index data.
As a preferred technical scheme of the invention: the data normalization processing steps are as follows:
;
wherein ,represents the normalized power supply index data, +.>Representing the collected power supply index data,/->Represents the maximum value in the collected power supply index data, < >>Representing the minimum value in the collected power supply index data.
As a preferred technical scheme of the invention: and when the intelligent mining module is used for mining that abnormal power supply index data does not exist, repeatedly mining the updated power supply index data based on a data analysis algorithm until the mining is used for obtaining the abnormal power supply index data in the updated power supply index data, and transmitting the abnormal power supply index data obtained by the mining to an abnormality analysis module for abnormality analysis.
As a preferred technical scheme of the invention: the data analysis algorithm of the intelligent mining module is specifically as follows:
constructing a power supply index data warehouse, and calculating initial entropy of power supply index data:
;
wherein ,classifying the power supply data into class numbers; performing entropy reduction calculation according to the power supply index data attribute transformation:
;
wherein ,for lowering entropy value->For the total number of power supply index data, < >>The total number of the power supply index data meeting the conversion requirement is set; there are N subsets within the power indicator data processing set formed by the entropy reduction calculation.
As a preferred technical scheme of the invention: in the data analysis algorithm, the rough set is used for acquiring the first of N subsetsPower supply index data of the centers of the clusters +.>Density function of->The following are provided:
;
wherein ,representing power supply index data sets in N subsets, < >>Power supply index data representing the remaining clusters, +.>Representing a neighborhood radius;
;
power supply index dataWeight of +.>The method comprises the following steps:
;
wherein ,representing cluster center set, +.>Representing a boundary field;
obtain the firstCenter point of each cluster->:
;
wherein ,indicate->Density function value maximum value of power supply data of each cluster, < ->Indicate->The density function value of the power supply data of each cluster is a sub-large value; />Is->The number of power index data in the clusters; />Representing an empty set;
calculating the distance from each power supply index data in the subset to the clustering center:
;
Obtaining an effective data processing model:
;
And mining the power supply index data by using the constructed data processing model to obtain abnormal power supply index data.
As a preferred technical scheme of the invention: the abnormality analysis module obtains the data characteristics of the power supply index data and sets according to the difference of occurrence frequency of the conventional abnormality informationDetermining different prior probabilitiesThe method comprises the steps of carrying out a first treatment on the surface of the Dividing the classification category of the power supply index data set and the corresponding threshold interval, circularly judging the probability of the power supply index data conforming to the threshold interval, and outputting a Bayesian classification probability value when the probability meets the maximization condition.
As a preferred technical scheme of the invention: bayesian classification probability valueThe calculation is as follows;
;
wherein ,represents the +.>Individual classification category->Express input->Individual power supply index data features,/->Representing a priori probabilities of being acquired in advance,/-)>Indicating about->The +.>Individual classification category probability->Representing the algorithm set coefficients.
As a preferred technical scheme of the invention: in the anomaly analysis module, training samples are set to correct Bayesian classification probability values, the anomaly information of different categories is subjected to probabilistic classification, all subsets are subjected to piecewise iteration by taking probability relations as convergence conditions, and the power supply index data in the power supply index data warehouse is traversed and then an anomaly information result is output.
As a preferred technical scheme of the invention: the abnormal information result comprises abnormal information type and abnormal power supply index data.
Compared with the prior art, the intelligent analysis alarm system for the power supply index has the beneficial effects that:
according to the invention, the power supply index data are mined through the data analysis algorithm, the data clustering accuracy and the execution efficiency are improved on the basis of constant classification effect of the power supply index data by the rough set processing mode, and the data processing effect can be improved by mining the abnormal data in the power supply index data. And then the abnormal power supply index data is identified and classified according to the probability coefficient set by the Bayesian algorithm according to different types of the abnormal information, so that the abnormal information classification accuracy, convergence speed and stability are improved.
Drawings
Fig. 1 is a system block diagram of a preferred embodiment of the present invention.
The meaning of each label in the figure is: 100. a data acquisition module; 200. a preprocessing module; 300. an intelligent digging module; 400. an anomaly analysis module; 500. and an abnormality alarm module.
Detailed Description
It should be noted that, under the condition of no conflict, the embodiments of the present embodiments and features in the embodiments may be combined with each other, and the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a preferred embodiment of the present invention provides an intelligent analysis alarm system for power supply indexes, including:
the data acquisition module 100: the power supply index data are used for acquiring power supply index data;
preprocessing module 200: the power supply index data preprocessing method comprises the steps of preprocessing acquired power supply index data;
intelligent mining module 300: the abnormal power supply index data is used for mining and acquiring the preprocessed power supply index data based on a data analysis algorithm;
anomaly analysis module 400: the power supply system is used for carrying out anomaly analysis on the acquired anomaly power supply index data based on a Bayesian algorithm;
abnormality alarm module 500: and the system is used for alarming to the control center according to the abnormal analysis result.
The preprocessing module 200 performs missing value supplementation and data normalization processing on the acquired power supply index data.
The data normalization processing steps are as follows:
;
wherein ,represents the normalized power supply index data, +.>Representing the collected power supply index data,/->Represents the maximum value in the collected power supply index data, < >>Representing the minimum value in the collected power supply index data.
When the intelligent mining module 300 mines that no abnormal power supply index data exists, the updated power supply index data is repeatedly mined based on a data analysis algorithm until the mining obtains the abnormal power supply index data in the updated power supply index data, and the abnormal power supply index data obtained by the mining is transmitted to the abnormality analysis module 400 for abnormality analysis.
The data analysis algorithm of the intelligent mining module 300 is specifically as follows:
constructing a power supply index data warehouse, and calculating initial entropy of power supply index data:
;
wherein ,classifying the power supply data into class numbers; performing entropy reduction calculation according to the power supply index data attribute transformation:
;
wherein ,for lowering entropy value->For the total number of power supply index data, < >>The total number of the power supply index data meeting the conversion requirement is set; there are N subsets within the power indicator data processing set formed by the entropy reduction calculation.
In the data analysis algorithm, the rough set is used for acquiring the first of N subsetsPower supply index data of the centers of the clusters +.>Density function of->The following are provided:
;
wherein ,representing power supply index data sets in N subsets, < >>Power supply index data representing the remaining clusters, +.>Representing a neighborhood radius;
;
power supply index dataWeight of +.>The method comprises the following steps:
wherein ,representing cluster center set, +.>Representing a boundary field;
obtain the firstCenter point of each cluster->:
;
wherein ,indicate->Density function value maximum value of power supply data of each cluster, < ->Indicate->The density function value of the power supply data of each cluster is a sub-large value; />Is->The number of power index data in the clusters; />Representing an empty set;
calculating the distance from each power supply index data in the subset to the clustering center:
;
Obtaining an effective data processing model:
;
And mining the power supply index data by using the constructed data processing model to obtain abnormal power supply index data.
In the anomaly analysis module 400, data characteristics of power supply index data are obtained, and different prior probabilities are set according to the difference of occurrence frequencies of the conventional anomaly informationThe method comprises the steps of carrying out a first treatment on the surface of the Dividing the classification category of the power supply index data set and the corresponding threshold interval, circularly judging the probability of the power supply index data conforming to the threshold interval, and outputting a Bayesian classification probability value when the probability meets the maximization condition. The abnormal information result comprises abnormal information type and abnormal power supply index data.
Bayesian classification probability valueThe calculation is as follows;
;
wherein ,represents the +.>Individual classification category->Express input->Individual power supply index data features,/->Representing a priori probabilities of being acquired in advance,/-)>Indicating about->The +.>Individual classification category probability->Representing the algorithm set coefficients.
In the anomaly analysis module 400, training samples are set to correct the probability values of Bayesian classification, the anomaly information of different categories is classified in a probabilistic manner, all subsets are subjected to piecewise iteration by taking the probability relation as a convergence condition, and the power supply index data in the power supply index data warehouse is traversed and then an anomaly information result is output. The abnormal information result comprises abnormal information type and abnormal power supply index data.
Specifically, the method comprises the following steps:
1. preprocessing training data: the training dataset is divided into features (inputs) and categories (outputs).
2. Calculating a priori probabilities: statistics of +.>The frequency of occurrence in the training data set is then divided by the total number of samples of the training data set.
3. Calculating conditional probabilities: for each category->Calculating each feature +.under this category>Conditional probability of (2). This is usually done by counting the number of classes +.>Lower appearance feature->And then divided by the total number of samples under that category.
4. For newly input power supply index data, a Bayesian formula is used for calculating posterior probability of each category. This requires the use of a priori probabilities +.>And conditional probability->。
5. Selecting the class with the greatest posterior probabilityAs a result of classification of the newly input power supply index data.
6. For convergence conditions and piecewise iterations, if the posterior probability changes during successive iterations are less than a predetermined threshold, or a maximum number of iterations is reached, the iteration is stopped. And summarizing and outputting the abnormal information result of each subset.
In the specific implementation process of this embodiment, because of sparsity of the power supply index data, the probability is possibly zero due to data sparsity, and this embodiment uses laplace smoothing to smooth the probability. The zero probability problem is avoided by adding a non-zero constant to each possible eigenvalue. In calculating conditional probabilitiesLaplacian smoothing is applied.
Wherein, the original conditional probability calculation formula:
;
and (3) applying a conditional probability calculation formula after Laplace smoothing:
;
then the Laplace smoothed Bayesian formula is used:
;
in this embodiment, the data acquisition module 100 acquires power supply index data in the power supply system, and the preprocessing module 200 performs missing value supplementation and normalization processing on the acquired power supply index data:
;
wherein ,represents the normalized power supply index data, +.>Representing the collected power supply index data,/->Represents the maximum value in the collected power supply index data, < >>Representing the minimum value in the collected power supply index data.
The intelligent mining module 300 normalizes the power supply index dataAnd (5) performing intelligent excavation. Firstly, constructing a power supply index data warehouse, and calculating initial entropy of power supply index data>:
;
wherein ,classifying the power supply data into class numbers; performing entropy reduction calculation according to the power supply index data attribute transformation:
;
wherein ,for lowering entropy value->For the total number of power supply index data, < >>The total number of the power supply index data meeting the conversion requirement is set; there are N subsets within the power indicator data processing set formed by the entropy reduction calculation.
Acquiring the first of N subsets using a coarse setPower supply index data of the centers of the clusters +.>Density function of->The following are provided:
wherein ,representing power supply index data sets in N subsets, < >>The number of clusters in N subsets is represented, and 18 cluster centers are provided, and the number of clusters is +.>Power supply index data representing the remaining clusters, +.>Representing a neighborhood radius;
;
power supply index dataWeight of +.>The method comprises the following steps:
;
wherein ,representing cluster center set, +.>Representing a boundary field;
obtain the firstCenter point of each cluster->:
;
wherein ,indicate->Density function value maximum value of power supply data of each cluster, < ->Indicate->The density function value of the power supply data of each cluster is a sub-large value; />Is->The number of power index data in the clusters; />Representing an empty set;
calculating the distance from each power supply index data in the subset to the clustering center:
;
Obtaining an effective data processing model:
;
And mining the power supply index data by using the constructed data processing model to obtain abnormal power supply index data.
The anomaly analysis module 400 obtains the data characteristics of the power supply index data, and sets the prior probabilities of different anomaly information based on the difference of the occurrence frequencies of the historical anomaly informationAnd divide the power supply fingersThe classification category of the standard data and the threshold interval corresponding to the classification, the probability of the power supply index data conforming to the threshold interval is circularly judged, and when the maximization condition is met, a Bayesian classification probability value is output>:
;
wherein ,represents the +.>Individual classification category->Express input->Individual power supply index data features,/->Representing a priori probabilities of being acquired in advance,/-)>Indicating about->The +.>Individual classification category probability->Representing the algorithm set coefficients.
Setting Bayesian classification probability values acquired by a plurality of training sample pairsMake correctionsThe method comprises the steps of carrying out probability classification on abnormal information of different categories, namely abnormal power supply index data which does not belong to a threshold value interval, carrying out segment iteration on all subsets by taking a probability relation as a convergence condition, traversing the power supply index data in a power supply index data warehouse, and outputting the abnormal information category and the abnormal power supply index data. The abnormality alarm module 500 alarms according to the outputted abnormality information type and abnormality power supply index data.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (7)
1. An intelligent analysis alarm system of power supply index, which is characterized in that: comprising the following steps:
data acquisition module (100): the power supply index data are used for acquiring power supply index data;
pretreatment module (200): the power supply index data preprocessing method comprises the steps of preprocessing acquired power supply index data;
intelligent excavation module (300): the abnormal power supply index data is used for mining and acquiring the preprocessed power supply index data based on a data analysis algorithm;
abnormality analysis module (400): the power supply system is used for carrying out anomaly analysis on the acquired anomaly power supply index data based on a Bayesian algorithm;
abnormality alarm module (500): the system is used for alarming to a control center according to an abnormality analysis result;
when the intelligent mining module (300) is used for mining that abnormal power supply index data does not exist, the updated power supply index data is repeatedly mined based on a data analysis algorithm until the mining is used for acquiring the abnormal power supply index data in the updated power supply index data, and the abnormal power supply index data acquired by mining is transmitted to the abnormality analysis module (400) for abnormality analysis;
the data analysis algorithm of the intelligent mining module (300) is specifically as follows:
constructing a power supply index data warehouse, and calculating initial entropy of power supply index data:
;
wherein ,classifying the power supply data into class numbers; performing entropy reduction calculation according to the power supply index data attribute transformation:
;
wherein ,for lowering entropy value->For the total number of power supply index data, < >>Power supply index data aggregate to meet conversion requirementsA number; n subsets exist in a power supply index data processing set formed by entropy reduction calculation;
in the data analysis algorithm, the rough set is used for acquiring the first of N subsetsPower supply index data of cluster centersDensity function of->The following are provided:
;
wherein ,representing power supply index data sets in N subsets, < >>Power supply index data representing the remaining clusters, +.>Representing a neighborhood radius;
;
power supply index dataWeight of +.>The method comprises the following steps:
;
wherein ,representing cluster center set, +.>Representing a boundary field;
obtain the firstCenter point of each cluster->:
;
wherein ,indicate->Density function value maximum value of power supply data of each cluster, < ->Indicate->The density function value of the power supply data of each cluster is a sub-large value; />Is->The number of power index data in the clusters; />Representing an empty set;
calculating the distance from each power supply index data in the subset to the clustering center:
;
Obtaining an effective data processing model:
;
And mining the power supply index data by using the constructed data processing model to obtain abnormal power supply index data.
2. The power indicator intelligent analysis alarm system according to claim 1, wherein: the preprocessing module (200) performs missing value supplementation and data normalization processing on the acquired power supply index data.
3. The power indicator intelligent analysis alarm system according to claim 2, wherein: the data normalization processing steps are as follows:
;
wherein ,represents the normalized power supply index data, +.>Representing the collected power supply index data,/->Represents the maximum value in the collected power supply index data, < >>Representing the minimum value in the collected power supply index data.
4. The power indicator intelligent analysis alarm system according to claim 1, wherein: in the abnormality analysis module (400), data characteristics of power supply index data are acquired, and different prior probabilities are set according to the difference of occurrence frequencies of the conventional abnormality informationThe method comprises the steps of carrying out a first treatment on the surface of the Dividing the classification category of the power supply index data set and the corresponding threshold interval, circularly judging the probability of the power supply index data conforming to the threshold interval, and outputting a Bayesian classification probability value when the probability meets the maximization condition.
5. The power indicator intelligent analysis alarm system according to claim 1, wherein: bayesian classification probability valueThe calculation is as follows;
;
wherein ,represents the +.>Individual classification category->Express input->Individual power supply index data features,/->Representing a priori probabilities of being acquired in advance,/-)>Indicating about->The +.>Individual classification category probability->Representing the algorithm set coefficients.
6. The power indicator intelligent analysis alarm system according to claim 1, wherein: in the anomaly analysis module (400), training samples are set to correct Bayesian classification probability values, probability classification is carried out on anomaly information of different categories, segmentation iteration is carried out on all subsets by taking probability relations as convergence conditions, and anomaly information results are output after power supply index data in a power supply index data warehouse are traversed.
7. The power indicator intelligent analysis alarm system according to claim 6, wherein: the abnormal information result comprises abnormal information type and abnormal power supply index data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310896198.5A CN116629709B (en) | 2023-07-21 | 2023-07-21 | Intelligent analysis alarm system of power supply index |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310896198.5A CN116629709B (en) | 2023-07-21 | 2023-07-21 | Intelligent analysis alarm system of power supply index |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116629709A CN116629709A (en) | 2023-08-22 |
CN116629709B true CN116629709B (en) | 2023-10-20 |
Family
ID=87621597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310896198.5A Active CN116629709B (en) | 2023-07-21 | 2023-07-21 | Intelligent analysis alarm system of power supply index |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116629709B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117273471A (en) * | 2023-11-22 | 2023-12-22 | 天津市德丰金属制品有限公司 | Method and system for supervising steel wire production process |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
CN106022477A (en) * | 2016-05-18 | 2016-10-12 | 国网信通亿力科技有限责任公司 | Intelligent analysis decision system and method |
CN109409628A (en) * | 2018-08-17 | 2019-03-01 | 国网浙江省电力有限公司 | Acquisition terminal production firm evaluation method based on metering big data Clustering Model |
CN113919416A (en) * | 2021-09-09 | 2022-01-11 | 天津科技大学 | High-dimensional data anomaly detection method, related system and device and storage medium |
CN114048870A (en) * | 2021-11-04 | 2022-02-15 | 佳源科技股份有限公司 | Power system abnormity monitoring method based on log characteristic intelligent mining |
CN114254691A (en) * | 2021-11-05 | 2022-03-29 | 国网辽宁省电力有限公司营销服务中心 | Multi-channel operation wind control method based on active identification and intelligent monitoring |
CN115345392A (en) * | 2021-05-12 | 2022-11-15 | 中国石油化工股份有限公司 | Abnormal situation studying and judging and key index screening method for power distribution network |
CN115423051A (en) * | 2022-11-04 | 2022-12-02 | 长春工程学院 | Power inspection data mining, equipment state classification and risk prediction system and method |
CN115561546A (en) * | 2022-09-19 | 2023-01-03 | 苏州新吴源电力工程有限公司 | Abnormity detection and alarm system for power system |
CN116451097A (en) * | 2023-04-19 | 2023-07-18 | 天津商业大学 | Power load data weighted incremental clustering method capable of adaptively determining clustering number |
-
2023
- 2023-07-21 CN CN202310896198.5A patent/CN116629709B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
CN106022477A (en) * | 2016-05-18 | 2016-10-12 | 国网信通亿力科技有限责任公司 | Intelligent analysis decision system and method |
CN109409628A (en) * | 2018-08-17 | 2019-03-01 | 国网浙江省电力有限公司 | Acquisition terminal production firm evaluation method based on metering big data Clustering Model |
CN115345392A (en) * | 2021-05-12 | 2022-11-15 | 中国石油化工股份有限公司 | Abnormal situation studying and judging and key index screening method for power distribution network |
CN113919416A (en) * | 2021-09-09 | 2022-01-11 | 天津科技大学 | High-dimensional data anomaly detection method, related system and device and storage medium |
CN114048870A (en) * | 2021-11-04 | 2022-02-15 | 佳源科技股份有限公司 | Power system abnormity monitoring method based on log characteristic intelligent mining |
CN114254691A (en) * | 2021-11-05 | 2022-03-29 | 国网辽宁省电力有限公司营销服务中心 | Multi-channel operation wind control method based on active identification and intelligent monitoring |
CN115561546A (en) * | 2022-09-19 | 2023-01-03 | 苏州新吴源电力工程有限公司 | Abnormity detection and alarm system for power system |
CN115423051A (en) * | 2022-11-04 | 2022-12-02 | 长春工程学院 | Power inspection data mining, equipment state classification and risk prediction system and method |
CN116451097A (en) * | 2023-04-19 | 2023-07-18 | 天津商业大学 | Power load data weighted incremental clustering method capable of adaptively determining clustering number |
Non-Patent Citations (1)
Title |
---|
孟海东.《大数据挖掘技术与应用》.冶金工业出版社,2014,(第1版),31-37. * |
Also Published As
Publication number | Publication date |
---|---|
CN116629709A (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fan et al. | A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data | |
CN107391772B (en) | Text classification method based on naive Bayes | |
CN111314353B (en) | Network intrusion detection method and system based on hybrid sampling | |
CN108985380B (en) | Point switch fault identification method based on cluster integration | |
CN110990461A (en) | Big data analysis model algorithm model selection method and device, electronic equipment and medium | |
CN116629709B (en) | Intelligent analysis alarm system of power supply index | |
CN109934301B (en) | Power load cluster analysis method, device and equipment | |
CN103455563A (en) | Data mining method applicable to integrated monitoring system of intelligent substation | |
CN106682835B (en) | Data-driven complex electromechanical system service quality state evaluation method | |
CN109582714B (en) | Government affair item data processing method based on time attenuation association | |
CN108241925A (en) | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection | |
CN111401573A (en) | Working condition state modeling and model correcting method | |
CN110348683A (en) | The main genetic analysis method, apparatus equipment of electrical energy power quality disturbance event and storage medium | |
CN110796159A (en) | Power data classification method and system based on k-means algorithm | |
CN114417971A (en) | Electric power data abnormal value detection algorithm based on K nearest neighbor density peak clustering | |
CN110059938B (en) | Power distribution network planning method based on association rule driving | |
CN110795610B (en) | Clustering-based power load analysis method | |
CN112905671A (en) | Time series exception handling method and device, electronic equipment and storage medium | |
CN114444573A (en) | Power customer label generation method based on big data clustering technology | |
CN116128544A (en) | Active auditing method and system for electric power marketing abnormal business data | |
CN116226693A (en) | Gaussian mixture model nuclear power operation condition division method based on density peak clustering | |
CN115313522A (en) | Spare capacity configuration method and system considering new energy output prediction deviation | |
CN111680852B (en) | Method and system for monitoring overall energy consumption of area | |
CN110955811B (en) | Power data classification method and system based on naive Bayes algorithm | |
Rahman et al. | Iterative Feature Selection Using Information Gain & Naïve Bayes for Document Classification |
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 |