CN117808157B - Intelligent identification-based unreported outage behavior prediction analysis system - Google Patents
Intelligent identification-based unreported outage behavior prediction analysis system Download PDFInfo
- Publication number
- CN117808157B CN117808157B CN202311853452.XA CN202311853452A CN117808157B CN 117808157 B CN117808157 B CN 117808157B CN 202311853452 A CN202311853452 A CN 202311853452A CN 117808157 B CN117808157 B CN 117808157B
- Authority
- CN
- China
- Prior art keywords
- real
- power
- time
- historical
- power consumption
- 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 88
- 230000005611 electricity Effects 0.000 claims abstract description 58
- 238000012216 screening Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 50
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 16
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Emergency Management (AREA)
- Manufacturing & Machinery (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention relates to the technical field of intelligent identification data analysis, in particular to an unreported power failure behavior prediction analysis system based on intelligent identification, which comprises a data acquisition module, a feature extraction module, a data screening module and an intelligent alarm module; the data acquisition module acquires sample data of historical electricity utilization and real-time electricity utilization data; the characteristic extraction module acquires the historical power failure frequency and the corresponding historical power consumption power of each period, and acquires a power failure characteristic coefficient according to the correlation calculation; the data screening module performs data screening on the real-time power consumption and acquires an analysis result of suspected power failure; the intelligent alarm module performs calibration analysis to obtain a real-time electricity utilization calibration analysis result, and calculates an alarm prediction coefficient to perform alarm processing. The intelligent power failure prediction method and the intelligent power failure prediction device are used for solving the technical problems that intelligent power failure prediction and alarm processing are inaccurate.
Description
Technical Field
The invention relates to the technical field of intelligent identification data analysis, in particular to an unreported power failure behavior prediction analysis system based on intelligent identification.
Background
Intelligent recognition refers to the process of recognizing and analyzing data such as images, voice, text and the like by utilizing artificial intelligence technology. Intelligent recognition is based on artificial intelligence technology, and realizes automatic analysis, recognition and understanding of various types of data by simulating the cognitive process of human beings.
The technology has wide application in the fields of image recognition, voice recognition, natural language processing and the like, and can help people to process and understand a large amount of data information more efficiently. However, the potential problem of predicting the unreported power outage behavior based on the intelligent recognition technology is not easy to find, better power outage detection and prevention cannot be provided, certain power is generated every time the power outage of a factory, when factory equipment is running, the error of monitoring data can cause inaccurate prediction results, and the power outage behavior cannot be accurately alarmed, so that the effectiveness and reliability of a power outage prediction analysis system are reduced, and the problem to be solved is urgent.
Disclosure of Invention
The invention aims to solve the problems in the background technology, and provides an intelligent identification-based unreported outage behavior prediction analysis system.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
The intelligent identification-based unreported outage behavior prediction analysis system comprises: the device comprises a data acquisition module, a characteristic extraction module, a data screening module and an intelligent alarm module;
the data acquisition module is used for acquiring sample data of historical electricity utilization and real-time electricity utilization data;
The data acquisition module comprises a historical sample data acquisition unit and a real-time operation data acquisition unit, wherein the historical sample data acquisition unit is used for acquiring historical electricity sample data, dividing time periods to acquire the historical electricity sample data, acquiring the historical power failure frequency and the corresponding historical electricity power of each electricity utilization period, and transmitting acquired information to the feature extraction module; the real-time operation data acquisition unit is used for acquiring real-time electricity utilization data of the current equipment, storing the acquired data into the database and simultaneously transmitting the acquired data to the data screening module;
The characteristic extraction module is used for receiving information of the historical sample data acquisition unit, acquiring historical power failure frequency and corresponding historical power consumption of each period, performing calculation and analysis according to correlation of the historical power failure frequency and the corresponding historical power consumption of each power consumption period, establishing a regression equation, and acquiring a power failure characteristic coefficient;
The data screening module is used for receiving information of the real-time operation data acquisition unit, acquiring reference ranges of abnormal power and normal power, calculating abnormal power consumption probability to determine a critical value of the abnormal power consumption probability, carrying out data screening on the real-time power consumption of the current equipment, generating a suspected abnormal signal of the real-time power consumption to obtain an analysis result of suspected power failure, and sending the analysis result to the intelligent alarm module;
the intelligent alarm module is used for performing calibration analysis on the analysis result of suspected power failure to obtain a real-time power consumption calibration analysis result, calculating an alarm prediction coefficient, acquiring different-level instructions, and performing different-level alarm processing on the different-level instructions.
It should be noted that, in the embodiment of the present invention, the application object of the unreported outage behavior prediction analysis system based on intelligent recognition may be data quality monitoring of the power energy usage status of the manufacturing plant, and specifically may be accurate intelligent prediction and alarm processing for the outage behavior of the manufacturing plant, where the monitoring index of the monitored outage data is the outage frequency and the power consumption index.
Further, the process of the historical sample data collection unit for collecting the historical electricity sample data comprises the following steps:
Acquiring historical electricity consumption sample data of the power system, and dividing the historical electricity consumption sample data according to time periods;
Taking 6 months as a power utilization period, and collecting power utilization data according to the power utilization period;
the method comprises the steps of obtaining the historical power failure frequency and the corresponding historical power consumption power of each power consumption period, storing the collected information into a database, marking the information as a historical power consumption database, and simultaneously sending the information to a feature extraction module.
Further, the step of acquiring the real-time electricity utilization data of the current device by the real-time operation data acquisition unit includes:
Acquiring real-time electricity utilization data of the current equipment, taking one week as a monitoring period, and acquiring real-time electricity utilization power of the equipment;
and storing the acquired data into a database, marking the acquired data as a real-time electricity utilization database, and simultaneously transmitting the acquired data to a data screening module.
Further, the feature extraction module establishes a regression equation according to the correlation between the historical power outage frequency and the corresponding historical power consumption, and the process of calculating and obtaining the power outage feature coefficient comprises
Receiving information of a historical sample data acquisition unit, acquiring historical electricity sample data of each period, and representing the data acquisition performed each time by i, wherein i=1, 2,3, … … and n; n is a positive integer;
Marking the historical power failure frequency and the corresponding historical power consumption as x i and y i respectively;
the data y i and x i are subjected to mean value and summation, and calculated to obtain />
Taking the historical power failure frequency as a control point, and carrying out regression analysis according to the correlation of the historical power failure frequency of each power utilization period and the corresponding historical power utilization power to establish a regression equation;
The power outage characteristic coefficient TD is calculated and analyzed through a power outage regression equation, wherein the calculation formula is y=bx+a, and the data unit is megawatt, in the formula,
The data collected in the embodiment of the invention is the power failure frequency of the factory in recent years, which takes half a year as a monitoring period, because the annual production efficiency or high or low of the factory is unstable, and the power load is different, the factory generates certain power consumption once each time the power fails, the power consumption refers to the power consumption value of stopping once power, a regression equation is established according to the correlation of the power consumption value and the power consumption value, the calculation process is as follows, the historical power failure frequency of the factory from 2020 to 2022 and the corresponding monitoring data of the historical power consumption are obtained, if x i＝2、1、0、3,yi = 0.005, 0.002, 0.001 and 0.006, then
From this, y= -0.0012x+0.0053 is obtained.
Further, the data screening module performs data screening on the real-time power consumption, and the process of calculating and analyzing to obtain the analysis result of suspected power failure comprises the following steps:
receiving information of a real-time operation data acquisition unit;
Analyzing and judging according to the power failure characteristic coefficient, and judging the corresponding historical power consumption as abnormal power consumption YD when the historical power failure frequency x is not less than 2; obtaining a reference range (ZDmin, ZDmax) of normal electric power of the device;
the abnormal electricity utilization probability YG is obtained through a calculation formula, wherein the calculation formula is as follows: YG= [ (YD-ZD)/ZD ]. Times.100%, and determining critical value A% of abnormal electricity consumption probability according to the calculation result;
The real-time power consumption is obtained, and the serial numbers are marked as SD j, j=1, 2,3, … … and m; m is a positive integer;
Data screening is carried out on the real-time power of the current equipment, the real-time power consumption probability SG is calculated through a calculation formula SG= [ (SD j -ZD)/ZD ] ×100%, if SG is larger than a critical value A of abnormal power consumption probability, the real-time power consumption is marked as SD k, wherein k represents the data number of the real-time power consumption, and a suspected abnormal signal of the real-time power consumption is generated to obtain an analysis result of suspected power failure;
and sending the analysis result of the suspected power failure to an intelligent alarm module.
Further, the process of performing the calibration analysis to obtain the real-time power utilization calibration analysis result by the intelligent alarm module according to the suspected power outage analysis result comprises the following steps:
Performing correction analysis on the analysis result of the suspected power failure to obtain a predicted value YC of the power consumption;
comparing the real-time power SD k corresponding to the suspected abnormal signal of the real-time power with the predicted value YC of the power, when the real-time power SD k is larger than the predicted value YC of the power, determining that the real-time power is abnormal, and generating an abnormal signal of the real-time power; when the real-time power SD k is not greater than the power predicted value YC, determining that the real-time power is normal, and generating a normal signal of the real-time power;
and obtaining a real-time power consumption calibration analysis result by the abnormal signal of the real-time power consumption and the normal signal of the real-time power consumption.
Further, the process of calculating, analyzing and predicting the coefficient by the intelligent alarm module and generating the instructions with different grades comprises the following steps:
Alarm prediction analysis is carried out according to the real-time electricity utilization calibration analysis result, and the analysis result is calculated according to the formula Calculating an alarm prediction coefficient by using the X P, wherein/>The average value of the real-time power consumption corresponding to the obtained suspected abnormal signal of the real-time power consumption is represented, P is a proportionality coefficient preset by an alarm prediction coefficient, and 0< P <1, wherein l=1, 2,3, … … and o; o is a positive integer;
Analyzing and processing the calculation result, and if the numerical range of the alarm prediction coefficient BJ is between (0.6,1), generating a first-level alarm instruction by the system; if the numerical range of the alarm prediction coefficient BJ is between (0.3 and 0.6), the system generates a secondary alarm instruction; if the numerical range of the alarm prediction coefficient BJ is between (0, 0.3), the system generates a three-level alarm instruction;
And the system carries out alarm processing of different levels according to the generated different level instructions.
Compared with the prior art, the invention provides an unreported power failure behavior prediction analysis system based on intelligent identification, which has the advantages that:
1. the invention obtains the sample data and the real-time electricity data of the historical electricity consumption through the data acquisition module, and respectively sends the acquired information to the feature extraction module and the data screening module;
2. According to the invention, the characteristic extraction module receives information of the historical sample data acquisition unit, the historical power failure frequency and the corresponding historical power consumption of each period are obtained, a regression equation is established by calculation and analysis according to the correlation of the historical power failure frequency and the corresponding historical power consumption of each power consumption period, and the power failure characteristic coefficient is obtained;
3. The method comprises the steps of receiving information of a real-time operation data acquisition unit through a data screening module, obtaining a reference range of abnormal electric power and normal electric power, calculating the abnormal electric power probability to determine a critical value of the abnormal electric power probability, carrying out data screening on the real-time electric power of the current equipment, generating a suspected abnormal signal of the real-time electric power to obtain an analysis result of suspected power failure, and sending the analysis result to an intelligent alarm module to ensure that abnormal information is accurate;
4. According to the invention, the intelligent alarm module is used for carrying out the calibration analysis on the analysis result of suspected power failure to obtain the real-time power utilization calibration analysis result, calculating the alarm prediction coefficient, acquiring different-level instructions, and carrying out different-level alarm processing on the different-level instructions, so that the alarm instructions are more accurate.
In summary, the invention can analyze and process the calculation result of the alarm prediction coefficient according to the actual situation, generate different-level instructions, and the system performs different-level alarm processing according to the generated different-level instructions, thereby improving the real-time performance and reliability of the alarm function, and ensuring the normal operation of the follow-up intelligent recognition-based non-backup power outage behavior prediction analysis system through comprehensive prediction data analysis and alarm optimization processing.
Drawings
FIG. 1 is a block diagram of an intelligent recognition-based unreported outage behavior prediction analysis system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. 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, an intelligent recognition-based unreported outage behavior prediction analysis system comprises a data acquisition module, a feature extraction module, a data screening module and an intelligent alarm module;
The data acquisition module is used for acquiring sample data of historical electricity utilization and real-time electricity utilization data; the data acquisition module comprises a historical sample data acquisition unit and a real-time operation data acquisition unit, wherein the historical sample data acquisition unit is used for acquiring historical electricity sample data, dividing time periods to acquire the historical electricity sample data, acquiring the historical power failure frequency and the corresponding historical electricity power of each electricity utilization period, and transmitting acquired information to the feature extraction module; the real-time operation data acquisition unit is used for acquiring real-time electricity utilization data of the current equipment, storing the acquired data into the database and simultaneously transmitting the acquired data to the data screening module;
The characteristic extraction module is used for receiving information of the historical sample data acquisition unit, acquiring historical power failure frequency and corresponding historical power consumption of each period, performing calculation and analysis according to correlation of the historical power failure frequency and the corresponding historical power consumption of each power consumption period, establishing a regression equation, and acquiring a power failure characteristic coefficient;
The data screening module is used for receiving information of the real-time operation data acquisition unit, acquiring reference ranges of abnormal power and normal power, calculating abnormal power consumption probability to determine a critical value of the abnormal power consumption probability, carrying out data screening on the real-time power consumption of the current equipment, generating a suspected abnormal signal of the real-time power consumption to obtain an analysis result of suspected power failure, and sending the analysis result to the intelligent alarm module;
the intelligent alarm module is used for performing calibration analysis on the analysis result of suspected power failure to obtain a real-time power consumption calibration analysis result, calculating an alarm prediction coefficient, acquiring different-level instructions, and performing different-level alarm processing on the different-level instructions.
It should be noted that, in the embodiment of the present invention, the application object of the unreported outage behavior prediction analysis system based on intelligent recognition may be data quality monitoring of the power energy usage status of the manufacturing plant, and specifically may be accurate intelligent prediction and alarm processing for the outage behavior of the manufacturing plant, where the monitoring index of the monitored outage data is the outage frequency and the power consumption index.
The process of the historical sample data acquisition unit for acquiring the historical electricity sample data comprises the following steps:
S101, acquiring historical electricity sample data of a power system, and dividing the historical electricity sample data according to time periods;
s102, taking 6 months as a power utilization period, and collecting power utilization data according to the power utilization period;
S103, acquiring the historical power failure frequency and the corresponding historical power consumption power of each power consumption period, storing the acquired information into a database, marking the acquired information as a historical power consumption database, and simultaneously transmitting the acquired information to a feature extraction module.
The step of acquiring the real-time power utilization data of the current equipment by the real-time operation data acquisition unit comprises the following steps:
s201, acquiring real-time power consumption data of current equipment, taking a week as a monitoring period, and acquiring the real-time power consumption of the equipment;
S202, storing the acquired data into a database, marking the data as a real-time electricity utilization database, and simultaneously sending the data to a data screening module.
The feature extraction module establishes a regression equation according to the correlation between the historical power failure frequency and the corresponding historical power consumption power, and the process of calculating and obtaining the power failure feature coefficient comprises the following steps:
S301, receiving information of a historical sample data acquisition unit, acquiring historical electricity sample data of each period, and representing data acquisition performed each time by using i, wherein i=1, 2,3, … … and n; n is a positive integer;
S302, marking the historical power failure frequency and the corresponding historical power consumption as x i and y i respectively;
S303, carrying out mean value and summation processing on the data x and y, and calculating to obtain And
S304, taking the historical power failure frequency as a control point, and carrying out regression analysis according to the correlation of the historical power failure frequency and the corresponding historical power consumption power of each power consumption period to establish a regression equation;
s305, calculating and analyzing a power failure characteristic coefficient TD through a power failure regression equation, wherein the calculation formula is y=bx+a, and the data unit is megawatt,
The data collected in the embodiment of the invention is the power failure frequency of the factory in recent years, which takes half a year as a monitoring period, because the annual production efficiency or high or low of the factory is unstable, and the power load is different, the factory generates certain power consumption once each time the power fails, the power consumption refers to the power consumption value of stopping once power, a regression equation is established according to the correlation of the power consumption value and the power consumption value, the calculation process is as follows, the historical power failure frequency of the factory from 2020 to 2022 and the corresponding monitoring data of the historical power consumption are obtained, if x i＝2、1、0、3,yi = 0.005, 0.002, 0.001 and 0.006, then
From this, y= -0.0012x+0.0053 is obtained.
The data screening module performs data screening on the real-time power consumption, and the process of calculating and analyzing to obtain the analysis result of suspected power failure comprises the following steps:
S401, receiving information of a real-time operation data acquisition unit;
S402, analyzing and judging according to the power failure characteristic coefficient, and judging the corresponding historical power consumption as abnormal power consumption YD when the historical power failure frequency x is not less than 2; obtaining a reference range (ZDmin, ZDmax) of normal electric power of the device;
S403, obtaining abnormal electricity utilization probability YG through a calculation formula, wherein the calculation formula is as follows: YG= [ (YD-ZD)/ZD ]. Times.100%, and determining critical value A% of abnormal electricity consumption probability according to the calculation result;
s404, acquiring real-time power, and numbering SD j, j=1, 2,3, … … and m; m is a positive integer;
S405, screening data of the real-time power of the current equipment, calculating real-time power consumption probability SG according to a calculation formula SG= [ (SD j -ZD)/ZD ] ×100%, and if SG is greater than a critical value A of abnormal power consumption probability, marking the real-time power consumption as SD k, wherein k represents the data number of the real-time power consumption, and generating a suspected abnormal signal of the real-time power consumption to obtain an analysis result of suspected power failure;
S406, sending the analysis result of the suspected power failure to the intelligent alarm module.
The process of the intelligent alarm module for performing the calibration analysis according to the analysis result of the suspected power failure to obtain the calibration analysis result of the real-time power consumption comprises the following steps:
S501, performing correction analysis on an analysis result of suspected power failure to obtain a predicted value YC of power consumption;
S502, comparing the real-time power SD k corresponding to the suspected abnormal signal of the real-time power with the predicted value YC of the power, and when the real-time power SD k is larger than the predicted value YC of the power, determining that the real-time power is abnormal, and generating an abnormal signal of the real-time power; when the real-time power SD k is not greater than the power predicted value YC, determining that the real-time power is normal, and generating a normal signal of the real-time power;
S503, obtaining a real-time power consumption calibration analysis result from the abnormal signal of the real-time power consumption and the normal signal of the real-time power consumption.
The intelligent alarm module calculates and analyzes the alarm prediction coefficient, and the process of generating different grades of instructions comprises the following steps:
S601, carrying out alarm prediction analysis according to a real-time electricity utilization check analysis result, and passing through a formula In the/>The average value of the real-time power consumption corresponding to the obtained suspected abnormal signal of the real-time power consumption is represented, P is a proportionality coefficient preset by an alarm prediction coefficient, and 0< P <1, wherein l=1, 2,3, … … and o; o is a positive integer;
S602, analyzing and processing a calculation result, and if the numerical range of the alarm prediction coefficient BJ is between (0.6,1), generating a first-level alarm instruction by the system; if the numerical range of the alarm prediction coefficient BJ is between (0.3 and 0.6), the system generates a secondary alarm instruction; if the numerical range of the alarm prediction coefficient BJ is between (0, 0.3), the system generates a three-level alarm instruction;
S603, the system carries out alarm processing of different levels according to the generated different level instructions.
In the embodiment of the invention, the data acquisition module acquires the historical power failure frequency and the corresponding historical power consumption of each power consumption period, the acquired information is transmitted to the feature extraction module, the real-time power consumption data of the current equipment are acquired at the same time, the acquired data are stored in the database and transmitted to the data screening module at the same time, the feature extraction module receives the information of the historical sample data acquisition unit, the historical power failure frequency and the corresponding historical power consumption of each period are acquired, a regression equation is established according to the correlation of the historical power failure frequency and the corresponding historical power consumption of each power consumption period in a calculation and analysis mode, a power failure characteristic coefficient is acquired, the data screening module receives the information of the real-time operation data acquisition unit, the reference range of the abnormal power consumption and the normal power consumption is acquired, the critical value of the abnormal power consumption probability is determined, the real-time power consumption of the current equipment is subjected to data screening, a suspected abnormal signal of the real-time power consumption is generated to obtain a suspected power failure analysis result, the suspected power failure analysis result is transmitted to the intelligent alarm module, the accuracy and the reliability of system monitoring abnormality are improved, the power failure analysis command is obtained by the intelligent alarm module, the intelligent power consumption module is subjected to the calculation and the alarm command is analyzed at different levels, and the same level alarm command is analyzed. In summary, the embodiment of the invention relates to data acquisition analysis, result generation and decision of optimization measures, and solves the problems of inaccurate intelligent prediction and alarm processing of the power outage behavior of the intelligent recognition-based unreported power outage behavior prediction analysis system. In practice, more data and context information may be needed to make specific decisions and optimization schemes.
In this specification, all embodiments are described in a progressive manner, and identical and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described as different from other embodiments. In particular, for the device embodiments, since they are basically based on the method embodiments, the description is relatively simple, and the relevant points are referred to in the description of the method embodiments.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Secondly: in the drawings of the disclosed embodiments, only the structures related to the embodiments of the present disclosure are referred to, other structures can refer to the general design, and the same embodiment and different embodiments of the present disclosure can be combined with each other under the condition of no conflict;
Finally: the foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical solution of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (6)
1. The intelligent identification-based unreported outage behavior prediction analysis system is characterized in that: the system comprises a data acquisition module, a feature extraction module, a data screening module and an intelligent alarm module;
The data acquisition module is used for acquiring sample data of historical electricity utilization and real-time electricity utilization data; the data acquisition module comprises a historical sample data acquisition unit and a real-time operation data acquisition unit, wherein the historical sample data acquisition unit is used for acquiring historical electricity sample data, dividing time periods to acquire the historical electricity sample data, acquiring the historical power failure frequency and the corresponding historical electricity power of each electricity utilization period, and transmitting acquired information to the feature extraction module; the real-time operation data acquisition unit is used for acquiring real-time electricity utilization data of the current equipment, storing the acquired data into the database and simultaneously transmitting the acquired data to the data screening module;
The characteristic extraction module is used for receiving information of the historical sample data acquisition unit, acquiring historical power failure frequency and corresponding historical power consumption of each period, performing calculation and analysis according to correlation of the historical power failure frequency and the corresponding historical power consumption of each power consumption period, establishing a regression equation, and acquiring a power failure characteristic coefficient;
The data screening module is used for receiving information of the real-time operation data acquisition unit, acquiring reference ranges of abnormal power and normal power, calculating abnormal power consumption probability to determine a critical value of the abnormal power consumption probability, carrying out data screening on the real-time power consumption of the current equipment, generating a suspected abnormal signal of the real-time power consumption to obtain an analysis result of suspected power failure, and sending the analysis result to the intelligent alarm module;
the data screening module performs data screening on the real-time power consumption, and the process of calculating and analyzing to obtain the analysis result of suspected power failure comprises the following steps:
receiving information of a real-time operation data acquisition unit;
Analyzing and judging according to the power failure characteristic coefficient, and judging the corresponding historical power consumption as abnormal power consumption YD when the historical power failure frequency x is not less than 2; obtaining a reference range (ZDmin, ZDmax) of normal electric power of the device;
the abnormal electricity utilization probability YG is obtained through a calculation formula, wherein the calculation formula is as follows: YG= [ (YD-ZD)/ZD ]. Times.100%, and determining critical value A% of abnormal electricity consumption probability according to the calculation result;
The real-time power consumption is obtained, and the serial numbers are marked as SD j, j=1, 2,3, … … and m; m is a positive integer;
Data screening is carried out on the real-time power of the current equipment, the real-time power consumption probability SG is calculated through a calculation formula SG= [ (SD j -ZD)/ZD ] ×100%, if SG is larger than a critical value A of abnormal power consumption probability, the real-time power consumption is marked as SD k, wherein k represents the data number of the real-time power consumption, and a suspected abnormal signal of the real-time power consumption is generated to obtain an analysis result of suspected power failure;
sending the analysis result of suspected power failure to an intelligent alarm module;
the intelligent alarm module is used for performing calibration analysis on the analysis result of suspected power failure to obtain a real-time power consumption calibration analysis result, calculating an alarm prediction coefficient, acquiring different-level instructions, and performing different-level alarm processing on the different-level instructions.
2. The intelligent recognition-based unreported outage behavior prediction analysis system according to claim 1, wherein: the process of the historical sample data acquisition unit for acquiring the historical electricity sample data comprises the following steps:
Acquiring historical electricity consumption sample data of the power system, and dividing the historical electricity consumption sample data according to time periods;
Taking 6 months as a power utilization period, and collecting power utilization data according to the power utilization period;
the method comprises the steps of obtaining the historical power failure frequency and the corresponding historical power consumption power of each power consumption period, storing the collected information into a database, marking the information as a historical power consumption database, and simultaneously sending the information to a feature extraction module.
3. The intelligent recognition-based unreported outage behavior prediction analysis system according to claim 1, wherein: the step of acquiring the real-time power utilization data of the current equipment by the real-time operation data acquisition unit comprises the following steps:
Acquiring real-time electricity utilization data of the current equipment, taking one week as a monitoring period, and acquiring real-time electricity utilization power of the equipment;
and storing the acquired data into a database, marking the acquired data as a real-time electricity utilization database, and simultaneously transmitting the acquired data to a data screening module.
4. The intelligent recognition-based unreported outage behavior prediction analysis system according to claim 1, wherein: the feature extraction module establishes a regression equation according to the correlation between the historical power failure frequency and the corresponding historical power consumption power, and the process of calculating and obtaining the power failure feature coefficient comprises the following steps:
receiving information of a historical sample data acquisition unit, acquiring historical electricity sample data of each period, and representing the data acquisition performed each time by i, wherein i=1, 2,3, … … and n; n is a positive integer;
Marking the historical power failure frequency and the corresponding historical power consumption as x i and y i respectively;
The data x and y are subjected to mean value and summation, and calculated to obtain />
Taking the historical power failure frequency as a control point, and carrying out regression analysis according to the correlation of the historical power failure frequency of each power utilization period and the corresponding historical power utilization power to establish a regression equation;
The power outage characteristic coefficient TD is calculated and analyzed through a power outage regression equation, wherein the calculation formula is y=bx+a, and the data unit is megawatt, in the formula,
5. The intelligent recognition-based unreported outage behavior prediction analysis system according to claim 1, wherein: the process of the intelligent alarm module for performing the calibration analysis according to the analysis result of the suspected power failure to obtain the calibration analysis result of the real-time power consumption comprises the following steps:
Performing correction analysis on the analysis result of the suspected power failure to obtain a predicted value YC of the power consumption;
comparing the real-time power SD k corresponding to the suspected abnormal signal of the real-time power with the predicted value YC of the power, when the real-time power SD k is larger than the predicted value YC of the power, determining that the real-time power is abnormal, and generating an abnormal signal of the real-time power; when the real-time power SD k is not greater than the power predicted value YC, determining that the real-time power is normal, and generating a normal signal of the real-time power;
And obtaining a real-time electricity utilization calibration analysis result from the abnormal signal of the real-time electricity utilization power and the normal signal of the real-time electricity utilization power.
6. The intelligent recognition-based unreported outage behavior prediction analysis system according to claim 1, wherein: the intelligent alarm module calculates and analyzes the alarm prediction coefficient, and the process of generating different grades of instructions comprises the following steps:
Alarm prediction analysis is carried out according to the real-time electricity utilization calibration analysis result, and the analysis result is calculated according to the formula Calculating an alarm prediction coefficient, wherein/>The average value of the real-time power consumption corresponding to the obtained suspected abnormal signal of the real-time power consumption is represented, P is a proportionality coefficient preset by an alarm prediction coefficient, and 0< P <1, wherein l=1, 2,3, … … and o; o is a positive integer;
Analyzing and processing the calculation result, and if the numerical range of the alarm prediction coefficient BJ is between (0.6,1), generating a first-level alarm instruction by the system; if the numerical range of the alarm prediction coefficient BJ is between (0.3 and 0.6), the system generates a secondary alarm instruction; if the numerical range of the alarm prediction coefficient BJ is between (0, 0.3), the system generates a three-level alarm instruction;
And the system carries out alarm processing of different levels according to the generated different level instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311853452.XA CN117808157B (en) | 2023-12-29 | 2023-12-29 | Intelligent identification-based unreported outage behavior prediction analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311853452.XA CN117808157B (en) | 2023-12-29 | 2023-12-29 | Intelligent identification-based unreported outage behavior prediction analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117808157A CN117808157A (en) | 2024-04-02 |
| CN117808157B true CN117808157B (en) | 2024-06-18 |
Family
ID=90431313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311853452.XA Active CN117808157B (en) | 2023-12-29 | 2023-12-29 | Intelligent identification-based unreported outage behavior prediction analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808157B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132025A (en) * | 2023-10-26 | 2023-11-28 | 国网山东省电力公司泰安供电公司 | Power consumption monitoring and early warning system based on multisource data fusion |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11475349B2 (en) * | 2020-06-12 | 2022-10-18 | Verizon Patent And Licensing Inc. | System and methods for scoring telecommunications network data using regression classification techniques |
| CN112632805B (en) * | 2021-03-15 | 2021-06-01 | 国能大渡河大数据服务有限公司 | Analysis early warning method, system, terminal and medium for crossing vibration area of unit |
| CN116613867B (en) * | 2023-07-20 | 2023-12-26 | 上海木链工业互联网科技有限公司 | Wireless power transmission system for AGV and control method thereof |
| CN117294000A (en) * | 2023-08-23 | 2023-12-26 | 内蒙古电力（集团）有限责任公司电力营销服务与运营管理分公司 | Intelligent power failure early warning system for power grid |
-
2023
- 2023-12-29 CN CN202311853452.XA patent/CN117808157B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132025A (en) * | 2023-10-26 | 2023-11-28 | 国网山东省电力公司泰安供电公司 | Power consumption monitoring and early warning system based on multisource data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117808157A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN109977535B (en) | Line loss abnormality diagnosis method, device, equipment and readable storage medium | |
| CN105184084B (en) | Method and system for predicting fault type of electric power metering automation terminal | |
| CN106780121B (en) | Power consumption abnormity identification method based on power consumption load mode analysis | |
| KR101872342B1 (en) | Method and device for intelligent fault diagnosis using improved rtc(real-time contrasts) method | |
| CN116933197B (en) | Fault discrimination method and system for electricity consumption information acquisition system based on big data | |
| CN101720453A (en) | System and method for predictive maintenance of a battery assembly using temporal signal processing | |
| CN105871634A (en) | Method and application for detecting cluster anomalies and cluster managing system | |
| CN116125361B (en) | Voltage transformer error evaluation method, system, electronic equipment and storage medium | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN117978628B (en) | Communication control method and system based on intelligent park | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN111080484A (en) | Method and device for monitoring abnormal data of power distribution network | |
| KR101960755B1 (en) | Method and apparatus of generating unacquired power data | |
| US20230297095A1 (en) | Monitoring device and method for detecting anomalies | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN117808157B (en) | Intelligent identification-based unreported outage behavior prediction analysis system | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN116448234A (en) | Power transformer running state voiceprint monitoring method and system | |
| KR20220097252A (en) | Method and system for managing equipment of smart plant using machine-learning | |
| CN111382946B (en) | Autonomous evaluation method and system for health state of equipment and industrial internet equipment | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment |
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 |