CN117874684A - Abnormality monitoring method and device for power equipment and storage medium - Google Patents
Abnormality monitoring method and device for power equipment and storage medium Download PDFInfo
- Publication number
- CN117874684A CN117874684A CN202410227202.3A CN202410227202A CN117874684A CN 117874684 A CN117874684 A CN 117874684A CN 202410227202 A CN202410227202 A CN 202410227202A CN 117874684 A CN117874684 A CN 117874684A
- Authority
- CN
- China
- Prior art keywords
- parameter
- power
- power equipment
- normal
- score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 230000005856 abnormality Effects 0.000 title claims abstract description 14
- 239000010687 lubricating oil Substances 0.000 claims abstract description 88
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000002159 abnormal effect Effects 0.000 claims description 67
- 230000008859 change Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 10
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000012806 monitoring device Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 13
- 230000036541 health Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000000356 contaminant Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
Abstract
The invention belongs to the technical field of power equipment state detection, and discloses an abnormality monitoring method, an abnormality monitoring device and a storage medium for power equipment; collecting m groups of equipment characteristic data, wherein the equipment characteristic parameters comprise electrical characteristic parameters and lubricating oil characteristic data; training a fraction prediction model for predicting the fraction of the lubricating oil based on the lubricating oil characteristic data; judging whether to generate a score acquisition instruction according to the electrical characteristic parameters, and if so, calculating the score of the electrical characteristic parameters; inputting the real-time lubricating oil characteristic data into a trained score prediction model, outputting predicted lubricating oil scores, and calculating the total score of the electric power equipment according to the electrical characteristic parameter scores and the lubricating oil scores; judging whether an early warning instruction is generated or not according to the duration time of the total score of the power equipment; the state of the power equipment in the operation process can be monitored in real time, and the approximate fault cause of the power equipment can be found in time.
Description
Technical Field
The present invention relates to the field of power equipment status detection technology, and more particularly, to an anomaly monitoring method, apparatus and storage medium for power equipment.
Background
Electrical power devices play a vital role in modern electrical power systems, for generating, transmitting, distributing and terminal power; stable operation of the power equipment is critical to maintaining reliability and safety of the power system; however, the power equipment may be affected by various factors such as load change, short circuit, environmental factors, equipment aging and malfunction in long-term operation, thereby causing abnormal states or malfunctions;
patent application publication number CN114841617a discloses a method and apparatus for acquiring a health status of a device, including: acquiring evaluation index parameters of equipment, wherein the evaluation index parameters at least comprise file parameters, operation parameters and defect parameters; based on the evaluation index parameters, processing the evaluation index parameters through a preset equipment health evaluation model to obtain evaluation parameters of equipment, wherein the evaluation parameters at least comprise evaluation scores of the equipment; determining a health state of the device based on the evaluation score, and outputting the health state of the device, the health state including at least one of the evaluation score, the device state, and the abnormal state quantity; the health state of the power distribution equipment is determined in a scientific and accurate evaluation mode, so that the method is applicable to various application scenes, the accuracy of equipment health state evaluation is improved, and the stable operation of the equipment is maintained;
However, when the above technology generates the evaluation score of the electrical parameter, the overload capacity of the electrical equipment is not considered, and when the electrical equipment is affected by load fluctuation, external environment change, harmonic wave, distortion and the like to some extent in the operation process, the overload capacity can effectively cope with the fluctuation, so that the situation of misjudgment exists when the health state of the electrical equipment is evaluated according to the evaluation score of the electrical parameter; the detection scoring is carried out on each part of the equipment, so that the parameter acquisition amount and the processing amount are large, the real-time state detection cannot be carried out on the power equipment, the detection can be carried out regularly, and the instantaneity is limited;
in view of the above, the present invention proposes an anomaly monitoring method, an anomaly monitoring device and a storage medium for an electrical device to solve the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the following technical scheme for achieving the purposes: an anomaly monitoring method for an electrical device, comprising:
collecting m groups of equipment characteristic parameters, wherein the equipment characteristic parameters comprise electrical characteristic parameters and lubricating oil characteristic data;
training a fraction prediction model for predicting the fraction of the lubricating oil based on the lubricating oil characteristic data;
Judging whether to generate a score acquisition instruction according to the electrical characteristic parameters, and if so, calculating the score of the electrical characteristic parameters;
inputting the real-time lubricating oil characteristic data into a trained score prediction model, outputting predicted lubricating oil scores, and calculating the total score of the electric power equipment according to the electrical characteristic parameter scores and the lubricating oil scores;
and setting a time threshold, judging whether to generate an early warning instruction according to the duration of the total score of the power equipment, and generating a corresponding early warning grade according to the total score of the power equipment if the early warning instruction is generated.
Further, the electrical characteristic parameters include a current parameter, a voltage parameter, a temperature parameter, and a vibration parameter; lubricating oil profile data includes viscosity, pH, and particle number.
Further, the training process of the score prediction model includes:
sequentially presetting different scores for lubricating oils with different characteristic data of the lubricating oils, wherein the score setting range is smaller than or equal to R score;
the method comprises the steps of taking lubricating oil characteristic data as input of a fraction prediction model, taking predicted lubricating oil fraction of each group of lubricating oil characteristic data as output of the fraction prediction model, taking actual lubricating oil fraction corresponding to the group of lubricating oil characteristic data as a prediction target, and taking the sum of prediction errors of all the lubricating oil characteristic data as a training target; training the fractional predictive model until the sum of the predictive errors reaches convergence, and stopping training; the score prediction model is either a deep neural network model or a deep belief network model.
Further, the method for judging whether to generate the score acquisition instruction comprises the following steps:
if the electrical characteristic parameters are all in the normal value range, a score acquisition instruction is not generated, the electrical characteristic parameters in the normal value range are marked as normal parameters, and the score corresponding to the normal parameters is set as R score;
if any parameter in the electrical characteristic parameters is out of the normal value range and is in the threshold value range, generating a score acquisition instruction, marking the parameter as a semi-normal parameter, calculating a score corresponding to the semi-normal parameter, wherein the normal value range is the normal value range corresponding to the parameter, and the threshold value range is the threshold value range corresponding to the parameter;
if any one of the electrical characteristic parameters is out of the threshold range, a score acquisition instruction is generated, the parameter is marked as an abnormal parameter, and a score corresponding to the abnormal parameter is calculated.
Further, the calculation method of the score corresponding to the semi-normal parameter comprises the following steps:
if the semi-normal parameter is smaller than the minimum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
f in the formula J Score corresponding to semi-normal parameter, J Zm Is the minimum value of the normal value range corresponding to the semi-normal parameter, J Ym The threshold range minimum value corresponding to the semi-normal parameter is given, and J is the semi-normal parameter;
if the semi-normal parameter is larger than the maximum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
in J Zs Maximum value of normal value range corresponding to semi-normal parameter, J Ys The maximum value of the threshold range corresponding to the semi-normal parameter;
the calculation method of the score corresponding to the abnormal parameter comprises the following steps:
if the abnormal parameter is smaller than the minimum value of the threshold range corresponding to the abnormal parameter, subtracting the minimum value of the threshold range corresponding to the abnormal parameter from the abnormal parameter to obtain a difference value serving as an abnormal parameter score;
if the abnormal parameter is larger than the maximum value of the threshold range corresponding to the abnormal parameter, subtracting the abnormal parameter from the maximum value of the threshold range corresponding to the abnormal parameter to obtain a difference value which is used as the abnormal parameter fraction.
The calculation method of the electrical characteristic parameter fraction is as follows:
S D ＝λ 1 F I +λ 2 F U +λ 3 F T +λ 4 F D ；
wherein S is D For the electrical characteristic parameter fraction, F I As the current parameter fraction, F U As the voltage parameter fraction, F T F is the temperature parameter fraction D Lambda is the vibration parameter fraction 1 、λ 2 、λ 3 、λ 4 Is a preset proportionality coefficient lambda 1 +λ 2 +λ 3 +λ 4 ＝1；
The total score of the power equipment is calculated as follows:
S＝ω 1 ×S D +ω 2 ×S R ；
wherein S is the total score of the power equipment, S R Is the lubricating oil fraction omega 1 、ω 2 Is of preset weight and omega 1 +ω 2 ＝1。
Further, the method for judging whether to generate the early warning instruction comprises the following steps:
drawing a time-total score graph;
if the total score of the power equipment in the time-total score graph is R time sharing, the corresponding duration is smaller than a time threshold, or the total score of the power equipment is lower than R time sharing and higher than 0 time sharing, and the corresponding duration is smaller than the time threshold, no early warning instruction is generated;
if the total score of the power equipment in the time-total score graph is lower than R score and the corresponding duration is greater than a time threshold or the total score of the power equipment is less than 0 time, generating an early warning instruction;
when an early warning instruction is generated, acquiring a corresponding early warning grade according to the total score of the power equipment; and outputting the early warning grade, the lubricating oil fraction and the electrical characteristic parameter fraction to a central control screen of the electric power system.
Further, when an early warning instruction is generated, the corresponding current parameter fraction is obtained, the failure cause of the power equipment is judged, and the electronic switch is regulated according to the failure cause of the power equipment;
the method for judging the failure cause of the power equipment comprises the following steps:
subtracting the current parameter fraction of the last time point from the current parameter fraction obtained at present to obtain the change amount of the current parameter fraction in unit time;
If the change amount of the current parameter in the unit time is larger than the change amount threshold value, judging that the power equipment is in short circuit fault at the moment;
if the change amount of the current parameter fraction in unit time is smaller than or equal to the change amount threshold value, judging that the power equipment is in overload fault at the moment;
the power device that is in a short circuit fault or overload fault is marked as a faulty power device.
Further, the adjusting method of the electronic switch comprises the following steps:
if the power equipment is in a short-circuit fault, the electronic switch connected with the load by the fault power equipment is disconnected, and the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is connected; adding the power parameters required by the load connected with the fault power equipment to obtain required power, and obtaining the available power of the normal power equipment, wherein the available power is the difference value of the total power of the power equipment minus the power required by the load connected with the power equipment;
if the available power of the power equipment is larger than or equal to the required power in the normal power equipment, marking the power equipment with the available power larger than or equal to the required power as available power equipment, and switching on an electronic switch on a circuit for connecting the available power equipment and the fault power equipment; if the available power of the normal power equipment is smaller than the required power, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the required power, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment; if the power accumulated value obtained by adding all the power equipment is smaller than the required power, the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is not regulated;
If the power equipment is in overload fault, switching on an electronic switch on a circuit for connecting the normal power equipment and the fault power equipment; multiplying the current parameter and the voltage parameter of the collected fault power equipment to obtain equipment power parameter, and subtracting the equipment power parameter from the required power to obtain a power parameter difference value; acquiring available power of normal power equipment; if the available power of the power equipment is larger than the power parameter difference value in the normal power equipment, marking the power equipment with the available power larger than the power parameter difference value as power-on power equipment, and switching on an electronic switch on a circuit for connecting the power-on power equipment and the fault power equipment; and if the available power of the normal power equipment is smaller than the power parameter difference value, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the power parameter difference value, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the anomaly monitoring method for a power device when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed implements the anomaly monitoring method for an electrical device.
The invention relates to an abnormality monitoring method and device for power equipment and a storage medium, which have the technical effects and advantages that:
1. calculating the lubricating oil fraction and the electrical characteristic parameter fraction by detecting the electrical characteristic parameter and the lubricating oil characteristic data in real time, and obtaining the total fraction of the electric power equipment; the state of the power equipment in the running process can be monitored in real time, so that a worker can find out the approximate fault cause of the power equipment in time; and the overload capacity of the power equipment is taken into consideration when the electrical characteristic parameter score is calculated, so that the misjudgment probability of the state of the power equipment is reduced.
2. And judging the fault reason of the power equipment through the current parameter fraction, and regulating an electronic switch on a circuit connected with the normal power equipment by the fault power equipment according to the fault reason of the power equipment, so as to ensure that the power provided by the power equipment meets the power required by the load and ensure that the load connected with the fault power equipment is in a normal running state.
Drawings
Fig. 1 is a schematic diagram of an anomaly monitoring system for an electrical device according to embodiment 1 of the present invention;
FIG. 2 is a graph showing the time-total score curve of example 1 of the present invention;
FIG. 3 is a schematic diagram of an anomaly monitoring system for an electrical device according to embodiment 2 of the present invention;
fig. 4 is a schematic diagram of a power system according to embodiment 2 of the present invention;
FIG. 5 is a flow chart of an anomaly monitoring method for electrical equipment according to embodiment 3 of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to embodiment 5 of the present invention.
Reference numerals: 1. an electric power device; 2. an electronic switch; 3. and (3) loading.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described 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.
Example 1:
referring to fig. 1, the anomaly monitoring system for electric power equipment according to the present embodiment includes a parameter acquisition module, a model training module, a score calculation module, a total score generation module, and a state analysis module, where each module is connected by a wired and/or wireless manner, so as to implement parameter transmission between the modules;
The parameter acquisition module acquires m groups of equipment characteristic parameters, wherein m is an integer greater than 1; the equipment characteristic parameters comprise electrical characteristic parameters and lubricating oil characteristic data;
the electrical characteristic parameters comprise current, voltage, temperature and vibration, wherein the current is the current in the power equipment, the current is obtained by a current sensor arranged at the power supply input end of the power equipment, and overload, overheat or damage of the power equipment can be caused by the fact that the current is too high or too low; the voltage is the voltage in the power equipment, and is obtained by a voltage sensor arranged at the power supply input end of the power equipment, and the power equipment is in fault, power loss or arc discharge caused by abnormal voltage; the temperature is the temperature of the power equipment, and is obtained by a temperature sensor arranged in the power equipment, and the excessive temperature can cause ageing of insulating materials, overheat of the equipment and even fire disaster; the vibration is the vibration of the electric equipment, and is obtained by a vibration sensor arranged on a base of the electric equipment, and the abnormal vibration indicates that bearing abrasion, unbalance or mechanical failure can occur;
the lubricating oil characteristic data comprise viscosity, PH value and particle number; the viscosity is the viscosity of the lubricating oil in the electric equipment, and is obtained by a viscosity sensor arranged at the outlet end of the oil pipe, so that the lubricating effect of the lubricating oil is poor due to abnormal viscosity, friction and abrasion are increased, and the energy efficiency of the electric equipment is reduced; the PH value is the PH value of lubricating oil in the electric equipment, and is obtained by a PH sensor arranged in an oil tank, and the lower PH value can damage metal equipment of the electric equipment, so that sealing elements are expanded or damaged, and lubricating oil leakage and electric equipment pollution are caused; particle count the number of particle contaminants in the lubricating oil is obtained by a particle counter mounted at the outlet end of the oil pipe; particulate contaminants can increase friction and wear inside the power equipment, which can cause sealing problems or cause failure of the power equipment when they enter the power equipment seals or moving parts;
The model training module is used for training a fraction prediction model for predicting the fraction of the lubricating oil based on the characteristic data of the lubricating oil; the specific training process of the score prediction model comprises the following steps:
under an experimental environment, sequentially presetting different scores for lubricating oil with different characteristic data of the lubricating oil, wherein the score setting range is smaller than or equal to R score; r is set by a worker according to the detection precision, and R is preferably 100 in the embodiment;
the method comprises the steps of taking lubricating oil characteristic data as input of a fraction prediction model, taking predicted lubricating oil fraction of each group of lubricating oil characteristic data as output of the fraction prediction model, taking actual lubricating oil fraction corresponding to the group of lubricating oil characteristic data as a prediction target, and taking the sum of prediction errors of all the lubricating oil characteristic data as a training target; wherein, the calculation formula of the prediction error is zk= (alpha k-mu k) 2 Where zk is a prediction error, k is a number of the lubricating oil feature data, αk is a predicted lubricating oil fraction corresponding to the kth set of lubricating oil feature data, and μk is an actual lubricating oil fraction corresponding to the kth set of lubricating oil feature data; training the fractional predictive model until the sum of the predictive errors reaches convergence, and stopping training;
The score prediction model is any one of a deep neural network model and a deep belief network model;
the score calculating module is used for judging whether to generate a score acquisition instruction according to the electrical characteristic parameters, and calculating the electrical characteristic parameter score if the score acquisition instruction is generated;
the score corresponding to the electrical characteristic parameters is that the current parameter, the voltage parameter, the temperature parameter and the vibration parameter of the power equipment are calculated in a score way, whether the power equipment is abnormal in state or not is reflected through the score, the lower the score is, the more the equipment characteristic data deviate from the normal value range, the higher the probability that the power equipment is in an abnormal state is, and the power equipment fault information can be collected by workers conveniently;
acquiring a normal value range and a threshold value range of each parameter in the electrical characteristic parameters according to the technical specification and a user manual of the electrical equipment, wherein the maximum value of the threshold value range is larger than the maximum value of the normal value range, and the minimum value of the threshold value range is smaller than the minimum value of the normal value range so as to leave a certain margin, namely overload capacity, and ensure that the electrical equipment runs in a normal operation range;
the reason for setting the overload capacity is that in the working process of the power equipment, the electrical characteristic parameters are affected to some extent, so that fluctuation occurs to a certain extent, and the overload capacity can effectively cope with the fluctuation; for example, transient fluctuations in the device characteristic parameters caused by load fluctuations can be tolerated; helping to cope with changes in device characteristic parameters caused by environmental factors; prolonging the service life of the power equipment, adapting to the aging condition of the equipment and the like;
The method for judging whether to generate the score acquisition instruction comprises the following steps:
if the electrical characteristic parameters are all in the normal value range, a score acquisition instruction is not generated, and the electrical characteristic parameters in the normal value range are marked as normal parameters; the power equipment is in a normal state at the moment, score calculation is not needed to be carried out on parameters in the electrical characteristic parameters, and the score corresponding to the normal parameters is set to be R score; the normal value range is a normal value range corresponding to the parameter, the threshold value range is a threshold value range corresponding to the parameter, and when the parameter is a current parameter, that is, the normal value range is a normal value range corresponding to the current parameter, the threshold value range is a threshold value range corresponding to the current parameter;
if the parameters in the electrical characteristic parameters are out of the normal value range and are within the threshold value range, a score acquisition instruction is generated, the parameters are marked as semi-normal parameters, and the score corresponding to the semi-normal parameters is calculated; indicating that the power equipment is in a semi-normal state at the moment, namely that the semi-normal parameters in the power equipment are in an overload capacity region, and performing score calculation on the semi-normal parameters;
if the parameters in the electrical characteristic parameters are out of the threshold range, generating a score acquisition instruction, marking the parameters as abnormal parameters, and calculating scores corresponding to the abnormal parameters; indicating that the power equipment is in an abnormal state at the moment;
The score acquisition instruction is an instruction for calculating the score of the electrical characteristic parameter, the instruction is a basic unit for executing the operation of the computer system, and when the score acquisition instruction is generated, the corresponding electrical characteristic parameter is calculated;
the calculation method of the score corresponding to the semi-normal parameter is as follows:
if the semi-normal parameter is smaller than the minimum value of the normal value corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
f in the formula J Score corresponding to semi-normal parameter, J Zm Is the minimum value of the normal value corresponding to the semi-normal parameter, J Ym The threshold value minimum value corresponding to the semi-normal parameter is given, and J is the semi-normal parameter;
if the semi-normal parameter is larger than the maximum value of the normal value corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
in J Zs Maximum value of normal value corresponding to semi-normal parameter, J Ys The threshold value maximum value corresponding to the semi-normal parameter;
the calculation method of the score corresponding to the abnormal parameter is as follows:
if the abnormal parameter is smaller than the threshold minimum value corresponding to the abnormal parameter, taking the difference value of the abnormal parameter minus the threshold minimum value corresponding to the abnormal parameter as an abnormal parameter fraction;
if the abnormal parameter is larger than the threshold maximum value corresponding to the abnormal parameter, subtracting the difference value of the abnormal parameter from the threshold maximum value corresponding to the abnormal parameter to obtain an abnormal parameter fraction;
Calculating an electrical characteristic parameter fraction according to the normal parameter fraction, the semi-normal parameter fraction and the abnormal parameter fraction;
the calculation method of the electrical characteristic parameter fraction is as follows:
S D ＝λ 1 F I +λ 2 F U +λ 3 F T +λ 4 F D ；
wherein S is D For the electrical characteristic parameter fraction, F I As the current parameter fraction, F U As the voltage parameter fraction, F T F is the temperature parameter fraction D Lambda is the vibration parameter fraction 1 、λ 2 、λ 3 、λ 4 Is a preset proportionality coefficient lambda 1 +λ 2 +λ 3 +λ 4 ＝1；
Wherein the preset proportionality coefficient is obtained by the person skilled in the art, a plurality of groups of comprehensive parameters are collected, corresponding proportionality coefficients are set for each group of comprehensive parameters, the preset proportionality coefficient and the collected comprehensive parameters are substituted into a formula, any four formulas form a quaternary once equation set, the calculated proportionality coefficients are screened and averaged to obtain lambda 1 、λ 2 、λ 3 、λ 4 Is a value of (2);
the calculation method of the current parameter fraction, the voltage parameter fraction, the temperature parameter fraction and the vibration parameter fraction is a calculation method of the normal parameter fraction, the semi-normal parameter fraction or the abnormal parameter fraction, and according to the values of the current, the voltage, the temperature and the vibration, whether the current, the voltage, the temperature and the vibration are marked as the normal parameter, the semi-normal parameter or the abnormal parameter is judged, and corresponding fraction calculation is performed; for example, if the current is marked as a semi-normal parameter, calculating a current parameter score corresponding to the current according to a calculation method of a score corresponding to the semi-normal parameter;
The total score generation module inputs the real-time lubricating oil characteristic data into a trained score prediction model, outputs predicted lubricating oil scores, and calculates total scores of the electric power equipment according to the electrical characteristic parameter scores and the lubricating oil scores;
the total score of the power equipment is calculated as follows:
S＝ω 1 ×S D +ω 2 ×S R ；
wherein S is the total score of the power equipment, S R Is the lubricating oil fraction omega 1 、ω 2 Is of preset weight and omega 1 +ω 2 ＝1；
Wherein the preset weight is acquired by a person skilled in the art, corresponding weights are set for each group of comprehensive parameters, the preset weight and the acquired comprehensive parameters are substituted into a formula, any two formulas form a binary one-time equation set, the calculated weights are filtered and averaged to obtain omega 1 、ω 2 Is a value of (2);
the state analysis module is used for setting a time threshold, judging whether an early warning instruction is generated according to the duration time of the total score of the power equipment, and generating a corresponding early warning grade according to the total score of the power equipment if the early warning instruction is generated;
when the total score of the power equipment is lower than R, starting acquisition by a time sensor arranged in the power equipment, and when the total score of the power equipment is equal to R, stopping acquisition by the time sensor, wherein the time elapsed from the start of acquisition to the stop of acquisition is taken as duration time, and the unit of the duration time is seconds;
Setting a time threshold, wherein the time threshold is determined according to the type and the purpose of the power equipment and is acquired through the technical specification and the user manual of the power equipment;
the method for judging whether to generate the early warning instruction comprises the following steps:
drawing a time-total score graph according to the time acquired by the time sensor, and referring to fig. 2;
if the total score of the power equipment in the time-total score graph is R time sharing, the corresponding duration is smaller than a time threshold, or the total score of the power equipment is lower than R time sharing and higher than 0 time sharing, and the corresponding duration is smaller than the time threshold, no early warning instruction is generated, and the power equipment can automatically cope with short equipment characteristic parameter fluctuation when the semi-normal parameter exists for only a short period of time;
if the total score of the power equipment in the time-total score graph is lower than R score and the corresponding duration time is greater than a time threshold or the total score of the power equipment is less than 0 time sharing, generating an early warning instruction, and indicating that the power equipment is in an abnormal state at the moment;
when an early warning instruction is generated, acquiring corresponding early warning grades according to the total score of the power equipment, wherein the early warning grades are shown in a table 1-early warning grade table; the early warning grade, the lubricating oil fraction and the electrical characteristic parameter fraction are all output to a central control screen of the power system, so that a worker can conveniently acquire the fault degree of the power equipment and know the approximate reason that the power equipment is in an abnormal state;
It should be noted that, the reason for setting the time threshold is that the overload capacity can only allow the device characteristic parameter of the power device to be out of the normal value range for a short period of time, but cannot be in the normal value range to the threshold range for a long time; if the characteristic parameters of the equipment are in the range from the normal value range to the threshold value range for a long time, the equipment is overheated, the service life is reduced or the fault risk is increased; that is, when the duration that the total score of the power device is less than R score exceeds the time threshold, the power device will transition from the semi-normal state to the abnormal state;
TABLE 1 early warning level Meter
According to the embodiment, through detecting the electrical characteristic parameters and the lubricating oil characteristic data in real time, calculating the lubricating oil fraction and the electrical characteristic parameter fraction, and obtaining the total fraction of the electric power equipment; the state of the power equipment in the running process can be monitored in real time, so that a worker can find out the approximate fault cause of the power equipment in time; and the overload capacity of the power equipment is taken into consideration when the electrical characteristic parameter score is calculated, so that the misjudgment probability of the state of the power equipment is reduced.
Example 2:
referring to fig. 3, the present embodiment is a further improved design based on embodiment 1, in the power system, a plurality of power devices 1 are connected in parallel and are connected to a plurality of loads 3, and an electronic switch 2 is disposed in a circuit connected to each power device and other power devices, for switching on/off states of the power devices and the loads, as shown in fig. 4; when an electrical characteristic parameter of an electrical device is abnormal, a process is needed from the generation of an early warning instruction to the previous maintenance of a worker, and at the moment, the electrical device may be damaged if the electrical device continues to operate, and if the electrical device is stopped, a load connected with the electrical device is stopped, so that the embodiment provides an abnormality monitoring system for the electrical device, and the abnormality monitoring system further comprises an adjusting module, which can ensure that the electrical device is not damaged and the load connected with the electrical device is in a normal operating state by adjusting one or more electronic switches on a circuit connected with the electrical device in the electrical system;
The adjusting module is used for acquiring corresponding current parameter fractions when an early warning instruction is generated in the embodiment 1, judging the failure cause of the power equipment, and adjusting the electronic switch according to the failure cause of the power equipment to ensure that a load connected with the power equipment is in a normal running state;
the method for judging the failure cause of the power equipment comprises the following steps:
subtracting the current parameter fraction of the last time point from the current parameter fraction obtained at present to obtain the change amount of the current parameter fraction in unit time;
if the change amount of the current parameter in the unit time is larger than the change amount threshold value, judging that the power equipment is in short circuit fault at the moment;
if the change amount of the current parameter fraction in unit time is smaller than or equal to the change amount threshold value, judging that the power equipment is in overload fault at the moment;
marking the power equipment in the short circuit fault or overload fault as fault power equipment;
the adjusting method of the electronic switch comprises the following steps:
if the power equipment is in a short-circuit fault, the electronic switch connected with the load by the fault power equipment is disconnected, and the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is connected; adding the power parameters required by the loads connected with the fault power equipment to obtain required power, and obtaining available power of normal power equipment, wherein the available power is the difference value of the total power of the power equipment minus the power required by the loads connected with the power equipment;
If the available power of the power equipment is larger than or equal to the required power in the normal power equipment, marking the power equipment with the available power larger than or equal to the required power as available power equipment, and switching on an electronic switch on a circuit for connecting the available power equipment and the fault power equipment; if the available power of the normal power equipment is smaller than the required power, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the required power, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment to ensure that the power provided by the power equipment meets the power required by the load and ensure that the load connected with the fault power equipment is in a normal running state; if the power accumulated value obtained by adding all the power equipment is smaller than the required power, the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is not regulated;
if the power equipment is in overload fault, switching on an electronic switch on a circuit for connecting the normal power equipment and the fault power equipment; at the moment, multiplying the current parameter and the voltage parameter of the collected fault power equipment to obtain equipment power parameter, and subtracting the equipment power parameter from the required power to obtain a power parameter difference value; acquiring available power of normal power equipment; if the available power of the power equipment is larger than the power parameter difference value in the normal power equipment, marking the power equipment with the available power larger than the power parameter difference value as power-on power equipment, and switching on an electronic switch on a circuit for connecting the power-on power equipment and the fault power equipment; if the available power of the normal power equipment is smaller than the power parameter difference value, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the power parameter difference value, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment; ensuring that the total power provided by the power equipment meets the power required by the load, and eliminating overload faults of the power equipment;
It should be noted that, the power parameter required by the load is obtained according to the specification of the load; the change amount threshold is a change amount of a worker in the experimental environment in which the worker calculates the change amount of the current parameter fraction in unit time when the short circuit occurs in the power equipment for a plurality of times, and the average value of the change amount of the current parameter fraction in unit time is used as the change amount threshold;
according to the method, the fault cause of the power equipment is judged through the current parameter fraction, the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is regulated according to the fault cause of the power equipment, the power provided by the power equipment is ensured to meet the power required by the load, damage to the power equipment is avoided, meanwhile, when the power equipment is judged to be overloaded, the power equipment is matched with the normal power equipment before overload tripping, the load connected with the fault power equipment is avoided from being powered off, and the normal running state is ensured.
Example 3:
referring to fig. 5, the details of embodiments 1 and 2 are not described in detail in this embodiment, and an anomaly monitoring method for an electrical device is provided, which includes:
collecting m groups of equipment characteristic parameters, wherein the equipment characteristic parameters comprise electrical characteristic parameters and lubricating oil characteristic data;
Training a fraction prediction model for predicting the fraction of the lubricating oil based on the lubricating oil characteristic data;
judging whether to generate a score acquisition instruction according to the electrical characteristic parameters, and if so, calculating the score of the electrical characteristic parameters;
inputting the real-time lubricating oil characteristic data into a trained score prediction model, outputting predicted lubricating oil scores, and calculating the total score of the electric power equipment according to the electrical characteristic parameter scores and the lubricating oil scores;
and setting a time threshold, judging whether to generate an early warning instruction according to the duration of the total score of the power equipment, and generating a corresponding early warning grade according to the total score of the power equipment if the early warning instruction is generated.
Further, the electrical characteristic parameters include a current parameter, a voltage parameter, a temperature parameter, and a vibration parameter; lubricating oil profile data includes viscosity, pH, and particle number.
Further, the training process of the score prediction model includes:
sequentially presetting different scores for lubricating oils with different characteristic data of the lubricating oils, wherein the score setting range is smaller than or equal to R score;
the method comprises the steps of taking lubricating oil characteristic data as input of a fraction prediction model, taking predicted lubricating oil fraction of each group of lubricating oil characteristic data as output of the fraction prediction model, taking actual lubricating oil fraction corresponding to the group of lubricating oil characteristic data as a prediction target, and taking the sum of prediction errors of all the lubricating oil characteristic data as a training target; training the fractional predictive model until the sum of the predictive errors reaches convergence, and stopping training; the score prediction model is either a deep neural network model or a deep belief network model.
Further, the method for judging whether to generate the score acquisition instruction comprises the following steps:
if the electrical characteristic parameters are all in the normal value range, a score acquisition instruction is not generated, the electrical characteristic parameters in the normal value range are marked as normal parameters, and the score corresponding to the normal parameters is set as R score;
if any parameter in the electrical characteristic parameters is out of the normal value range and is in the threshold value range, generating a score acquisition instruction, marking the parameter as a semi-normal parameter, calculating a score corresponding to the semi-normal parameter, wherein the normal value range is the normal value range corresponding to the parameter, and the threshold value range is the threshold value range corresponding to the parameter;
if any one of the electrical characteristic parameters is out of the threshold range, a score acquisition instruction is generated, the parameter is marked as an abnormal parameter, and a score corresponding to the abnormal parameter is calculated.
Further, the calculating method of the half normal parameter corresponding score comprises the following steps:
if the semi-normal parameter is smaller than the minimum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
f in the formula J Score corresponding to semi-normal parameter, J Zm Is the minimum value of the normal value range corresponding to the semi-normal parameter, J Ym The threshold range minimum value corresponding to the semi-normal parameter is given, and J is the semi-normal parameter;
if the semi-normal parameter is larger than the maximum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
in J Zs Maximum value of normal value range corresponding to semi-normal parameter, J Ys The maximum value of the threshold range corresponding to the semi-normal parameter;
the calculation method of the abnormal parameter corresponding score comprises the following steps:
if the abnormal parameter is smaller than the minimum value of the threshold range corresponding to the abnormal parameter, subtracting the minimum value of the threshold range corresponding to the abnormal parameter from the abnormal parameter to obtain a difference value serving as an abnormal parameter score;
if the abnormal parameter is larger than the maximum value of the threshold range corresponding to the abnormal parameter, subtracting the abnormal parameter from the maximum value of the threshold range corresponding to the abnormal parameter to obtain a difference value which is used as the abnormal parameter fraction.
The calculation method of the electrical characteristic parameter fraction is as follows:
S D ＝λ 1 F I +λ 2 F U +λ 3 F T +λ 4 F D ；
wherein S is D For the electrical characteristic parameter fraction, F I As the current parameter fraction, F U As a fraction of the voltage parameter，F T F is the temperature parameter fraction D Lambda is the vibration parameter fraction 1 、λ 2 、λ 3 、λ 4 Is a preset proportionality coefficient lambda 1 +λ 2 +λ 3 +λ 4 ＝1；
The total score of the power equipment is calculated as follows:
S＝ω 1 ×S D +ω 2 ×S R ；
wherein S is the total score of the power equipment, S R Is the lubricating oil fraction omega 1 、ω 2 Is of preset weight and omega 1 +ω 2 ＝1。
Further, the method for judging whether to generate the early warning instruction comprises the following steps:
drawing a time-total score graph;
if the total score of the power equipment in the time-total score graph is R time sharing, the corresponding duration is smaller than a time threshold, or the total score of the power equipment is lower than R time sharing and higher than 0 time sharing, and the corresponding duration is smaller than the time threshold, no early warning instruction is generated;
if the total score of the power equipment in the time-total score graph is lower than R score and the corresponding duration is greater than a time threshold or the total score of the power equipment is less than 0 time, generating an early warning instruction;
when an early warning instruction is generated, acquiring a corresponding early warning grade according to the total score of the power equipment; and outputting the early warning grade, the lubricating oil fraction and the electrical characteristic parameter fraction to a central control screen of the electric power system.
Further, when an early warning instruction is generated, the corresponding current parameter fraction is obtained, the failure cause of the power equipment is judged, and the electronic switch is regulated according to the failure cause of the power equipment;
the method for judging the failure cause of the power equipment comprises the following steps:
subtracting the current parameter fraction of the last time point from the current parameter fraction obtained at present to obtain the change amount of the current parameter fraction in unit time;
If the change amount of the current parameter in the unit time is larger than the change amount threshold value, judging that the power equipment is in short circuit fault at the moment;
if the change amount of the current parameter fraction in unit time is smaller than or equal to the change amount threshold value, judging that the power equipment is in overload fault at the moment;
the power device that is in a short circuit fault or overload fault is marked as a faulty power device.
Further, the adjusting method of the electronic switch comprises the following steps:
if the power equipment is in a short-circuit fault, the electronic switch connected with the load by the fault power equipment is disconnected, and the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is connected; adding the power parameters required by the load connected with the fault power equipment to obtain required power, and obtaining the available power of the normal power equipment, wherein the available power is the difference value of the total power of the power equipment minus the power required by the load connected with the power equipment;
if the available power of the power equipment is larger than or equal to the required power in the normal power equipment, marking the power equipment with the available power larger than or equal to the required power as available power equipment, and switching on an electronic switch on a circuit for connecting the available power equipment and the fault power equipment; if the available power of the normal power equipment is smaller than the required power, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the required power, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment; if the power accumulated value obtained by adding all the power equipment is smaller than the required power, the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is not regulated;
If the power equipment is in overload fault, switching on an electronic switch on a circuit for connecting the normal power equipment and the fault power equipment; multiplying the current parameter and the voltage parameter of the collected fault power equipment to obtain equipment power parameter, and subtracting the equipment power parameter from the required power to obtain a power parameter difference value; acquiring available power of normal power equipment; if the available power of the power equipment is larger than the power parameter difference value in the normal power equipment, marking the power equipment with the available power larger than the power parameter difference value as power-on power equipment, and switching on an electronic switch on a circuit for connecting the power-on power equipment and the fault power equipment; and if the available power of the normal power equipment is smaller than the power parameter difference value, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the power parameter difference value, switching on the electronic switches on the circuits connected with the corresponding normal power equipment and the fault power equipment.
Example 4:
referring to fig. 6, the disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements an anomaly monitoring method for a power device provided by the above methods when executing the computer program.
Since the electronic device described in this embodiment is an electronic device used to implement an abnormality monitoring method for electrical equipment in this embodiment, based on the abnormality monitoring method for electrical equipment described in this embodiment, those skilled in the art will be able to understand the specific implementation of the electronic device in this embodiment and various modifications thereof, so how to implement the method in this embodiment of the present application in this electronic device will not be described in detail herein. Any electronic device used by those skilled in the art to implement an abnormality monitoring method for an electrical device according to the embodiments of the present application falls within the scope of protection intended by the present application.
Example 5:
the embodiment discloses a computer readable storage medium, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes an abnormality monitoring method for power equipment according to any one of the methods provided by the processor when executing the computer program.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. An anomaly monitoring method for an electrical device, comprising:
collecting m groups of equipment characteristic parameters, wherein the equipment characteristic parameters comprise electrical characteristic parameters and lubricating oil characteristic data;
training a fraction prediction model for predicting the fraction of the lubricating oil based on the lubricating oil characteristic data;
judging whether to generate a score acquisition instruction according to the electrical characteristic parameters, and if so, calculating the score of the electrical characteristic parameters;
inputting the real-time lubricating oil characteristic data into a trained score prediction model, outputting predicted lubricating oil scores, and calculating the total score of the electric power equipment according to the electrical characteristic parameter scores and the lubricating oil scores;
and setting a time threshold, judging whether to generate an early warning instruction according to the duration of the total score of the power equipment, and generating a corresponding early warning grade according to the total score of the power equipment if the early warning instruction is generated.
2. The anomaly monitoring method for an electrical device of claim 1, wherein the electrical characteristic parameters include a current parameter, a voltage parameter, a temperature parameter, and a vibration parameter; lubricating oil profile data includes viscosity, pH, and particle number.
3. The anomaly monitoring method for a power plant of claim 2, wherein the training process of the score prediction model comprises:
sequentially presetting different scores for lubricating oils with different characteristic data of the lubricating oils, wherein the score setting range is smaller than or equal to R score;
the method comprises the steps of taking lubricating oil characteristic data as input of a fraction prediction model, taking predicted lubricating oil fraction of each group of lubricating oil characteristic data as output of the fraction prediction model, taking actual lubricating oil fraction corresponding to the group of lubricating oil characteristic data as a prediction target, and taking the sum of prediction errors of all the lubricating oil characteristic data as a training target; training the fractional predictive model until the sum of the predictive errors reaches convergence, and stopping training; the score prediction model is either a deep neural network model or a deep belief network model.
4. A method for anomaly monitoring of electrical equipment according to claim 3, wherein the method of determining whether to generate a score acquisition instruction comprises:
if the electrical characteristic parameters are all in the normal value range, a score acquisition instruction is not generated, the electrical characteristic parameters in the normal value range are marked as normal parameters, and the score corresponding to the normal parameters is set as R score;
If any parameter in the electrical characteristic parameters is out of the normal value range and is in the threshold value range, generating a score acquisition instruction, marking the parameter as a semi-normal parameter, calculating a score corresponding to the semi-normal parameter, wherein the normal value range is the normal value range corresponding to the parameter, and the threshold value range is the threshold value range corresponding to the parameter;
if any one of the electrical characteristic parameters is out of the threshold range, a score acquisition instruction is generated, the parameter is marked as an abnormal parameter, and a score corresponding to the abnormal parameter is calculated.
5. The anomaly monitoring method for an electrical device of claim 4, wherein the calculation method of the score corresponding to the semi-normal parameter comprises:
if the semi-normal parameter is smaller than the minimum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
wherein FJ is a fraction corresponding to a semi-normal parameter, J Zm Is the minimum value of the normal value range corresponding to the semi-normal parameter, J Ym The threshold range minimum value corresponding to the semi-normal parameter is given, and J is the semi-normal parameter;
if the semi-normal parameter is larger than the maximum value of the normal value range corresponding to the semi-normal parameter, the method for calculating the corresponding score of the semi-normal parameter is as follows;
In J Zs Maximum value of normal value range corresponding to semi-normal parameter, J Ys The maximum value of the threshold range corresponding to the semi-normal parameter;
the calculation method of the score corresponding to the abnormal parameter comprises the following steps:
if the abnormal parameter is smaller than the minimum value of the threshold range corresponding to the abnormal parameter, subtracting the minimum value of the threshold range corresponding to the abnormal parameter from the abnormal parameter to obtain a difference value serving as an abnormal parameter score;
if the abnormal parameter is larger than the maximum value of the threshold range corresponding to the abnormal parameter, subtracting the abnormal parameter from the maximum value of the threshold range corresponding to the abnormal parameter to obtain a difference value which is used as an abnormal parameter fraction;
the calculation method of the electrical characteristic parameter fraction comprises the following steps:
SD＝λ1FI+λ2FU+λ3FT+λ4FD；
wherein SD is the electrical characteristic parameter fraction, F I As the current parameter fraction, F U As the voltage parameter fraction, F T F is the temperature parameter fraction D For the vibration parameter fraction, λ1, λ2, λ3, λ4 are the preset ratioCoefficients and λ1+λ2+λ3+λ4=1;
the calculation of the total score of the power equipment is as follows:
S＝ω1×SD+ω2×SR；
wherein S is the total fraction of the electric equipment, SR is the fraction of the lubricating oil, ω1, ω2 are preset weights and ω1+ω2=1.
6. The abnormality monitoring method for an electrical device according to claim 5, wherein the method of judging whether to generate an early warning instruction includes:
Drawing a time-total score graph;
if the total score of the power equipment in the time-total score graph is R time sharing, the corresponding duration is smaller than a time threshold, or the total score of the power equipment is lower than R time sharing and higher than 0 time sharing, and the corresponding duration is smaller than the time threshold, no early warning instruction is generated;
if the total score of the power equipment in the time-total score graph is lower than R score and the corresponding duration is greater than a time threshold or the total score of the power equipment is less than 0 time, generating an early warning instruction;
when an early warning instruction is generated, acquiring a corresponding early warning grade according to the total score of the power equipment; and outputting the early warning grade, the lubricating oil fraction and the electrical characteristic parameter fraction to a central control screen of the electric power system.
7. The abnormality monitoring method for an electrical device according to claim 6, wherein when an early warning instruction is generated, a corresponding current parameter score is obtained, a cause of a failure of the electrical device is judged, and an electronic switch is adjusted according to the cause of the failure of the electrical device;
the method for judging the failure cause of the power equipment comprises the following steps:
subtracting the current parameter fraction of the last time point from the current parameter fraction obtained at present to obtain the change amount of the current parameter fraction in unit time;
If the change amount of the current parameter in the unit time is larger than the change amount threshold value, judging that the power equipment is in short circuit fault at the moment;
if the change amount of the current parameter fraction in unit time is smaller than or equal to the change amount threshold value, judging that the power equipment is in overload fault at the moment;
the power device that is in a short circuit fault or overload fault is marked as a faulty power device.
8. The abnormality monitoring method for an electrical device according to claim 7, characterized in that the adjusting method of the electronic switch includes:
if the power equipment is in a short-circuit fault, the electronic switch connected with the load by the fault power equipment is disconnected, and the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is connected; adding the power parameters required by the load connected with the fault power equipment to obtain required power, and obtaining the available power of the normal power equipment, wherein the available power is the difference value of the total power of the power equipment minus the power required by the load connected with the power equipment;
if the available power of the power equipment is larger than or equal to the required power in the normal power equipment, marking the power equipment with the available power larger than or equal to the required power as available power equipment, and switching on an electronic switch on a circuit for connecting the available power equipment and the fault power equipment; if the available power of the normal power equipment is smaller than the required power, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the required power, switching on the electronic switch on the circuit for connecting the corresponding normal power equipment and the fault power equipment; if the power accumulated value obtained by adding all the power equipment is smaller than the required power, the electronic switch on the circuit connected with the normal power equipment and the fault power equipment is not regulated;
If the power equipment is in overload fault, switching on an electronic switch on a circuit for connecting the normal power equipment and the fault power equipment; multiplying the current parameter and the voltage parameter of the collected fault power equipment to obtain equipment power parameter, and subtracting the equipment power parameter from the required power to obtain a power parameter difference value; acquiring available power of normal power equipment; if the available power of the power equipment is larger than the power parameter difference value in the normal power equipment, marking the power equipment with the available power larger than the power parameter difference value as power-on power equipment, and switching on an electronic switch on a circuit for connecting the power-on power equipment and the fault power equipment; and if the available power of the normal power equipment is smaller than the power parameter difference value, adding the available power of the normal power equipment to obtain a power accumulated value, and when the power accumulated value is larger than or equal to the power parameter difference value, switching on the electronic switch on the circuit for connecting the corresponding normal power equipment and the fault power equipment.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a method for anomaly monitoring of a power plant according to any one of claims 1-8 when the computer program is executed by the processor.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed, implements an anomaly monitoring method for an electrical device according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410227202.3A CN117874684B (en) | 2024-02-29 | 2024-02-29 | Abnormality monitoring method and device for power equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410227202.3A CN117874684B (en) | 2024-02-29 | 2024-02-29 | Abnormality monitoring method and device for power equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874684A true CN117874684A (en) | 2024-04-12 |
| CN117874684B CN117874684B (en) | 2024-07-19 |
Family
ID=90588639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410227202.3A Active CN117874684B (en) | 2024-02-29 | 2024-02-29 | Abnormality monitoring method and device for power equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874684B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118162032A (en) * | 2024-05-15 | 2024-06-11 | 山东北方淄特特种油股份有限公司 | Intelligent tank type reconciliation equipment for adaptively adjusting process parameters |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070030068A1 (en) * | 2005-08-08 | 2007-02-08 | Mitsubishi Denki Kabushiki Kaisha | Non-feedback type load current controller |
| US20110276828A1 (en) * | 2009-01-14 | 2011-11-10 | Kenji Tamaki | Apparatus anomaly monitoring method and system |
| CN113268835A (en) * | 2021-06-21 | 2021-08-17 | 河南工业大学 | Pumped storage hydroelectric generating set health assessment method and device based on extended isolation forest and cloud model |
| CN113469408A (en) * | 2021-05-21 | 2021-10-01 | 国网湖南省电力有限公司 | Running state trend prediction method and system for phase modulator |
| CN116383636A (en) * | 2023-03-30 | 2023-07-04 | 武汉理工大学 | Coal mill fault early warning method based on PCA and LSTM fusion algorithm |
| CN116537965A (en) * | 2023-06-13 | 2023-08-04 | 阳江核电有限公司 | On-line monitoring and fault diagnosis device for diesel engine |
| CN117213551A (en) * | 2023-06-09 | 2023-12-12 | 江苏方天电力技术有限公司 | Camera safety precaution and state evaluation system |
| CN117272179A (en) * | 2023-11-22 | 2023-12-22 | 南京迅集科技有限公司 | Equipment state detection system and method based on Internet of things |
-
2024
- 2024-02-29 CN CN202410227202.3A patent/CN117874684B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070030068A1 (en) * | 2005-08-08 | 2007-02-08 | Mitsubishi Denki Kabushiki Kaisha | Non-feedback type load current controller |
| US20110276828A1 (en) * | 2009-01-14 | 2011-11-10 | Kenji Tamaki | Apparatus anomaly monitoring method and system |
| CN113469408A (en) * | 2021-05-21 | 2021-10-01 | 国网湖南省电力有限公司 | Running state trend prediction method and system for phase modulator |
| CN113268835A (en) * | 2021-06-21 | 2021-08-17 | 河南工业大学 | Pumped storage hydroelectric generating set health assessment method and device based on extended isolation forest and cloud model |
| CN116383636A (en) * | 2023-03-30 | 2023-07-04 | 武汉理工大学 | Coal mill fault early warning method based on PCA and LSTM fusion algorithm |
| CN117213551A (en) * | 2023-06-09 | 2023-12-12 | 江苏方天电力技术有限公司 | Camera safety precaution and state evaluation system |
| CN116537965A (en) * | 2023-06-13 | 2023-08-04 | 阳江核电有限公司 | On-line monitoring and fault diagnosis device for diesel engine |
| CN117272179A (en) * | 2023-11-22 | 2023-12-22 | 南京迅集科技有限公司 | Equipment state detection system and method based on Internet of things |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118162032A (en) * | 2024-05-15 | 2024-06-11 | 山东北方淄特特种油股份有限公司 | Intelligent tank type reconciliation equipment for adaptively adjusting process parameters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874684B (en) | 2024-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117874684B (en) | Abnormality monitoring method and device for power equipment and storage medium | |
| EP3638900B1 (en) | Independent monitoring system for a wind turbine | |
| US20220376504A1 (en) | Proactive intelligent load shedding | |
| US20220221499A1 (en) | Electric disaster preemptive detection and prevention system using technology | |
| CN110726886B (en) | Apparatus, system and method for predicting remaining life of an electrical system | |
| CN108985498A (en) | A kind of retired replacing options of cable based on risk assessment | |
| CN111008485B (en) | Neural network-based multi-parameter life prediction method for three-phase alternating current asynchronous motor | |
| CN113156058A (en) | Nuclear power station transformer light gas alarm response method, device, equipment and medium | |
| US20190340708A1 (en) | Method for the usage planning of an electrical system for supplying energy | |
| Dhanraj et al. | Design on iot based real time transformer performance monitoring system for enhancing the safety measures | |
| US20130187389A1 (en) | Method for predictive monitoring of switch contactors and system therefor | |
| CN117196251A (en) | Monitoring method, system, equipment and medium for park power distribution facility | |
| CN116861615A (en) | Intelligent management system for on-site electric energy of building engineering | |
| RU2554574C2 (en) | High-voltage electrotechnical equipment (hvee) monitoring system | |
| CN114577452B (en) | Method, device, electronic equipment and computer medium for predicting service life of switch contact | |
| EP4084280A1 (en) | Status evaluation of electrical power distribution grids for power production plants or power consuming facilities | |
| CN113687259B (en) | Machine room UPS detection method and system for data center | |
| Wiboonrat | Condition Based Maintenance for Data Center Operations Management | |
| JP4044512B2 (en) | Power system stabilization control device and power system stabilization control method | |
| US11321450B2 (en) | Online static security assessment under the QSS model | |
| US20220019208A1 (en) | Method for Monitoring the Vitality of Devices of a Distributed System | |
| Desai et al. | If It Ain't Broke... | |
| CN118432481A (en) | Hydropower station excitation device operation control system | |
| Tripathi et al. | Fuzzy Inference System based Fault Detection in Smart Grid | |
| CN118409246A (en) | Monitoring method, device, monitoring system and storage medium for oil immersed transformer |
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 |