CN117134507B - Online monitoring method and system for full-station capacitive equipment based on intelligent group association - Google Patents
Online monitoring method and system for full-station capacitive equipment based on intelligent group association Download PDFInfo
- Publication number
- CN117134507B CN117134507B CN202311406306.2A CN202311406306A CN117134507B CN 117134507 B CN117134507 B CN 117134507B CN 202311406306 A CN202311406306 A CN 202311406306A CN 117134507 B CN117134507 B CN 117134507B
- Authority
- CN
- China
- Prior art keywords
- data
- capacitive
- time
- value
- equipment
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000002245 particle Substances 0.000 claims abstract description 53
- 230000006870 function Effects 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000012098 association analyses Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000010219 correlation analysis Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000007613 environmental effect Effects 0.000 claims description 26
- 238000013480 data collection Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 7
- 230000015556 catabolic process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000006731 degradation reaction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000003449 preventive effect Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012731 temporal analysis Methods 0.000 claims description 3
- 238000000700 time series analysis Methods 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 230000001932 seasonal effect Effects 0.000 claims description 2
- 230000000087 stabilizing effect Effects 0.000 claims description 2
- 230000005251 gamma ray Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 230000002068 genetic effect Effects 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 210000002364 input neuron Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00016—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent monitoring and analysis of power systems, and discloses an online monitoring method and an online monitoring system of full-station capacitive equipment based on intelligent group association, wherein the online monitoring method comprises the following steps: collecting real-time operation data of the capacitive device; preprocessing the collected data; establishing a capacitive equipment LSTM model by using an intelligent group association algorithm and a neural network learning technology, and carrying out real-time association analysis on the preprocessed data; based on the result of the correlation analysis, possible faults are predicted, and performance optimization suggestions are provided. The intelligent group association-based online monitoring method for the full-station capacitive equipment reduces power consumption in the network, measures load balance between the cloud network and the server by using the fitness function, and can be suitable for processing resource optimization. The results of the particle swarm are used as the initial population of the genetic algorithm, and the invention has better effects on the aspects of execution cost, load balancing and completion time.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring and analysis of power systems, in particular to an online monitoring method and an online monitoring system of full-station capacitive equipment based on intelligent group association.
Background
With the increasing complexity and scale of modern power systems, the need for real-time monitoring and fault prediction of power equipment is also increasing. Conventional power plant monitoring methods often rely on fixed thresholds and empirical rules, which may be misdirected or missed in the face of complex and diverse operating environments. In order to improve the operating efficiency and safety of electrical equipment, a more intelligent and accurate monitoring method is required.
Capacitive devices, as critical components in electrical power systems, have a direct impact on the safety and stable operation of the overall electrical power system in terms of stability and health. Traditional capacitive device monitoring methods are mainly based on physical characteristics and empirical data of the device, but these methods tend to be poorly effective when dealing with large-scale, high-dimensional real-time data.
In recent years, deep learning and machine learning technologies have made remarkable progress in many fields, which provides new possibilities for intelligent monitoring of electric power equipment. However, relying solely on deep learning or machine learning techniques may not adequately capture the complex characteristics and dynamic changes of the capacitive device. The intelligent group association algorithm, which is an optimization algorithm for simulating the behavior of the biological group, has good global searching capability and robustness, and can effectively solve the problem.
However, how to combine intelligent group association algorithms with deep learning and machine learning techniques to achieve efficient, accurate online monitoring of capacitive devices remains an unresolved challenge.
Therefore, the invention aims to provide an online monitoring method for full-station capacitive equipment based on intelligent group association so as to solve the problems.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: how to effectively combine the intelligent group association algorithm with the deep learning and machine learning technology so as to realize the efficient and accurate on-line monitoring of the capacitive equipment. In the face of large-scale, high-dimensional real-time data, traditional capacitive device monitoring methods may not be effective, but simply relying on deep learning or machine learning techniques may not adequately capture the complex characteristics and dynamic changes of the capacitive device. Therefore, the invention aims to improve the robustness and the accuracy of the monitoring method and ensure the stability and the safety of the capacitive equipment in various running environments by introducing an intelligent group correlation algorithm.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent group association-based online monitoring method for full-station capacitive equipment comprises the following steps:
collecting real-time operation data of the capacitive device;
preprocessing the collected data;
establishing a capacitive equipment LSTM model by using an intelligent group association algorithm and a neural network learning technology, and carrying out real-time association analysis on the preprocessed data;
based on the result of the association analysis, fault prediction is carried out, and performance optimization suggestions are provided.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: the real-time operational data is collected with IoT intelligent sensors,
current data: the IoT smart sensor monitors current changes of the capacitive device in real-time, including peak current, average current, and current waveforms;
voltage data: measuring input and output voltages of the equipment in real time, and stabilizing voltage and fluctuation conditions;
temperature data: the temperature of the equipment is monitored in real time by arranging a temperature sensor at the key part of the equipment;
vibration and sound data: monitoring physical vibration and operation noise of the equipment in real time through a vibration sensor and a sound sensor;
power quality data: including harmonics, voltage flicker, and frequency offset;
device status data: switch status, protection device status, and fault indication;
environmental data: humidity, atmospheric pressure, and ambient temperature.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: the pre-treatment may comprise the steps of,
data cleaning: identifying and processing abnormal values, missing values and repeated values, and ensuring the integrity and accuracy of data;
data normalization: converting all data into unified standards and ranges;
feature extraction: extracting identifiable features from the raw data;
data dimension reduction: the main component analysis technology is used, so that the dimensionality of data is reduced, most of information is reserved, and the operation efficiency of an algorithm is improved;
time series analysis: and (3) carrying out time sequence analysis on the continuously collected data, and identifying the trend, periodicity and seasonal characteristics of the data.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: the establishing of the capacitive device LSTM model includes,
introducing a plurality of particle swarms, wherein each particle swarm represents one characteristic of the capacitive device, and the weight and bias of each particle swarm are adjusted in real time according to the characteristic represented by the particle swarm, and the particle swarm is specifically expressed as:
；
wherein,indicate->Layer network->The weight of the individual particle groups is +.>A value at the time of the iteration; />Indicate->Layer network->Bias of individual particle swarm at +.>A value at the time of the iteration; />Indicate->Individual grainsThe learning rate of the subgroup; />Indicate->An optimization algorithm of the individual particle swarms;
fusing a plurality of particle swarms to obtain the output of each layer, wherein the specific formula is as follows:
；
wherein,indicate->Layer network->Outputting individual particle swarms; />Is an activation function; />Indicate->The weight of each particle swarm, which represents the requirement in fusion; />Representing the number of particle swarms; />Indicate->Layer network->The weight of each particle swarm; />Indicate->Layer network->Bias of individual particle swarms; />Representing an input;denoted as +.>The sum of the outputs of the layer network;
the final output of the activation function and the model is used for obtaining the characteristic description of the capacitive equipment at the moment t; the specific formula is as follows:
；
wherein,expressed as a history function; />Represented as an environmental function; />And->Is a weight parameter representing the importance of historical data and environmental factors; />Indicate->The weight of the individual history data; />Indicate->Weights of individual environmental factors; />Indicate->A personal environmental factor; />Representing the number of environmental factors; />A characterization denoted as time t-i.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: the establishing of the LSTM model of the capacitive device further comprises,
combining the historical data with the environmental factors to obtain a combined function：
；
Obtaining final feature descriptions of models by activating functions:
；
Wherein,and->Is a newly introduced nonlinear function and represents the relation between the working state of the capacitive equipment and the historical data and environmental factors thereof; />Expressed as external field coefficients +.>Expressed as external field strength>An influence index expressed as an external field; />Expressed as considering the external field coefficient +.>External field strength->Impact index of external fieldIs->A nonlinear combining function; />Expressed as an influence index taking into account the external field +.>Is->A nonlinear combining function;
obtaining the moment of time of the capacitive deviceFeature description of (1)>：
；
Wherein,representing the newly introduced weight parameters; />Expressed as considering the external field coefficient +.>External field strength->Influence index of external field->Is->A nonlinear function; />Expressed as considering the external field coefficient +.>External field strength->Influence index of external field->History, environment>A nonlinear function.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: performing the real-time correlation analysis on the preprocessed data includes,
description of working states: description of capacitive device at timeIs a working state of (a);
health index: a scalar value indicating the health status of the capacitive device, a high value indicating a good status of the device, otherwise a problem exists;
probability of failure: a value between 0 and 1, representing the probability of the capacitive device failing within a certain time period in the future;
performance score: a scalar value, representing the performance of the capacitive device, is used for comparison with other devices or historical data.
As a preferable scheme of the intelligent group association-based online monitoring method for the total station capacitive equipment, the invention comprises the following steps: predicting faults based on the result of the association analysis, and providing the performance optimization suggestions, wherein the performance optimization suggestions specifically comprise different optimization suggestions are obtained according to different analysis conditions;
the working state description:
when (when)When the value of (2) is greater than 0.9, it means that the capacitive device is at time +.>Is optimal;
when (when)When the value of (2) is greater than or equal to 0.5 and less than or equal to 0.9, the capacitive device is indicated at the moment +.>The working state of the device is normal;
when (when)When the value of (2) is smaller than 0.5, it means that the capacitive device is at time +.>Is poor;
the health index:
when (when)The value of (2) is greater than or equal to 0.8, the capacitive equipment is in a healthy state at present and is not subjected to any maintenance;
when (when)The value of (2) is between 0.5 and 0.8, the capacitive device is in a sub-health state, and an instruction for scheduling routine inspection is sent;
when (when)If the value of the number is less than or equal to 0.5, the capacitive equipment is in an unhealthy state, and immediately sends out an instruction for scheduling maintenance and inspection;
the probability of failure:
when (when)The value of (2) is less than or equal to 0.3, which indicates that the probability of the fault of the capacitive equipment is high, and the monitored attention weight is added to the capacitive equipment with high probability of predicting the fault;
when (when)A value of between 0.3 and 0.6, indicating that the capacitive device has a moderate risk of failure, for preventive maintenance;
when (when)The value of (2) is more than or equal to 0.6, which means that the risk of the fault of the capacitive equipment in the future is low, and the monitoring attention weight is reduced;
the performance score:
when (when)The value of (2) is more than or equal to 0.9, which means that the capacity device has good performance and can continuously work;
when (when)The value of (2) is between 0.7 and 0.9, which indicates that the capacity device has good performance, the attention weight is increased, and the performance change of the capacity device after long-time working is focused;
when (when)The value of (2) is 0.7 or less, which indicates the performance degradation of the capacitive device, and issues an environment monitoring instruction to check whether or not there is a performance degradation due to an external factor.
Full station capacitive equipment on-line monitoring system based on intelligent group association includes:
and a data collection module: the system comprises a data collection module, a data collection module and a data collection module, wherein the data collection module is used for collecting real-time operation data of the capacitive equipment;
and a data preprocessing module: receiving real-time operation data from a data collection module and preprocessing the real-time operation data to meet the input requirements of a subsequent module;
intelligent group association algorithm and neural network learning module:
LSTM model unit: performing real-time association analysis on the preprocessed data from the data preprocessing module by using an intelligent group association algorithm and a neural network learning technology;
correlation analysis unit: based on the output of the LSTM model unit, performing association analysis to determine the current state and the future state of the capacitive device;
fault prediction and performance optimization suggestion module: and receiving a correlation analysis result from the intelligent group correlation algorithm and the neural network learning module, predicting possible faults, and proposing performance optimization suggestions according to the prediction result.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method as described above.
The invention has the beneficial effects that: the intelligent group association-based full-station capacitive equipment online monitoring method reduces the power consumption in the network, measures the load balance between the cloud network and the server (host) by using the fitness function, and converts the load balance problem into the optimization problem, so that the method is suitable for processing resource optimization. The results of the particle swarm are used as the initial population of the genetic algorithm, and the invention has better effects on the aspects of execution cost, load balancing and completion time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is an overall flowchart of an online monitoring method for full-station capacitive devices based on intelligent group association according to a first embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided an online monitoring method for full-station capacitive devices based on intelligent group association, including:
s1: real-time operational data of the capacitive device is collected.
The following data were collected with IoT intelligent sensors:
current data: ioT smart sensors monitor current changes of capacitive devices in real-time, including peak current, average current, and current waveforms.
Voltage data: the input and output voltages of the device are measured in real time, as well as voltage stability and ripple conditions.
Temperature data: the temperature sensor is deployed at the key part of the equipment, so that the temperature of the equipment is monitored in real time, and the operation of the equipment in a safe range is ensured.
Vibration and sound data: physical vibration and operating noise of the device are monitored in real time by vibration and sound sensors to predict and detect mechanical faults.
Power quality data: including harmonics, voltage flicker, and frequency offset, etc., ensure that the device operates in a good power environment.
Device status data: switch status, protection device status, and fault indication.
Environmental data: humidity, atmospheric pressure and ambient temperature, the working environment of the device was analyzed for its effect on performance and lifetime.
Further, ioT intelligent sensors may not only collect data in real-time, but may also perform preliminary analysis and processing. They can be directly connected with cloud or other systems to realize real-time data sharing and remote monitoring.
It should be noted that other sensors may be replaced or used in combination for different data information requirements to achieve comprehensive and accurate monitoring of the capacitive device. By selecting the appropriate sensor type and configuration, accurate acquisition of real-time data of the capacitive device can be ensured and specific monitoring requirements and conditions are met.
S2: preprocessing the collected data.
Data cleaning: identifying and processing abnormal values, missing values and repeated values, and ensuring the integrity and accuracy of data.
Data normalization: all data are converted into a unified standard or range to eliminate the dimension and scale differences of the data.
Data fusion: combining data from different sensors results in more comprehensive equipment operation information.
Feature extraction: key features are extracted from the raw data to simplify subsequent analysis and computation.
Data dimension reduction: the principal component analysis technology is used, the dimensionality of data is reduced, most of information is reserved, and the operation efficiency of an algorithm is improved.
Time series analysis: and (3) carrying out time sequence analysis on the continuously collected data, identifying the characteristics of data such as trend, periodicity and seasonality, and providing references for subsequent association analysis and fault prediction.
It should be noted that preprocessing also includes encryption and compression of data, ensuring the security and transmission efficiency of data. Meanwhile, the system can also segment and batch process the data according to actual needs so as to adapt to different analysis and calculation requirements.
S3: and establishing a capacitive equipment LSTM model by using an intelligent group association algorithm and a neural network learning technology, and carrying out real-time association analysis on the preprocessed data.
A plurality of particle populations are introduced, each particle population representing a particular characteristic of the capacitive device. The weight and bias of each particle swarm is adjusted in real time according to the characteristic represented by the particle swarm. The concrete steps are as follows:
；
wherein,indicate->Layer network->The weight of the individual particle groups is +.>A value at the time of the iteration; />Indicate->Layer network->Bias of individual particle swarm at +.>A value at the time of the iteration; />Indicate->The learning rate of the individual particle swarms; />Indicate->An optimization algorithm of the individual particle swarms;
fusing a plurality of particle swarms to obtain the output of each layer, wherein the specific formula is as follows:
；
wherein,indicate->Layer network->Outputting individual particle swarms; />Is an activation function; />Indicate->The weight of each particle swarm, which represents the requirement in fusion; />Representing the number of particle swarms; />Indicate->Layer network->The weight of each particle swarm; />Indicate->Layer network->Bias of individual particle swarms; />Representing an input;denoted as +.>The sum of the outputs of the layer network;
the characteristic description of the capacitive device at the moment t is obtained through the special activation function and the final output of the model; the specific formula is as follows:
；
wherein,expressed as a history function; />Represented as an environmental function; />And->Is a weight parameter representing the importance of historical data and environmental factors; />Indicate->The weight of the individual history data; />Indicate->Weights of individual environmental factors; />Indicate->A personal environmental factor; />Representing the number of environmental factors; />A characterization denoted as time t-i.
Combining the historical data with the environmental factors to obtain a combined function：
；
Obtaining final feature descriptions of models by activating functions:
；
Wherein,and->Is a newly introduced nonlinear function and represents the relation between the working state of the capacitive equipment and the historical data and environmental factors thereof; />Expressed as external field coefficients +.>Expressed as external field strength>An influence index expressed as an external field; />Expressed as considering the external field coefficient +.>External field strength->Impact index of external fieldIs->A nonlinear combining function; />Expressed as an influence index taking into account the external field +.>Is->A nonlinear combining function;
obtaining the moment of time of the capacitive deviceFeature description of (1)>：
；
Wherein,representing the newly introduced weight parameters; />Expressed as considering the external field coefficient +.>External field strength->Influence index of external field->Is->A nonlinear function; />Expressed as considering the external field coefficient +.>External field strength->Influence index of external field->History, environment>A nonlinear function.
It should be noted that, in order to improve the accuracy of the calculation result in the present invention, the influence of the external field of the capacitive device is considered in the function, and this influence cannot be ignored in the accuracy calculation.
And carrying out the real-time association analysis on the preprocessed data:
description of working states: description of capacitive device at timeIs not in the operating state.
Health index: a scalar value indicates the health of the capacitive device, with higher values indicating better device status and vice versa may be problematic.
Probability of failure: a value between 0 and 1 indicates the probability of the capacitive device failing within a certain time period in the future.
Performance score: a scalar value, representing the performance of the capacitive device, may be used for comparison with other devices or historical data.
Furthermore, the model and the formula are based on the combination of an intelligent group association algorithm and a neural network learning technology, and aim to provide a more accurate and robust online monitoring method for the capacitive equipment. In practical applications, the real-time adjustment of the characteristics, weights and biases of the capacitive device represented by each particle swarm, and the fusion of a plurality of particle swarms are all used for ensuring that the model can better capture the dynamic change and complex characteristics of the capacitive device.
The specific model structure is as follows:
input layer (layer 1):
the functions are as follows: receiving real-time data of the accommodating device.
The structure is as follows: composed of input neurons, the number depends on the number of characteristics collected.
Intelligent group association layer (layer 2):
the functions are as follows: the input data is feature extracted using a plurality of particle swarms. Each particle swarm learns and represents a particular characteristic of the capacitive device.
The structure is as follows: consists of a plurality of particle populations, each particle population having its weight and bias. These weights and offsets are adjusted in real time based on the characteristics they represent.
LSTM layer (layer 3):
the functions are as follows: long-term dependencies in the time series data are captured. The LSTM unit may remember past information and use for future predictions.
The structure is as follows: consists of a plurality of LSTM cells, each cell having its weight and bias.
Full tie layer (layer 4):
the functions are as follows: the output of the LSTM layer is converted into a fixed-size vector in preparation for final prediction or classification.
The structure is as follows: is composed of multiple neurons, each with its weight and bias.
Output layer (layer 5):
the functions are as follows: based on the output of the fully connected layer, the future state of the capacitive device is predicted or classified.
The structure is as follows: composed of output neurons, the number depends on the number of predicted classes or the range of consecutive values.
Input layer and intelligent group association layer: the output of the input layer is directly used as the input of the intelligent group association layer, and the characteristic extraction is carried out through the particle swarm.
Intelligent group association layer and LSTM layer: after being processed, the output of the intelligent group association layer is used as the input of the LSTM layer and is used for capturing the long-term dependency relationship in the time sequence data.
LSTM layer and full connection layer: the output of the LSTM layer is directly used as an input to the full link layer for further processing.
Full tie layer and output layer: and after the output of the full-connection layer is processed by the activation function, the output is used as the input of the output layer to carry out final prediction or classification.
Furthermore, the new nonlinear function and the weight parameter are introduced into the model so that the model can better consider the relation between the working state of the capacitive equipment and the historical data and environmental factors of the capacitive equipment. These new components and parameters are all based on a great deal of experiments and researches, aiming at improving the prediction accuracy and stability of the model.
It should be noted that, although the above model and formula provide a new online monitoring method for the capacitive device, in practical application, appropriate adjustment and optimization is required according to the specific type of the capacitive device, the working environment and the data characteristics. In addition, continuous training and updating of the model is also required in order to ensure the high efficiency and real-time performance of the model.
S4: based on the result of the correlation analysis, possible faults are predicted, and performance optimization suggestions are provided.
According to different analysis conditions, different optimization suggestions are obtained; description of working states:
when (when)When the value of (2) is greater than 0.9, it means that the capacitive device is at time +.>Is optimal, maintaining the current attention weight; when->When the value of (2) is greater than or equal to 0.5 and less than or equal to 0.9, the capacitive device is indicated at the moment +.>Normal working state, increasing attention weight by 5%; when->When the value of (2) is smaller than 0.5, it means that the capacitive device is at time +.>Is poor in working state and increases attentionThe force weight is 10%.
Health index:
when (when)If the value of (2) is more than or equal to 0.8, the capacitive equipment is in a healthy state at present, no maintenance is needed, and the attention weight is reduced by 5%; when->If the value of (2) is between 0.5 and 0.8, the capacitive device is in a sub-health state, and sends out an instruction for scheduling routine inspection, so that the current attention weight is kept; when->If the value of (2) is less than or equal to 0.5, the capacitive device has an instruction of non-health state, and immediately scheduling maintenance and inspection, and increasing the attention weight by 15%.
Probability of failure:
when (when)The value of (2) is less than or equal to 0.3, which means that the probability of the fault of the capacitive equipment is high, and the attention weight is increased by 20%; when->A value of 0.3 to 0.6, indicating that the capacitive device has a moderate risk of failure, performing preventive maintenance, and increasing the attention weight by 10%; when->The value of (2) is greater than or equal to 0.6, which means that the risk of the fault of the capacitive equipment in the future is low, and the attention weight is reduced by 5%.
Performance score:
when (when)The value of (2) is more than or equal to 0.9, which means that the performance of the capacitive device is very excellent, and the capacitive device can work continuously, and the attention weight is reduced by 5%; when->The value of (2) is between 0.7 and 0.9, which indicates that the performance of the capacitive device is good, the attention weight is increased, the performance change after the capacitive device works for a long time is focused, and the attention weight is increased by 5 percent; when->The value of (2) is less than or equal to 0.7, which indicates the performance degradation of the capacitive device, and issues an environment monitoring instruction to check whether there is a performance degradation caused by an external factor, and increase the attention weight by 10%.
Further, for the real-time monitoring of the capacitive device, besides the basic indexes, factors such as working environment, service life, history maintenance record and the like of the device can be considered, so that more comprehensive fault prediction and performance evaluation can be provided. For example, for a capacitive device operating in a high temperature, high humidity environment for a long period of time, even if its current operating condition index is good, more frequent inspection and maintenance may be required to prevent potential failure due to environmental factors.
Further, the failure mode and performance decay curves may be different for different types and brands of capacitive devices. Therefore, in performing fault prediction and performance evaluation, specific models of devices and technical parameters provided by manufacturers are also required to be considered so as to ensure the accuracy and pertinence of analysis.
It should be noted that the above-described failure prediction and performance evaluation methods are based on a large amount of experimental data and practical application experience. In practical applications, in order to ensure accuracy and real-time performance of prediction, continuous training and updating of the model are also required to adapt to technical progress of the capacitive device and changes of use environment. Meanwhile, for each fault prediction and performance evaluation result, comparison and verification with the actual equipment state are required to further optimize parameters and algorithms of the model.
The above attention control deployment scheme is one way adopted by the present invention, and does not represent the best strategy in practical application. In practical application, the weight adjustment values should be adjusted according to the specific requirements and practical situations of the system.
In the above embodiment, the system for online monitoring of all-station capacitive devices based on intelligent group association is also included, which includes,
and a data collection module: the system comprises a data collection module, a data collection module and a data collection module, wherein the data collection module is used for collecting real-time operation data of the capacitive equipment;
and a data preprocessing module: receiving real-time operation data from a data collection module and preprocessing the real-time operation data to meet the input requirements of a subsequent module;
intelligent group association algorithm and neural network learning module:
LSTM model unit: performing real-time association analysis on the preprocessed data from the data preprocessing module by using an intelligent group association algorithm and a neural network learning technology;
correlation analysis unit: performing association analysis based on the output of the LSTM model unit to determine the current state and possible future state of the capacitive device;
fault prediction and performance optimization suggestion module: and receiving a correlation analysis result from the intelligent group correlation algorithm and the neural network learning module, predicting possible faults, and proposing performance optimization suggestions according to the prediction result.
The computer device may be a server. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data cluster data of the power monitoring system. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements an intelligent group association-based online monitoring method for full-station capacitive devices.
Example 2
For one embodiment of the invention, an online monitoring method of the full-station capacitive equipment based on intelligent group association is provided, and in order to verify the beneficial effects of the invention, scientific demonstration is carried out through economic benefit calculation and simulation/comparison experiments.
Experiment setting:
the purpose is as follows: and comparing the difference of the intelligent group association-based full-station capacitive equipment online monitoring method (hereinafter referred to as a new method) and the traditional capacitive equipment monitoring method (hereinafter referred to as a traditional method) in fault prediction accuracy, performance evaluation accuracy and response time.
Test equipment: 10 pieces of capacitive equipment, each piece of equipment has the same working condition and history record.
Test period: for 30 days
Fault injection: during the test period, faults were injected randomly for 5 devices.
The results of the experiments are shown in the following table,
table 1 experimental results
From experimental results, the new method has higher accuracy in fault prediction than the conventional method, especially in the case of fault injection but not detected by the conventional method. The performance score of the new method is closer to the state of the actual equipment, and the health condition of the equipment can be reflected more accurately. The response time of the new method is faster than the conventional method, which means that the new method can provide feedback to the operator faster, thereby taking necessary measures faster.
Further, comparing the accuracy of the data of the conventional method with that of the present invention, the comparison data are as follows:
table 2 comparison table of predicted current values
Table 3 comparison table of predicted device temperatures
Table 4 comparison table for predicting humidity of a plant
From the above data, it can be seen that the predicted value of the present invention is very close to the true value, and there is a certain deviation between the predicted value and the true value of the conventional LSTM model, which further proves the superiority and accuracy of the model of the present invention.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (8)
1. The online monitoring method for the full-station capacitive equipment based on intelligent group association is characterized by comprising the following steps of:
collecting real-time operation data of the capacitive device;
preprocessing the collected data;
establishing a capacitive equipment LSTM model by using an intelligent group association algorithm and a neural network learning technology, and carrying out real-time association analysis on the preprocessed data;
based on the result of the association analysis, performing fault prediction and providing performance optimization suggestions;
the establishing of the capacitive device LSTM model includes,
introducing a plurality of particle swarms, wherein each particle swarm represents one characteristic of the capacitive device, and the weight and bias of each particle swarm are adjusted in real time according to the characteristic represented by the particle swarm, and the particle swarm is specifically expressed as:
wherein,a value representing the weight of j particle groups of the i-th layer network at the kth iteration; />Representing the value of the bias of j particle groups of the i-th layer network at the kth iteration; alpha j The learning rate of the jth particle group is represented; PSO (particle swarm optimization) j An optimization algorithm representing a j-th particle swarm;
fusing a plurality of particle swarms to obtain the output of each layer, wherein the specific formula is as follows:
f i,j (x)＝σ(W i,j ·x+b i,j )
wherein f i,j Output of j particle groups representing the i-th layer network; sigma is an activation function; gamma ray j The weight of the j-th particle group is represented, and the requirement in fusion is represented; n represents the number of particle swarms; w (W) i,j Weights representing j particle groups of the i-th layer network; b i,j A bias representing j particle groups of the i-th layer network; x represents an input; f (f) i,combined (x) Represented as the sum of the outputs of the layer i network;
the final output of the activation function and the model is used for obtaining the characteristic description of the capacitive equipment at the moment t; the specific formula is as follows:
wherein f history Expressed as a history function; f (f) env Represented as an environmental function; λ and μ are weight parameters representing the importance of the historical data and environmental factors; δi represents the weight of the i-th history data; η (eta) j A weight representing a j-th environmental factor; ENV (enhanced optical network) j Represents the j-th environmental factor; m represents the number of environmental factors; CD (compact disc) t-i A characterization denoted as time t-i;
combining the historical data with the environmental factors to obtain a combination function f combined ：
f combined ＝f i,combined +f history +f env
Obtaining final feature description f of model by activating function final (f combined ):
Wherein,and xi is a newly introduced nonlinear function representing the relationship of the working state of the capacitive device with its historical data and environmental factors; c is expressed as an external field coefficient, L is expressed as an external field strength, and θ is expressed as an influence index of the external field;expressed as +.f considering the external field coefficient C, the external field strength L, the external field influence index θ>A nonlinear combining function; zeta (f) combined θ) is represented as a ζ nonlinear combination function considering an influence index θ of the external field;
obtaining a characterization CD of the capacitive device at time t t ：
CD t ＝α×f final (f combined )+β×ψ(C'L’θ)+γ×ξ(C'L'θ'f history ’ fenv )
Wherein, alpha, beta and gamma represent newly introduced weight parameters; ψ (C, L, θ) is expressed as an index θ considering the external field coefficient C, the external field strength L, and the influence of the external fieldA nonlinear function; ζ (C, L, θ, f) history ，f env ) Represented as a nonlinear function taking into account the external field coefficient C, the external field strength L, the history of the external field's impact index θ, the environment ζ.
2. The intelligent group association-based online monitoring method for full-station capacitive devices as claimed in claim 1, wherein: the real-time operational data is collected with IoT intelligent sensors,
current data: the IoT smart sensor monitors current changes of the capacitive device in real-time, including peak current, average current, and current waveforms;
voltage data: measuring input and output voltages of the equipment in real time, and stabilizing voltage and fluctuation conditions;
temperature data: the temperature of the equipment is monitored in real time by arranging a temperature sensor at the key part of the equipment;
vibration and sound data: monitoring physical vibration and operation noise of the equipment in real time through a vibration sensor and a sound sensor;
power quality data: including harmonics, voltage flicker, and frequency offset;
device status data: switch status, protection device status, and fault indication;
environmental data: humidity, atmospheric pressure, and ambient temperature.
3. The intelligent group association-based online monitoring method for full-station capacitive devices as claimed in claim 2, wherein: the pre-treatment may comprise the steps of,
data cleaning: identifying and processing abnormal values, missing values and repeated values, and ensuring the integrity and accuracy of data;
data normalization: converting all data into unified standards and ranges;
feature extraction: extracting identifiable features from the raw data;
data dimension reduction: the main component analysis technology is used, so that the dimensionality of data is reduced, most of information is reserved, and the operation efficiency of an algorithm is improved;
time series analysis: and (3) carrying out time sequence analysis on the continuously collected data, and identifying the trend, periodicity and seasonal characteristics of the data.
4. The intelligent group association-based online monitoring method for full-station capacitive devices as claimed in claim 3, wherein: performing the real-time correlation analysis on the preprocessed data includes,
description of working states: describing the working state of the capacitive device at time t;
health index: a scalar value indicating the health status of the capacitive device, a high value indicating a good status of the device, otherwise problematic;
probability of failure: a value between 0 and 1, representing the probability of the capacitive device failing within a certain time period in the future;
performance score: a scalar value, representing the performance of the capacitive device, is used for comparison with other devices or historical data.
5. The intelligent group association-based online monitoring method for full-station capacitive devices as claimed in claim 4, wherein: predicting faults based on the result of the association analysis, and providing the performance optimization suggestions, wherein the performance optimization suggestions specifically comprise different optimization suggestions are obtained according to different analysis conditions;
the working state description:
when CD t When the value of (2) is greater than 0.9, it indicates that the working state of the capacitive device at time t is the mostPreferably;
when CD t When the value of (2) is more than or equal to 0.5 and less than or equal to 0.9, the working state of the capacitive device at the time t is normal;
when CD t When the value of (2) is smaller than 0.5, the working state difference of the capacitive device at the time t is represented;
the health index:
when CD t The value of (2) is greater than or equal to 0.8, the capacitive equipment is in a healthy state at present and is not subjected to any maintenance;
when CD t The value of (2) is between 0.5 and 0.8, the capacitive device is in a sub-health state, and an instruction for scheduling routine inspection is sent;
when CD t If the value of the number is less than or equal to 0.5, the capacitive equipment is in an unhealthy state, and immediately sends out an instruction for scheduling maintenance and inspection;
the probability of failure:
when CD t The value of (2) is less than or equal to 0.3, which indicates that the probability of the fault of the capacitive equipment is high, and the monitored attention weight is added to the capacitive equipment with high probability of predicting the fault;
when CD t A value of between 0.3 and 0.6, indicating that the capacitive device has a moderate risk of failure, for preventive maintenance;
when CD t The value of (2) is more than or equal to 0.6, which means that the risk of the fault of the capacitive equipment in the future is low, and the monitoring attention weight is reduced;
the performance score:
when CD t The value of (2) is more than or equal to 0.9, which means that the capacity device has good performance and can continuously work;
when CD t The value of (2) is between 0.7 and 0.9, which indicates that the capacity device has good performance, the attention weight is increased, and the performance change of the capacity device after long-time working is focused;
when CD t The value of (2) is 0.7 or less, which indicates the performance degradation of the capacitive device, and issues an environment monitoring instruction to check whether or not there is a performance degradation due to an external factor.
6. An intelligent group association-based full-station capacitive equipment online monitoring system based on the method of any one of claims 1 to 5, which is characterized in that: comprising the steps of (a) a step of,
and a data collection module: the system comprises a data collection module, a data collection module and a data collection module, wherein the data collection module is used for collecting real-time operation data of the capacitive equipment;
and a data preprocessing module: receiving real-time operation data from a data collection module and preprocessing the real-time operation data to meet the input requirements of a subsequent module;
intelligent group association algorithm and neural network learning module:
LSTM model unit: performing real-time association analysis on the preprocessed data from the data preprocessing module by using an intelligent group association algorithm and a neural network learning technology;
correlation analysis unit: based on the output of the LSTM model unit, performing association analysis to determine the current state and the future state of the capacitive device;
fault prediction and performance optimization suggestion module: and receiving a correlation analysis result from the intelligent group correlation algorithm and the neural network learning module, predicting the fault, and proposing performance optimization suggestions according to the prediction result.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311406306.2A CN117134507B (en) | 2023-10-27 | 2023-10-27 | Online monitoring method and system for full-station capacitive equipment based on intelligent group association |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311406306.2A CN117134507B (en) | 2023-10-27 | 2023-10-27 | Online monitoring method and system for full-station capacitive equipment based on intelligent group association |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117134507A CN117134507A (en) | 2023-11-28 |
| CN117134507B true CN117134507B (en) | 2024-01-02 |
Family
ID=88861322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311406306.2A Active CN117134507B (en) | 2023-10-27 | 2023-10-27 | Online monitoring method and system for full-station capacitive equipment based on intelligent group association |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117134507B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
| CN112906764A (en) * | 2021-02-01 | 2021-06-04 | 中国人民解放军海军工程大学 | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network |
| CN114970774A (en) * | 2022-07-29 | 2022-08-30 | 国网经济技术研究院有限公司 | Intelligent transformer fault prediction method and device |
| CN115579870A (en) * | 2022-10-12 | 2023-01-06 | 国网河南省电力公司濮阳供电公司 | Resource optimal configuration control method for power grid operation monitoring and source grid load storage |
| CN116680598A (en) * | 2023-06-01 | 2023-09-01 | 电子科技大学长三角研究院(衢州) | Fault diagnosis and residual life prediction method for intelligent distribution box of construction site |
| CN116739562A (en) * | 2023-06-15 | 2023-09-12 | 国网安徽省电力有限公司宿州供电公司 | LSTM-based power distribution network stability operation and maintenance method |
-
2023
- 2023-10-27 CN CN202311406306.2A patent/CN117134507B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
| CN112906764A (en) * | 2021-02-01 | 2021-06-04 | 中国人民解放军海军工程大学 | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network |
| CN114970774A (en) * | 2022-07-29 | 2022-08-30 | 国网经济技术研究院有限公司 | Intelligent transformer fault prediction method and device |
| CN115579870A (en) * | 2022-10-12 | 2023-01-06 | 国网河南省电力公司濮阳供电公司 | Resource optimal configuration control method for power grid operation monitoring and source grid load storage |
| CN116680598A (en) * | 2023-06-01 | 2023-09-01 | 电子科技大学长三角研究院(衢州) | Fault diagnosis and residual life prediction method for intelligent distribution box of construction site |
| CN116739562A (en) * | 2023-06-15 | 2023-09-12 | 国网安徽省电力有限公司宿州供电公司 | LSTM-based power distribution network stability operation and maintenance method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117134507A (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612650B (en) | DTW distance-based power consumer grouping method and system | |
| CN110222991B (en) | Metering device fault diagnosis method based on RF-GBDT | |
| CN107807860B (en) | Power failure analysis method and system based on matrix decomposition | |
| CN108921230A (en) | Method for diagnosing faults based on class mean value core pivot element analysis and BP neural network | |
| CN109409444B (en) | Multivariate power grid fault type discrimination method based on prior probability | |
| CN110879377A (en) | Metering device fault tracing method based on deep belief network | |
| Li et al. | A hybrid framework for predicting the remaining useful life of battery using Gaussian process regression | |
| CN117368745B (en) | Hard-pack lithium battery safety monitoring method and device based on deep learning | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN117134507B (en) | Online monitoring method and system for full-station capacitive equipment based on intelligent group association | |
| CN117113202A (en) | Power loop energy consumption detection method and equipment based on joint error stacking model | |
| CN115952928A (en) | Short-term power load prediction method, device, equipment and storage medium | |
| CN113961708B (en) | Power equipment fault tracing method based on multi-level graph convolutional network | |
| Liu et al. | Prediction method for battery self-discharge voltage drop based on pre-classifier | |
| CN113076217A (en) | Disk fault prediction method based on domestic platform | |
| Yin et al. | A binary-classification method based on dictionary learning and admm for network intrusion detection | |
| Zhang et al. | Artificial intelligence-based early warning method for abnormal operation and maintenance data of medical and health equipment | |
| Guo et al. | Construction of user abnormal behavior detection model based on smart charging platform for electric vehicles | |
| Wang et al. | Anomaly monitoring in high-density data centers based on gaussian distribution anomaly detection algorithm | |
| CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
| CN117540344A (en) | Distribution transformer anomaly monitoring and operation trend prediction method, equipment and medium | |
| CN117691756B (en) | Safety early warning management method and system for power distribution cabinet | |
| CN115712064B (en) | Excitation system fault diagnosis method based on LSTM-CNN hybrid neural network | |
| CN118133109A (en) | User intelligent electricity consumption analysis device and analysis method thereof | |
| Shen et al. | Prediction of SOC for lead-acid battery based on LSTM-Attention and LightGBM |
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 |