CN117556359A - Power distribution equipment health state evaluation system and method - Google Patents
Power distribution equipment health state evaluation system and method Download PDFInfo
- Publication number
- CN117556359A CN117556359A CN202311579720.3A CN202311579720A CN117556359A CN 117556359 A CN117556359 A CN 117556359A CN 202311579720 A CN202311579720 A CN 202311579720A CN 117556359 A CN117556359 A CN 117556359A
- Authority
- CN
- China
- Prior art keywords
- data
- power distribution
- twin model
- digital twin
- vibration
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 104
- 230000036541 health Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 97
- 238000012544 monitoring process Methods 0.000 claims abstract description 66
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 54
- 238000000354 decomposition reaction Methods 0.000 claims description 30
- 238000004141 dimensional analysis Methods 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 22
- 238000012512 characterization method Methods 0.000 claims description 15
- 230000003862 health status Effects 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 230000001537 neural effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 9
- 230000002159 abnormal effect Effects 0.000 description 14
- 238000000605 extraction Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000009432 framing Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- AYFVYJQAPQTCCC-GBXIJSLDSA-N L-threonine Chemical compound C[C@@H](O)[C@H](N)C(O)=O AYFVYJQAPQTCCC-GBXIJSLDSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- 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
- 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]
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a power distribution equipment health state evaluation system and a method, wherein the system comprises the following steps: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; the data acquisition module is used for acquiring equipment monitoring data corresponding to a target power distribution station and sending the equipment monitoring data to the digital twin model configuration module; the digital twin model configuration module is used for configuring a digital twin model corresponding to the target power distribution station according to the equipment monitoring data and determining evaluation data based on the digital twin model; the intelligent analysis module is used for determining an analysis result corresponding to the target power distribution station according to the evaluation data. Based on the technical scheme, the problem of low evaluation efficiency in the process of evaluating the health state of the power distribution equipment is solved, and the reliability of the evaluation result is improved.
Description
Technical Field
The invention relates to the field of health evaluation of power distribution equipment, in particular to a system and a method for evaluating the health state of power distribution equipment.
Background
With the continuous development of power technology, in order to ensure the automatic operation of a power distribution network, real-time, quasi-real-time and non-real-time data of the power distribution network equipment are generally integrated and integrated to realize monitoring, protection, control and the like of the normal operation and accident situation of the power distribution network. Moreover, in order for the distribution network equipment to function properly, it is often necessary to evaluate the status of each distribution equipment in the distribution network.
However, the existing health state evaluation mode usually performs field inspection on equipment through operation and maintenance personnel/experts, and then evaluates the health state of power distribution to obtain a corresponding health state evaluation conclusion, so that the evaluation efficiency is too low, and the reliability of an evaluation result is insufficient.
Disclosure of Invention
The invention provides a system and a method for evaluating the health state of power distribution equipment, which are used for improving the health evaluation efficiency of the power distribution equipment and the credibility of the health state evaluation result.
According to an aspect of the present invention, there is provided a power distribution apparatus health status evaluation system, characterized in that the system includes: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; wherein,
The data acquisition module is used for acquiring equipment monitoring data corresponding to the target power distribution station and sending the equipment monitoring data to the digital twin model configuration module;
the digital twin model configuration module is used for configuring a digital twin model corresponding to the target power distribution station according to the equipment monitoring data and determining evaluation data based on the digital twin model;
the intelligent analysis module is used for determining an analysis result corresponding to the target power distribution station according to the evaluation data.
According to another aspect of the present invention, there is provided a power distribution equipment health state evaluation method, which is characterized by being applied to a power distribution equipment health state evaluation system including: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; the power distribution equipment health state evaluation method comprises the following steps:
acquiring equipment monitoring data corresponding to a target power distribution station through the data acquisition module, and transmitting the equipment monitoring data to the digital twin model configuration module;
the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the equipment monitoring data, and determines evaluation data based on the digital twin model;
Upon determining the evaluation data, the intelligent analysis module determines an analysis result corresponding to the target substation based on the evaluation data.
According to the technical scheme, equipment monitoring data corresponding to a target power distribution station are obtained through the data acquisition module, the equipment monitoring data are sent to the digital twin model configuration module, the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the equipment monitoring data, evaluation data are determined based on the digital twin model, and after the evaluation data are determined, the intelligent analysis module determines an analysis result corresponding to the target power distribution station according to the evaluation data. Based on the technical scheme, the problem of low evaluation efficiency in the process of evaluating the health state of the power distribution equipment is solved, and the reliability of the evaluation result is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram of a power distribution equipment health status evaluation system provided according to an embodiment of the present invention;
fig. 2 is a block diagram of a power distribution equipment health status evaluation system according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for evaluating health status of a power distribution device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled 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.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a block diagram of a health status evaluation system of a power distribution device according to an embodiment of the present invention. As shown in fig. 1, the system includes: a data acquisition module 110, a digital twin model configuration module 120, and an intelligent analysis module 130; wherein,
the data acquisition module 110 is configured to acquire device monitoring data corresponding to a target power distribution station, and send the device monitoring data to the digital twin model configuration module 120;
The digital twin model configuration module 120 is configured to configure a digital twin model corresponding to the target power distribution station according to the device monitoring data, and determine evaluation data based on the digital twin model;
the intelligent analysis module 130 is configured to determine an analysis result corresponding to the target substation according to the evaluation data.
The data acquisition module may be a module preset in the target power distribution station and used for acquiring equipment monitoring data of the power distribution station. The target power distribution station may be understood as a power distribution station for which a health status assessment is required, for example, a power distribution station selected by an operation and maintenance person according to the requirement. The device detection data may be data acquired by a sensor provided in the target power distribution station, for example, vibration data acquired by a vibration sensor, image data acquired by an image sensor, temperature data acquired by a temperature sensor, or the like. The digital twin model configuration module may be a module for configuring a digital twin model corresponding to the target substation. The evaluation data may be understood as evaluation data obtained by processing the device detection data. The intelligent analysis module may be a module for health status assessment of the target substation based on the assessment data. The analysis result may be understood as a health status evaluation result corresponding to the target substation, and may be, for example, a fault type, a health status, a health score, an evaluation report, and the like.
Specifically, the device monitoring data corresponding to the target power distribution station is obtained through the data acquisition module, and the device monitoring data is sent to the digital twin model configuration module, so that the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the device monitoring data, and determines the evaluation data based on the digital twin model, so that the intelligent analysis module determines an analysis result corresponding to the target power distribution station based on the evaluation data, intelligent analysis of health evaluation of the power distribution equipment and remote supervision of health condition of the power distribution equipment are realized, manpower and material resources required by health management of the power distribution equipment are reduced, and objectivity and reliability of health management of the power distribution equipment are improved.
On the basis of the technical scheme, the data acquisition module comprises: an environmental information acquisition unit and an equipment information acquisition unit; the device comprises an environment information acquisition unit, a digital twin model configuration module and a device information acquisition unit, wherein the environment information acquisition unit is used for acquiring environment information corresponding to the target power distribution station and sending the environment information to the digital twin model configuration module, and the device information acquisition unit is used for acquiring running state data of each power distribution device in the target power distribution station and sending the running state data to the digital twin model configuration module.
The environmental information may be understood as, among other things, the relevant environmental information of the target substation, including, for example, temperature, humidity, noise, and field images. The operational status data may be operational data of each power distribution device within the target substation, for example, the operational status data includes current voltage, vibration signal, leakage data, magnetic field data.
Specifically, environmental information corresponding to the target power distribution station is collected through each environmental sensor arranged in the target power distribution station, for example, temperature in the transformer substation is collected through a temperature outlet sensor, humidity is collected through a humidity sensor and the like, running state data corresponding to each power transformation device is collected through a sensor arranged on each power transformation device, and after data collection is completed, the collected data is sent to a digital twin model configuration module.
The data acquisition modules are respectively set as an environment information acquisition unit for acquiring environment information of a target power distribution station (such as a power distribution room, a power transmission line, a power plant and the like) and an equipment information acquisition unit for acquiring running state data of power distribution equipment (such as a transformer, a power distribution box, a power transmission line, a power distribution switch and the like), and through multi-dimensional acquisition of the environment information and the running state data, on one hand, real-time and automatic acquisition of monitoring data can be realized, and on the other hand, the accuracy of restoring and monitoring a power distribution field through a digital twin model is facilitated, and the reliability and objectivity of the health state evaluation of the power distribution equipment are improved.
It should be noted that, the data acquisition module may further include a receiving unit and a sending unit, where the receiving unit establishes communication connection with each sensor in the target power distribution station, and is configured to acquire sensor information acquired by each sensor in the target power distribution station, perform security verification on the acquired sensor information, obtain a security verification result, and screen the sensor information based on the security verification result, to obtain device monitoring data. The sending unit is configured to send the device monitoring data to the digital twin model configuration module, and may, for example, transmit the obtained device monitoring data to the digital twin model configuration module by means of 5G communication or Wifi communication.
On the basis of the technical scheme, the digital twin model configuration module comprises: the twin model building unit and the twin model updating unit; the twin model construction unit is used for acquiring substation configuration information corresponding to the target power distribution station and establishing a digital twin model corresponding to the target power distribution station based on the substation configuration information; the twin model updating unit is used for acquiring the equipment monitoring data and updating the digital twin model based on the equipment monitoring data.
The substation configuration information may be configuration information of the target substation in the process of establishing, for example, may be information of a substation name, a substation line, a device configuration, a device number, a substation planning, and the like.
The system comprises a power distribution field digital twin model construction unit, a power distribution field digital twin model generation unit and a power distribution unit, wherein the power distribution field digital twin model construction unit is used for constructing a corresponding power distribution field digital twin model according to the configuration condition of actual power distribution equipment in a power distribution field, the digital twin model comprises power distribution field environment nodes and corresponding power distribution equipment nodes, the power distribution field environment nodes comprise environment parameters, and equipment information corresponding to the power distribution equipment and operation state parameters corresponding to the equipment are arranged in the power distribution nodes; and configuring environmental parameters of the environmental nodes or operating state parameters of the power distribution equipment nodes according to the acquired equipment detection monitoring data.
The twin model construction unit is used for constructing a corresponding distribution field digital twin model according to transformer substation configuration information of actual distribution equipment in a distribution field, configuring environment parameters of distribution field environment nodes in the digital twin model and operation state parameter types of the distribution equipment nodes according to the transformer substation configuration information, pairing corresponding parameters with corresponding data interface information, and analyzing the obtained equipment monitoring data according to the obtained equipment monitoring data and updating operation state parameters of the corresponding distribution field environment nodes or the distribution equipment nodes in the digital twin model according to the interface information of the equipment monitoring data.
On the basis of the technical scheme, the twin model updating unit comprises: an environment information updating subunit and a device information updating subunit; the environment information updating subunit is used for configuring environment nodes in the digital twin model based on environment information; the device information updating subunit is configured to configure the device nodes in the digital twin model based on the operation state data.
Wherein the environmental node may be an environmental simulation node corresponding to the target substation. A plant node may be understood as a plant simulation node corresponding to each distribution plant within a target substation.
Specifically, basic information (such as space division, distribution equipment node setting, distribution equipment basic information input and the like) of the digital twin model is configured through the twin model updating unit, corresponding field environment nodes or distribution equipment nodes are correspondingly configured in the digital twin model according to acquired equipment monitoring information, so that the distribution equipment field is truly displayed, data sources of all the nodes are further configured according to the corresponding relation between the configured nodes and the remote monitoring module, and further acquired equipment information and environment information can be displayed in the digital twin model corresponding to the target distribution station.
On the basis of the technical scheme, the intelligent analysis module further comprises: the system comprises a single-dimensional analysis unit, a multi-dimensional analysis unit and a vibration fault analysis unit, wherein the single-dimensional analysis unit is used for acquiring a standard parameter interval corresponding to evaluation data when the evaluation data are single-dimensional data, and determining an analysis result based on the standard parameter interval and the evaluation data; the multi-dimensional analysis unit is used for acquiring a multi-dimensional analysis model when the evaluation data are multi-dimensional data, and determining the analysis result based on the multi-dimensional analysis model and the evaluation data, wherein the multi-dimensional analysis model is a neural model obtained by training in advance; and the vibration fault analysis unit is used for determining a vibration characteristic vector based on the vibration sequence data when the evaluation data is the vibration sequence data, and determining the analysis result based on the vibration characteristic vector and a vibration analysis model.
The single-dimensional data may be understood as monitoring data of a device, such as a temperature, a voltage value, a current value, etc., which directly obtain an analysis result by comparison. The standard parameter interval may be interval information corresponding to the one-dimensional data. The multi-dimensional data may be understood as data that needs to be processed and analyzed to obtain an analysis result, and may be, for example, image data, audio data, and the like. The multidimensional analytical model can be understood as a neural network model trained in advance. The vibration sequence data may be vibration data corresponding to each of the power distribution devices within the target substation. The vibration feature vector can understand the feature vector i extract from the vibration sequence data.
Specifically, the single-dimensional analysis unit is configured to perform single-dimensional analysis according to the obtained quantifiable distribution field environmental parameter or operation state parameter (such as voltage value, temperature value, leakage data, magnetic field data, and equipment state) of the distribution equipment node, compare the distribution field environmental parameter or operation state parameter with corresponding preset parameter standards, and obtain a single-index health state evaluation result of the distribution equipment as health when the parameter is within the parameter standard range; the multidimensional analysis unit is used for comprehensively analyzing the acquired multiple parameters according to a preset multidimensional health analysis model to obtain a multidimensional health state assessment result, wherein the multidimensional health state assessment result comprises equipment health state ratings; the vibration fault analysis unit is used for carrying out corresponding health state characteristic analysis according to the obtained unquantifiable distribution field environment parameters or the operation state parameters (such as vibration signal sequences) of the distribution equipment nodes, and comprises the following steps: and performing feature extraction according to the obtained feature data sequence (such as the vibration signal sequence), and performing power distribution equipment health state analysis according to the obtained feature data to obtain a feature health state evaluation result of the power distribution equipment.
The method comprises the steps that an exemplary single-dimensional analysis unit firstly analyzes acquired health monitoring data according to the acquired health monitoring data, and firstly acquires corresponding nodes of the health monitoring data, wherein the nodes comprise distribution field environment nodes and distribution equipment nodes; according to the obtained node information, parameter standards corresponding to the node information are called from a configuration database; comparing the type of health monitoring with the corresponding parameter standard, and obtaining a single-index health state evaluation result of the power distribution equipment as health when the parameter is within the parameter standard range; when the parameter exceeds the standard range, marking that the evaluation result of the index health state of the power distribution equipment corresponding to the parameter is abnormal; when the parameter is out of the standard range, the abnormal target health state evaluation result is marked as different abnormal grades according to the out-of-range degree of the parameter.
The multidimensional analysis model is an analysis model constructed based on a CNN neural network, and comprises an input layer, a cache layer, a distribution layer, a convolution layer, an LSTM layer, a full-connection layer and an output layer; the input layer is used for inputting a plurality of (all) acquired health monitoring data into the model; the buffer layer is used for buffering the input health monitoring data respectively; the distribution layer is used for calling corresponding health monitoring data from the cache layer to form a test data packet according to a preset packet rule; the convolution layer comprises a plurality of network structures, wherein each network structure is correspondingly arranged with a corresponding test data packet, the network structure of the convolution layer comprises a plurality of convolution kernels, the feature extraction is carried out on the test data packet, the LSTM layer adopts a bi-LSTM structure, the obtained multidimensional feature data is further processed, and the feature data is predicted; the full-connection layer respectively carries out pooling operation on the characteristic data and the predicted characteristic data obtained according to each test data group, and classifies the characteristic data and the predicted characteristic data based on a relu activation function to obtain single-dimensional health state analysis data obtained according to each test data group; and integrating the output layer according to the single-dimensional health state analysis data to obtain a multi-dimensional health state evaluation result.
The vibration analysis model is of a convolution structure and comprises an input layer, a convolution layer pooling layer and a full connection layer; the input layer acquires a feature vector extracted based on the vibration signal; the convolution layer performs feature extraction on input data through a series of convolution cores, wherein the convolution layer comprises a 4-layer convolution kernel structure, the convolution kernel size of each layer is 1, the number of filters of the 4-layer convolution kernel structure is 64, 32, 16 and 1 in sequence, the output of the convolution layer is set to be single output, a normalization layer is arranged behind each layer of convolution kernel, and the generalization level of the model is improved through the normalization layer; the pooling layer adopts a maximum pooling function to sample the obtained characteristic data; the full connection layer classifies the characteristics obtained in the front, wherein an activation function adopted by the full connection layer is a Softmax activation function, an obtained output result is a classification result ranging from normalization to 0-1, and a corresponding distribution equipment health state analysis result is obtained through the obtained classification result corresponding to a classification boundary obtained based on a training set, wherein the distribution equipment health analysis result comprises normal, abnormal (or specific abnormal classification) and the like.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a signal preprocessing subunit and a signal decomposing subunit; the signal preprocessing subunit is used for carrying out framing sampling on the evaluation data based on a preset sampling step length to determine a vibration signal sequence segment; the signal decomposition subunit is used for performing variation modal decomposition on the vibration signal sequence segment based on a preset decomposition number, and determining each connotation modal component corresponding to the vibration signal sequence segment.
The preset sampling step length may be a preset length value. The preset number of decompositions can be understood as a preset number of decompositions. The decomposition method of the variation mode decomposition can decompose the original signal into a plurality of single-component amplitude modulation and frequency modulation signals. The connotation modal component may be understood as a modal component obtained by decomposing the original signal.
Specifically, the acquired vibration signal in a period of time is sampled in frames to obtain a vibration signal sequence segment Z with a fixed length org (i) Wherein the variable i=1, …, L represents a preset fixed length, Z org (i) Representing the amplitude of the ith sampling point in the vibration signal sequence segment; VMD decomposition is carried out according to the obtained vibration signal sequence segment, and an connotation modal component Z of each decomposition scale of the vibration signal sequence segment is obtained imfk Where k=1, …, K represents the decomposition scale of the VMD, Z imfk Representing an connotation modal component obtained by the kth decomposition scale; the length L of the obtained connotation mode component is the same as that of the original signal sequence segment.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a correlation determination subunit and a signal type determination subunit; the correlation determination subunit is configured to determine a first modal component based on an connotation modal component, and determine a feature correlation between the first modal component and the vibration signal sequence segment; the signal type determining subunit is used for determining the signal type corresponding to the vibration signal sequence section based on the characteristic correlation degree and a preset characteristic threshold value.
The first modal component may be a first modal component obtained by decomposition. The characteristic correlation may be understood as the degree of correlation between the first modal component and the original signal. The preset feature threshold may be a preset feature classification threshold. The signal type may be understood as the type of the original signal, the signal type including a characteristic signal and a variation signal.
Specifically, signal change feature analysis is performed according to the acquired first scale connotation modal component: according to the acquired first scale connotation modal component Z imf1 With vibration signal sequence segment Z org Calculating the feature correlation of the two, wherein the adopted feature correlation calculation function is as follows:
wherein sim (Z imf1 ,Z org ) Representing a characteristic correlation between the first scale content modal component and the vibration signal sequence segment; z is Z imf1 (i) Representing the amplitude value of the ith sampling point in the first scale content modal component, Z imf1 Representing the average amplitude value of each sampling point in the first scale content modal component, Z org (i) Representing the amplitude of the ith sample point in the vibration signal sequence segment,representing the average amplitude of each sample point in the vibration signal sequence segment. Based on the obtained feature correlation sim (Z imf1 ,Z org ) Comparing with a preset variation characteristic threshold value thrsim, if sim (Z imf1 ,Z org )>thrsims, i.e. marking a vibration signal sequence segment as a characteristic signal; otherwise if sim (Z imf1 ,Z org ) The value is less than or equal to thrsims, namely, the vibration signal sequence segment is marked as a change signal; wherein thrsims E [0.2,0.6 ]]。
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a characterization factor determination subunit and a feature vector determination subunit; the characterization factor determining subunit is configured to determine, when the signal type is the characteristic signal, a characterization factor corresponding to each content modality component to be screened based on the characteristic relevance and each content modality component; the feature vector determining subunit is configured to determine at least one to-be-applied content modal component from the to-be-screened content modal components according to the characterization factor, and determine a vibration feature vector based on the to-be-applied content modal component and the first modal component.
Wherein the connotation modal component to be screened is an connotation modal component other than the first modal component. The characterization factor is a numerical value used for characterizing the relativity of each component to be screened and the original signal.
Specifically, for the situation that the vibration signal sequence segment is a characteristic signal, the residual scale connotation modal component Z is further calculated imf2 ,…,Z imfK With vibration signal sequence segment Z org To obtain the characteristic correlation sim (Z) between the content modal component of each scale and the vibration signal sequence segment imf2 ,Z org ),…,sim(Z imfK ,Z org ) The method comprises the steps of carrying out a first treatment on the surface of the Based on the obtained feature correlation sim (Z imf2 ,Z org ),…,sim(Z imfK ,Z org ) And carrying out characteristic component analysis on the 2 nd to K th scale connotation modal components, wherein the adopted characteristic analysis function is as follows: wherein cha (Z) imfk ) Characterization factors representing the k-th scale content modal components, func1 (sim (Z imfk ,Z org ) Thrsim represents the first judgment function, when sim (Z) imfk ,Z org )>At thrsim, func1 (sim (Z imfk ,Z org ) Thrsim) =1; otherwise Func1 (sim (Z) imfk ,Z org ),thrsim)＝0；zro(Z imfk ) And zro (Z) imfk-1 ) The zero crossing rates of the content modal components of the kth scale and the kth-1 scale are respectively represented; thrzro represents a preset zero crossing rate change threshold, where thrzro ε [1.2,2 ]]；Representing a second judgment function when +.>In the time-course of which the first and second contact surfaces,otherwise, when->In the time-course of which the first and second contact surfaces,according to the characterization factors of the content modal components of each scale, the characterization factors cha (Z imfk ) The connotative modal component of =2 is labeled as the feature component; according to the obtained first scale connotation modal component Z imf1 And an connotation modal component Z marked as a feature component imfk Reconstructing to obtain a characteristic signal segment Z chr For example, the feature vector may be obtained by adding the meaning modal component to be applied and the first modal component.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a threshold filtering subunit and a signal reconstruction subunit; the threshold filtering subunit is used for carrying out wavelet decomposition on the vibration signal sequence segment based on a preset wavelet base when the signal type is a change signal, determining a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, carrying out filtering processing based on a preset filtering threshold and the high-frequency wavelet coefficient, and determining a target frequency wavelet coefficient; the signal reconstruction subunit is configured to reconstruct the vibration signal sequence segment based on the target high-frequency wavelet coefficient and the low-frequency wavelet coefficient, and send the reconstructed vibration signal sequence segment to the signal decomposition subunit.
The preset wavelet basis may be a preset wavelet basis function. The high frequency wavelet coefficients may be understood as coefficients for reflecting signal characteristics, such as the broken line waveform of the response characteristic curve. The low frequency wavelet coefficients may be coefficients for representing the degree of fit of the curve.
Specifically, for the case where the vibration signal sequence segment is a change signal, the vibration signal sequence segment Z org And (3) filtering:
the preset wavelet base is adopted to make the vibration signal sequence section Z org A single-scale wavelet decomposition is performed,obtaining the vibration signal sequence section Z org The high-frequency wavelet coefficient and the low-frequency wavelet coefficient of the (2) are subjected to threshold filtering processing for the obtained high-frequency wavelet coefficient, wherein the adopted threshold filtering function is as follows:
wherein e' k And e k Represents the kth high-frequency wavelet coefficient after threshold filtering processing and before threshold filtering processing respectively, and alpha represents a filtering adjustment factor, wherein alpha is E [0.1,0.5 ]]The method comprises the steps of carrying out a first treatment on the surface of the thre represents a set filtering threshold value, and is reconstructed according to the high-frequency wavelet coefficient after filtering and the low-frequency wavelet coefficient obtained by wavelet decomposition to obtain a vibration signal sequence segment Z 'after filtering' org (i) And carrying out variational modal decomposition on the reconstructed vibration signal sequence segment again until a characteristic vector is obtained.
It should be noted that, the technical solution provided in this method embodiment firstly processes the obtained vibration signal sequence segment based on the variation modal decomposition, and according to the law of high-low frequency variation of the obtained features of each scale, particularly, analyzes the overall feature variation of the obtained vibration signal based on the feature correlation degree of the lowest frequency content modal component of the first scale and the original vibration signal sequence segment, when the feature correlation degree of the two is greater than the standard, judges that the current vibration signal sequence segment can extract the feature vector capable of reflecting the signal variation, based on this condition, further obtains the feature correlation degree of the content modal component of other scales, and performs feature component analysis on the content modal component of other scales based on the feature correlation degree, wherein a feature analysis function is specifically provided to characterize the degree of the content modal component of other scales reflecting the variation feature of the vibration signal sequence segment, reserves the content modal component capable of reflecting the feature of the vibration signal sequence segment, discards other content component of high frequency noise, obtains the final feature signal segment, and inputs the feature signal segment as the feature vector into the training fault state failure analysis device according to the feature signal segment, and obtains the fault state analysis result of the fault condition analysis device. Meanwhile, when the feature correlation degree between the lowest frequency content modal component of the first scale and the original vibration signal sequence section is smaller than the standard, the current vibration signal sequence section is judged to be subjected to more noise interference, the signal change characteristic and noise data are mixed, and for the situation, threshold filtering processing based on wavelet decomposition is carried out on the basis of the original vibration signal sequence section as a whole, wherein a threshold filtering function is provided, interference of high-frequency noise can be eliminated under the condition of retaining signal change characteristics, the characterization level of the signal change characteristics is improved, the signal section after threshold filtering is further used as a basis, the feature signal section extraction process of variation modal decomposition is repeated, and finally extracted feature signal sections are obtained to serve as feature vectors to be input into a trained vibration fault abnormal analysis model for further analysis and processing. Based on the technical scheme for extracting the characteristics of the vibration signal data, which is provided by the embodiment, the obtained vibration signal can be subjected to high-low frequency analysis and high-frequency noise removal processing in a self-adaptive manner according to the characteristic change condition of the abnormal characteristics of the power distribution equipment in the actual condition, and corresponding characteristic vectors are further extracted, so that the accuracy and the adaptability of extracting the characteristics of the obtained vibration signal data segment and further analyzing the health state of the power distribution equipment are improved.
According to the technical scheme, the device monitoring data corresponding to the target power distribution station is obtained through the data acquisition module, and the device monitoring data is sent to the digital twin model configuration module, so that the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the device monitoring data, determines evaluation data based on the digital twin model, and when the evaluation data are determined, the intelligent analysis module determines an analysis result corresponding to the target power distribution station according to the evaluation data based on the technical scheme, the problem of low evaluation efficiency in the process of evaluating the health state of the power distribution equipment is solved, and the reliability of the evaluation result is improved.
Example two
Fig. 2 is a block diagram of a health status evaluation system of a power distribution device according to an embodiment of the present invention, where the embodiment is optimized based on the foregoing embodiment, and the power distribution network operation data storage system provided in the embodiment includes: a data acquisition module 210, a digital twin model configuration module 220, and an intelligent analysis module 230; wherein,
the data acquisition module is used for acquiring equipment monitoring data corresponding to the target power distribution station and sending the equipment monitoring data to the digital twin model configuration module;
The digital twin model configuration module is used for configuring a digital twin model corresponding to the target power distribution station according to the equipment monitoring data and determining evaluation data based on the digital twin model;
the intelligent analysis module is used for determining an analysis result corresponding to the target power distribution station according to the evaluation data.
The vibration signal characteristics reflected by the key parts of the power distribution equipment are characteristic signals which change regularly, but when abrasion, dislocation deviation and the like occur to the power distribution equipment, abnormal changes are generated to the vibration signals (the changes are similar to periodic changes, but specific frequencies, amplitudes and the like are abnormal); in practical situations, the vibration signals are interfered by noise in the acquisition and transmission processes, so that the obtained vibration signals contain high-frequency noise interference, and the high-frequency noise interference is easy to cover and influence the abnormal change of the vibration signals under abnormal conditions, so that the accuracy of the analysis result of the health state is influenced when the feature extraction and the further analysis of the health state are carried out according to the vibration signals.
On the basis of the technical scheme, the power distribution equipment health state evaluation system further comprises a visualization module 240, wherein the visualization module 240 is used for integrating the obtained power distribution equipment health state evaluation result into a digital twin model and displaying the updated power distribution field digital twin model; when the health state evaluation result of the power distribution equipment is abnormal, corresponding abnormal prompt information is sent out.
The visual display is performed on the digital twin model of the distribution equipment field through the visual module 240, and the parameters of the environment and each distribution equipment in the distribution equipment field and the health state evaluation result of each distribution equipment are displayed through the digital twin model, so that a manager can intuitively know the condition of the distribution equipment field, and timely conduct investigation and processing on the occurred health abnormal condition, thereby improving the reliability of distribution equipment management.
According to the technical scheme, the device monitoring data corresponding to the target power distribution station is obtained through the data acquisition module, and the device monitoring data is sent to the digital twin model configuration module, so that the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the device monitoring data, determines evaluation data based on the digital twin model, and when the evaluation data are determined, the intelligent analysis module determines an analysis result corresponding to the target power distribution station according to the evaluation data based on the technical scheme, the problem of low evaluation efficiency in the process of evaluating the health state of the power distribution equipment is solved, and the reliability of the evaluation result is improved.
Example III
Fig. 3 is a flow chart of a method for evaluating health status of power distribution equipment according to an embodiment of the present invention. The embodiment is applicable to the situation that health status evaluation is performed on each power distribution device in a power distribution station, and the method can be applied to a power distribution device health status evaluation system, and the power distribution device health status evaluation system can be implemented in a form of hardware and/or software. Specifically, the power distribution equipment health state evaluation system includes: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; the power distribution equipment health state evaluation method comprises the following steps:
s110, acquiring equipment monitoring data corresponding to a target power distribution station through the data acquisition module, and transmitting the equipment monitoring data to the digital twin model configuration module;
s120, the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the equipment monitoring data, and determines evaluation data based on the digital twin model;
and S130, after the evaluation data are determined, the intelligent analysis module determines an analysis result corresponding to the target power distribution station according to the evaluation data.
On the basis of the technical scheme, the intelligent analysis module further comprises: the system comprises a single-dimensional analysis unit, a multi-dimensional analysis unit and a vibration fault analysis unit, wherein the single-dimensional analysis unit is used for acquiring a standard parameter interval corresponding to evaluation data when the evaluation data are single-dimensional data, and determining an analysis result based on the standard parameter interval and the evaluation data; the multi-dimensional analysis unit is used for acquiring a multi-dimensional analysis model when the evaluation data are multi-dimensional data, and determining the analysis result based on the multi-dimensional analysis model and the evaluation data, wherein the multi-dimensional analysis model is a neural model obtained by training in advance; and the vibration fault analysis unit is used for determining a vibration characteristic vector based on the vibration sequence data when the evaluation data is the vibration sequence data, and determining the analysis result based on the vibration characteristic vector and a vibration analysis model.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a signal preprocessing subunit and a signal decomposing subunit; the signal preprocessing subunit is used for carrying out framing sampling on the evaluation data based on a preset sampling step length to determine a vibration signal sequence segment; the signal decomposition subunit is used for carrying out variation modal decomposition on the vibration signal sequence segment based on a preset decomposition number, and determining each intrinsic modal component corresponding to the vibration signal sequence segment.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a correlation determination subunit and a signal type determination subunit; the correlation determination subunit is used for determining a first modal component based on the intrinsic modal component and determining the characteristic correlation between the first modal component and the vibration signal sequence segment; the signal type determining subunit is used for determining the signal type corresponding to the vibration signal sequence section based on the characteristic correlation degree and a preset characteristic threshold value; wherein the signal types include a characteristic signal and a variation signal. The vibration fault analysis unit further includes: a characterization factor determination subunit and a feature vector determination subunit; the characteristic factor determining subunit is configured to determine, when the signal type is the characteristic signal, a characteristic factor corresponding to each eigenmode component to be screened based on the feature correlation degree and each eigenmode component; the eigenvector determining subunit is configured to determine at least one eigenvector to be applied from the eigenvector components to be screened according to the characterization factor, and determine an eigenvector of vibration based on the eigenvector component to be applied and the first modal component, where the eigenvector component to be screened is an eigenvector component other than the first modal component.
On the basis of the technical scheme, the vibration fault analysis unit further comprises: a threshold filtering subunit and a signal reconstruction subunit; the threshold filtering subunit is configured to perform wavelet decomposition on the vibration signal sequence segment on a preset wavelet basis when the signal type is a change signal, determine a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, and perform filtering processing based on a preset filtering threshold and the high-frequency wavelet coefficient to determine a target frequency wavelet coefficient; the signal reconstruction subunit is configured to reconstruct the vibration signal sequence segment based on the target high-frequency wavelet coefficient and the low-frequency wavelet coefficient, and send the reconstructed vibration signal sequence segment to the signal decomposition subunit.
On the basis of the technical scheme, the data acquisition module comprises: an environmental information acquisition unit and an equipment information acquisition unit; the environment information acquisition unit is used for acquiring environment information corresponding to the target power distribution station and sending the environment information to the digital twin model configuration module, wherein the environment information comprises temperature, humidity, noise and field images; the equipment information acquisition unit is used for acquiring the running state data of each power distribution equipment in the target power distribution station and sending the running state data to the digital twin model configuration module, wherein the running state data comprises current and voltage, vibration signals, electric leakage data and magnetic field data.
On the basis of the technical scheme, the digital twin model configuration module comprises: the twin model building unit and the twin model updating unit; the twin model construction unit is used for acquiring substation configuration information corresponding to the target power distribution station and establishing a digital twin model corresponding to the target power distribution station based on the substation configuration information; the twin model updating unit is used for acquiring the equipment monitoring data and updating the digital twin model based on the equipment monitoring data.
On the basis of the technical scheme, the twin model updating unit comprises: an environment information updating subunit and a device information updating subunit; the environment information updating subunit is used for configuring environment nodes in the digital twin model based on environment information; the device information updating subunit is configured to configure the device nodes in the digital twin model based on the operation state data.
According to the technical scheme, the device monitoring data corresponding to the target power distribution station is obtained through the data acquisition module, and the device monitoring data is sent to the digital twin model configuration module, so that the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the device monitoring data, determines evaluation data based on the digital twin model, and when the evaluation data are determined, the intelligent analysis module determines an analysis result corresponding to the target power distribution station according to the evaluation data based on the technical scheme, the problem of low evaluation efficiency in the process of evaluating the health state of the power distribution equipment is solved, and the reliability of the evaluation result is improved.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A power distribution equipment health status assessment system, the system comprising: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; wherein,
the data acquisition module is used for acquiring equipment monitoring data corresponding to the target power distribution station and sending the equipment monitoring data to the digital twin model configuration module;
the digital twin model configuration module is used for configuring a digital twin model corresponding to the target power distribution station according to the equipment monitoring data and determining evaluation data based on the digital twin model;
The intelligent analysis module is used for determining an analysis result corresponding to the target power distribution station according to the evaluation data.
2. The system of claim 1, wherein the intelligent analysis module further comprises: a single-dimensional analysis unit, a multi-dimensional analysis unit and a vibration fault analysis unit, wherein,
the single-dimensional analysis unit is used for acquiring a standard parameter interval corresponding to the evaluation data when the evaluation data are single-dimensional data, and determining the analysis result based on the standard parameter interval and the evaluation data;
the multi-dimensional analysis unit is used for acquiring a multi-dimensional analysis model when the evaluation data are multi-dimensional data, and determining the analysis result based on the multi-dimensional analysis model and the evaluation data, wherein the multi-dimensional analysis model is a neural model obtained by training in advance;
and the vibration fault analysis unit is used for determining a vibration characteristic vector based on the vibration sequence data when the evaluation data is the vibration sequence data, and determining the analysis result based on the vibration characteristic vector and a vibration analysis model.
3. The system of claim 2, the vibration fault analysis unit further comprising: a signal preprocessing subunit and a signal decomposing subunit; wherein,
The signal preprocessing subunit is used for carrying out frame sampling on the evaluation data based on a preset sampling step length to determine a vibration signal sequence segment;
the signal decomposition subunit is used for performing variation modal decomposition on the vibration signal sequence segment based on a preset decomposition number, and determining each connotation modal component corresponding to the vibration signal sequence segment.
4. The system of claim 2, the vibration fault analysis unit further comprising: a correlation determination subunit and a signal type determination subunit; wherein,
the correlation determination subunit is used for determining a first modal component based on the connotation modal component and determining the characteristic correlation between the first modal component and the vibration signal sequence segment;
the signal type determining subunit is used for determining the signal type corresponding to the vibration signal sequence section based on the characteristic correlation degree and a preset characteristic threshold value; wherein the signal types include a characteristic signal and a variation signal.
5. The system of claim 2, the vibration fault analysis unit further comprising: a characterization factor determination subunit and a feature vector determination subunit; wherein,
the characterization factor determining subunit is configured to determine, when the signal type is the characteristic signal, a characterization factor corresponding to each content modality component to be screened based on the feature correlation and each content modality component;
The feature vector determining subunit is configured to determine at least one to-be-applied content modal component from the to-be-screened content modal components according to the characterization factor, and determine a vibration feature vector based on the to-be-applied content modal component and the first modal component, where the to-be-screened content modal component is a content modal component other than the first modal component.
6. The system of claim 2, the vibration fault analysis unit further comprising: a threshold filtering subunit and a signal reconstruction subunit; wherein,
the threshold filtering subunit is used for carrying out wavelet decomposition on the vibration signal sequence segment based on a preset wavelet base when the signal type is a change signal, determining a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, carrying out filtering processing based on a preset filtering threshold and the high-frequency wavelet coefficient, and determining a target frequency wavelet coefficient;
the signal reconstruction subunit is configured to reconstruct the vibration signal sequence segment based on the target high-frequency wavelet coefficient and the low-frequency wavelet coefficient, and send the reconstructed vibration signal sequence segment to the signal decomposition subunit.
7. The system of claim 1, wherein the data acquisition module comprises: an environmental information acquisition unit and an equipment information acquisition unit; wherein,
The environment information acquisition unit is used for acquiring environment information corresponding to the target power distribution station and sending the environment information to the digital twin model configuration module, wherein the environment information comprises temperature, humidity, noise and field images;
the equipment information acquisition unit is used for acquiring the running state data of each power distribution equipment in the target power distribution station and sending the running state data to the digital twin model configuration module, wherein the running state data comprises current and voltage, vibration signals, electric leakage data and magnetic field data.
8. The system of claim 1, wherein the digital twin model configuration module comprises: the twin model building unit and the twin model updating unit; wherein,
the twin model construction unit is used for acquiring substation configuration information corresponding to the target power distribution station and establishing a digital twin model corresponding to the target power distribution station based on the substation configuration information;
the twin model updating unit is used for acquiring the equipment monitoring data and updating the digital twin model based on the equipment monitoring data.
9. The system of claim 8, wherein the twin model update unit comprises: an environment information updating subunit and a device information updating subunit; wherein,
the environment information updating subunit is used for configuring environment nodes in the digital twin model based on environment information;
the device information updating subunit is configured to configure the device nodes in the digital twin model based on the operation state data.
10. A power distribution equipment health state assessment method, characterized by being applied to a power distribution equipment health state assessment system, the power distribution equipment health state assessment system comprising: the system comprises a data acquisition module, a digital twin model configuration module and an intelligent analysis module; the power distribution equipment health state evaluation method comprises the following steps:
acquiring equipment monitoring data corresponding to a target power distribution station through the data acquisition module, and transmitting the equipment monitoring data to the digital twin model configuration module;
the digital twin model configuration module configures a digital twin model corresponding to the target power distribution station according to the equipment monitoring data, and determines evaluation data based on the digital twin model;
Upon determining the evaluation data, the intelligent analysis module determines an analysis result corresponding to the target substation based on the evaluation data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311579720.3A CN117556359A (en) | 2023-11-24 | 2023-11-24 | Power distribution equipment health state evaluation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311579720.3A CN117556359A (en) | 2023-11-24 | 2023-11-24 | Power distribution equipment health state evaluation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117556359A true CN117556359A (en) | 2024-02-13 |
Family
ID=89812437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311579720.3A Pending CN117556359A (en) | 2023-11-24 | 2023-11-24 | Power distribution equipment health state evaluation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117556359A (en) |
-
2023
- 2023-11-24 CN CN202311579720.3A patent/CN117556359A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| CN111242171B (en) | Model training and diagnosis prediction method and device for network faults and electronic equipment | |
| CN106056879B (en) | A kind of ammeter remote monitoring system based on intelligent recognition | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN108880706A (en) | A kind of fast diagnosis method of satellite channel link failure | |
| CN111444233B (en) | Method for discovering environmental monitoring abnormal data based on duplicator neural network model | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN115372816A (en) | Power distribution switchgear operation fault prediction system and method based on data analysis | |
| CN115238785A (en) | Rotary machine fault diagnosis method and system based on image fusion and integrated network | |
| CN117273550B (en) | Information management method of intelligent laboratory for food detection | |
| CN117041312A (en) | Enterprise-level information technology monitoring system based on Internet of things | |
| CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
| CN117556359A (en) | Power distribution equipment health state evaluation system and method | |
| CN116881661A (en) | Performance automatic analysis method and system based on low-voltage power capacitor | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN114625627B (en) | User intelligent perception method based on big data multidimensional analysis | |
| CN114993671A (en) | Vibration fault diagnosis method and system based on Q factor wavelet transform | |
| CN112486096A (en) | Machine tool operation state monitoring method | |
| CN113326728A (en) | Network anomaly detection method based on D-S evidence theory | |
| CN117914003B (en) | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation | |
| CN116993734B (en) | Battery heat insulation cotton cutting quality prediction system based on visual imaging analysis | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |