CN118014564B - Power equipment fault diagnosis system and method based on data driving - Google Patents
Power equipment fault diagnosis system and method based on data driving Download PDFInfo
- Publication number
- CN118014564B CN118014564B CN202410423810.1A CN202410423810A CN118014564B CN 118014564 B CN118014564 B CN 118014564B CN 202410423810 A CN202410423810 A CN 202410423810A CN 118014564 B CN118014564 B CN 118014564B
- Authority
- CN
- China
- Prior art keywords
- node
- fault
- data
- power equipment
- data processing
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 115
- 230000002159 abnormal effect Effects 0.000 claims abstract description 85
- 238000013480 data collection Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 8
- 238000009434 installation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 16
- 238000004804 winding Methods 0.000 description 13
- 238000013528 artificial neural network Methods 0.000 description 10
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000009413 insulation Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004868 gas analysis Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Discrete Mathematics (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to a power equipment fault diagnosis system and method based on data driving, which relates to the technical field of data processing, wherein the system comprises: the data acquisition module comprises a plurality of data acquisition nodes; the node association module is used for establishing a node association map; the fault and node association module is used for establishing a fault and node association map; the fault and feature association module is used for establishing a fault and feature association map; the data processing module comprises a data processing center and a plurality of data processing nodes, wherein the data processing nodes are used for receiving the state data set acquired by each associated data acquisition node, judging whether abnormal data is acquired or not, if yes, marking the abnormal nodes, uploading the state data set to the data processing center, and determining the fault type of the power equipment based on the state data set acquired by each abnormal node, the fault and node association map and the fault and feature association map, thereby having the advantage of improving the efficiency of fault diagnosis of the power equipment.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a power equipment fault diagnosis system and method based on data driving.
Background
After the equipment is in fault (including serious defect and abnormality), a reasonable fault diagnosis method (inspection, test and analysis) is applied to the fault diagnosis of the equipment in the system, the reason and the position of the equipment are distinguished, corresponding treatment measures are provided, along with the continuous construction and development of the power grid, the power equipment is greatly increased, the prediction and the prejudgment of the faults of the important equipment are realized, the diagnosis and the analysis of the possible faults are realized, and the fault diagnosis method is the guarantee of the safe operation of the power grid and is the trend of the development of the intelligent power grid.
In the existing state monitoring and state overhauling system, fault diagnosis of equipment is mainly based on fault tree analysis, topic analysis (such as in-oil gas analysis) is adopted, and aiming at possible fault phenomena, an expert knowledge base is combined to use a diagnosis module to trace out all possible reasons through pushing down layer by layer, so that fault reasons and fault treatment measures possibly causing equipment faults are found out, operation inspection reference bases are provided for professionals, but in recent years, the mode also has defects including excessive listed reasons and insufficient definition of primary and secondary, so that inconvenience and trouble are brought to management, work efficiency is influenced, and safe operation of a power grid is further influenced.
Accordingly, there is a need to provide a data-driven-based power equipment fault diagnosis system and method for improving efficiency of power equipment fault diagnosis.
Disclosure of Invention
One of the embodiments of the present specification provides a data-driven-based power equipment fault diagnosis system, including: the data acquisition module comprises a plurality of data acquisition nodes arranged in the power equipment, wherein different data acquisition nodes are used for acquiring state data sets of different components in the power equipment, and the state data sets comprise multiple types of state data; the node association module is used for establishing a node association graph, wherein the node association graph is used for representing association relations among the plurality of data acquisition nodes; the fault and node association module is used for establishing a fault and node association map, wherein the fault and node association map is used for representing association relations between various fault types and the data acquisition nodes respectively; the fault and feature association module is used for establishing a fault and feature association map, wherein the fault and type association map is used for representing the state data set features of each associated data acquisition node corresponding to each fault type; the data processing module comprises a data processing center and a plurality of data processing nodes, wherein the data processing center is used for determining at least one data acquisition node associated with each data processing node based on the node association graph, the data processing node is used for receiving a state data set acquired by each associated data acquisition node, judging whether the data acquisition node acquires abnormal data, if yes, marking the data acquisition node as the abnormal node, uploading the state data set acquired by the abnormal node to the data processing center, and the data processing center is used for determining the fault type of the power equipment based on the state data set acquired by each abnormal node, the fault and node association graph and the fault and feature association graph.
Still further, the data acquisition module sets the plurality of data acquisition nodes, including: acquiring historical fault data of a plurality of sample power equipment corresponding to the power equipment, wherein the topology structure, application environment information and included fault frequency of each component of the sample power equipment; generating a plurality of training samples based on historical fault data of a plurality of sample power devices corresponding to the power devices; establishing a failure rate determination model, and training the failure rate determination model by using the plurality of training samples; acquiring related information of the power equipment, wherein the related information of the power equipment at least comprises topological structure and application environment information of the power equipment; determining, by the failure rate determination model, a failure probability of each component that the electrical device includes; and determining the installation positions of the plurality of data acquisition nodes and the type of the state data acquired by each data acquisition node based on the fault probability of each component included in the power equipment.
Still further, the node association module establishes a node association graph comprising: acquiring a plurality of fault types corresponding to the power equipment; determining a probability of occurrence of each of the fault types based on a probability of failure of each component included in the power device; determining the association degree between any two data acquisition nodes based on the fault and node association map and the occurrence probability of each fault type; and establishing the node association map based on the association degree between any two data acquisition nodes.
Still further, the fault association module establishes a fault and node association graph, including: acquiring analog data of the power equipment; determining the association degree of each fault type and each data acquisition node based on the simulation data of the power equipment; and establishing a fault and node association map based on the association degree of each fault type and each data acquisition node.
Still further, the fault and feature correlation module establishes a fault and feature correlation map, comprising: and determining the state data set characteristics of each associated data acquisition node corresponding to each fault type based on the simulation data of the power equipment, and establishing a fault and characteristic association map.
Still further, the data processing center is configured to determine the type of the power equipment fault based on the status data set collected by each of the abnormal nodes, the fault-to-node association map, and the fault-to-feature association map, and includes: determining at least one candidate fault type based on a state data set collected by each abnormal node and the fault and node association map; for each candidate fault type, determining a real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on a state data set acquired by each abnormal node associated with the candidate fault type, and determining a fault matching value of the candidate fault type and the power equipment based on the real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment and the fault and feature association map; and determining the fault type of the power equipment based on the fault matching value of each candidate fault type and the power equipment.
Still further, the data processing center determines a real-time status dataset feature of each associated data collection node of the candidate fault type corresponding to the power device based on the status dataset collected by each of the anomaly nodes associated with the candidate fault type, comprising: invoking a joint denoising model corresponding to the candidate fault type to perform joint denoising on state data sets acquired by each abnormal node associated with the candidate fault type, and performing joint denoising on multiple types of state data included in the state data sets acquired by each abnormal node associated with the candidate fault type to generate a denoised state data set acquired by each abnormal node associated with the candidate fault type; and determining the real-time state data set characteristics of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on the state data set acquired by each abnormal node associated with the candidate fault type after denoising.
Furthermore, the data processing node is further configured to send a heartbeat packet to the data processing center according to a preset frequency; the data processing center is used for determining the state of the data processing node based on the heartbeat data packet sent by the data processing node; the data processing center is further used for dynamically adjusting the corresponding relation between the plurality of data acquisition nodes and the plurality of data processing nodes based on the state of the data processing nodes and the node association map.
Further, the data processing center dynamically adjusts the correspondence between the plurality of data collection nodes and the plurality of data processing nodes based on the state of the data processing nodes and the node association graph, including: when the state of the data processing node is an abnormal state, marking the data processing node as an abnormal data processing node; and for each data acquisition node corresponding to the abnormal data processing node, determining a replacement data processing node from the data processing nodes in the normal state based on the node association map and the related information of each data processing node in the normal state, associating the data acquisition node with the replacement data processing node, and disconnecting the association relationship between the data acquisition node and the abnormal data processing node.
One of the embodiments of the present specification provides a data-drive-based power equipment fault diagnosis method, including: providing a plurality of data acquisition nodes in a power device, wherein different data acquisition nodes are used for acquiring state data sets of different components in the power device, and the state data sets comprise at least one type of state data; establishing a node association graph, wherein the node association graph is used for representing association relations among the plurality of data acquisition nodes; establishing a fault and node association graph, wherein the fault and node association graph is used for representing association relations between a plurality of fault types and a plurality of data acquisition nodes respectively; establishing a fault and feature association map, wherein the fault and type association map is used for representing the state data set features of each associated data acquisition node corresponding to each fault type; determining at least one data acquisition node associated with each data processing node based on the node association map; the data processing node receives the state data set collected by each associated data collection node, judges whether the data collection node collects abnormal data, if yes, marks the data collection node as an abnormal node, and uploads the state data set collected by the abnormal node to a data processing center; the data processing center determines the fault type of the power equipment based on the state data set, the fault-node association map and the fault-feature association map which are acquired by each abnormal node.
Compared with the prior art, the power equipment fault diagnosis system and method based on data driving provided by the specification have the following beneficial effects:
1. The distributed acquisition of the state data of the power equipment is realized by arranging the plurality of data acquisition nodes in the power equipment, further, the distributed calculation is realized by arranging the plurality of data processing nodes, the judgment of whether the plurality of data acquisition nodes acquire abnormal data or not can be simultaneously carried out, the real-time performance of the judgment is improved, when the abnormal nodes exist, the data are summarized to the data processing center, and the data processing center can synthesize the state data set acquired by the plurality of abnormal nodes to combine the fault and node association map and the fault and feature association map from higher dimensionality, so that the fault diagnosis of the power equipment can be carried out more accurately;
2. By establishing a fault and node association map, the candidate fault types possibly occurring at present of the power equipment can be determined based on the state data set collected by each abnormal node relatively quickly, the number of fault types needing to be matched is reduced, the subsequent data processing amount is reduced, and on the basis, the fault matching value of the candidate fault types and the power equipment can be determined relatively quickly and accurately based on the real-time state data set characteristics and fault and characteristic association map of each associated data collection node of the candidate fault types corresponding to the power equipment;
3. Based on the node association map and the related information of each data processing node in a normal state, a replacement data processing node is determined from the data processing nodes in the normal state, the data acquisition node is associated with the replacement data processing node, and the association relation between the data acquisition node and the abnormal data processing node is disconnected, so that when part of the data processing nodes are in failure, the state data set acquired by the abnormal nodes can still be uploaded to the data processing center, and the redundancy of data transmission is improved.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a block diagram of a data drive based power equipment fault diagnosis system shown in an embodiment of the present application;
FIG. 2 is a flow chart of a data drive based power device fault diagnosis method in accordance with one embodiment of the present application;
FIG. 3 is a flow chart illustrating the placement of multiple data collection nodes in an embodiment of the present application;
FIG. 4 is a flow chart illustrating the establishment of a node association graph in an embodiment of the present application;
FIG. 5 is a flow chart illustrating a determination of a power device fault type in an embodiment of the present application;
FIG. 6 is a schematic diagram of a failure and node association graph shown in an embodiment of the application;
FIG. 7 is a schematic diagram of a node association graph in accordance with an embodiment of the present application;
FIG. 8 is a schematic diagram of a fault and feature correlation graph shown in an embodiment of the application;
fig. 9 is a schematic diagram showing a technical effect of a data-driven-based power equipment fault diagnosis system according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below.
Fig. 1 is a block diagram of a data-driven-based power equipment fault diagnosis system according to an embodiment of the present application, and as shown in fig. 1, a data-driven-based power equipment fault diagnosis system may include a data acquisition module, a node association module, a fault and feature association module, and a data processing module.
The data collection module may include a plurality of data collection nodes disposed within the power device, wherein different data collection nodes are configured to collect state data sets for different components within the power device, the state data sets including a plurality of types of state data, such as types of temperature, humidity, loop circuitry, return voltage, sound, vibration, and the like.
FIG. 3 is a flow chart illustrating the configuration of a plurality of data collection nodes according to an embodiment of the present application, and as shown in FIG. 3, the data collection module configures the plurality of data collection nodes, including:
acquiring historical fault data of a plurality of sample power equipment corresponding to the power equipment, wherein the topology structure, the application environment information and the fault frequency of each component of the sample power equipment are included;
Generating a plurality of training samples based on historical fault data of a plurality of sample power devices corresponding to the power devices, wherein one training sample can comprise topological structure and application environment information of one sample power device, and a label of the training sample can comprise fault frequency of each component included by the sample power device;
Establishing a fault rate determination model, and training the fault rate determination model by using a plurality of training samples, wherein the fault rate determination model can be a machine learning model such as an artificial neural network (ARTIFICIAL NEURAL NETWORK, ANN) model, a cyclic neural network (Recurrent Neural Networks, RNN) model, a Long Short-Term Memory (LSTM) model, a bidirectional cyclic neural network (BRNN) model and the like;
Acquiring relevant information of the power equipment, wherein the relevant information of the power equipment at least comprises a topological structure and application environment information of the power equipment;
Determining, by the failure rate determination model, a failure probability of each component included in the power equipment based on the related information of the power equipment;
Based on the fault probability of each component included in the power equipment, the installation positions of a plurality of data acquisition nodes and the type of state data acquired by each data acquisition node are determined.
Specifically, a component with the fault probability larger than a preset fault probability threshold is used as a target component, a plurality of target components are clustered based on the topological structure of the power equipment, a plurality of component cluster clusters are determined, and a data acquisition node is arranged for each component cluster. And determining the type of the state data acquired by the data acquisition node according to the type of the abnormal data under each fault of each target component included in each component cluster. For example, the component cluster 1 may have a fault 1 and a fault 2, where when the component cluster 1 has the fault 1, a sound abnormality and a vibration abnormality may occur in the component cluster 1, and when the component cluster 1 has the fault 2, a current abnormality and a temperature abnormality may occur in the component cluster 1, and then the data collection node corresponding to the component cluster 1 may be used to collect sound information, vibration information, current information and temperature information.
The fault and node association module may be configured to establish a fault and node association graph, where the fault and node association graph is configured to characterize association relationships between multiple fault types and multiple data collection nodes, respectively.
In some embodiments, the fault correlation module builds a fault-to-node correlation map comprising:
acquiring analog data of the power equipment;
Determining the association degree of each fault type and each data acquisition node based on the simulation data of the power equipment;
And establishing a fault and node association map based on the association degree of each fault type and each data acquisition node.
Specifically, the degree of association of each fault type with each data collection node may be determined based on the simulation data of the electrical device based on the following formula:
Wherein, For the degree of association of the ith fault type and the jth data acquisition node,For the number of times abnormal data is detected by the jth data acquisition node when the ith fault type occurs in the simulated data, the data is recorded as the data of the jth data acquisition nodeIs the total number of occurrences of the ith fault type in the simulated data.
The fault and node association map may include two types of nodes, where one type of node may represent a fault type, and the other type of node may represent a data collection node, and when the association degree between a certain fault type and a certain data collection node is greater than a first preset association degree threshold, the node corresponding to the fault type and the node corresponding to the data collection node in the fault and node association map may be connected by an edge, where the greater the association degree between the fault type and the data collection node, the shorter the edge between the node corresponding to the fault type and the node corresponding to the data collection node.
The node association module may be configured to establish a node association graph, where the node association graph is used to characterize an association relationship between a plurality of data collection nodes.
The fault and node association graph may include a type of node, with one node in the fault and node association graph representing one data acquisition node.
Fig. 4 is a flowchart illustrating a method for establishing a node association graph according to an embodiment of the present application, where, as shown in fig. 4, a node association module establishes a node association graph, including:
Acquiring a plurality of fault types corresponding to the power equipment;
Determining a probability of occurrence of each fault type based on a probability of failure of each component included in the power device;
determining the association degree between any two data acquisition nodes based on the fault and node association map and the occurrence probability of each fault type;
And establishing a node association map based on the association degree between any two data acquisition nodes.
Specifically, the association degree between any two data acquisition nodes can be determined based on the failure and node association map and the occurrence probability of each failure type through the following formula:
Wherein, For the relevance between the kth data acquisition node and the ith data acquisition node, M is the total number of fault types associated with the kth data acquisition node and the ith data acquisition node simultaneously, and is/areFor the occurrence probability of the m-th fault type in the fault types simultaneously associated with the kth data acquisition node and the first data acquisition node,Is a preset parameter.
When the association degree between any two data acquisition nodes is larger than a second preset association degree threshold value, the nodes corresponding to the two data acquisition nodes in the node association map can be connected through edges, and the larger the association degree between the two data acquisition nodes is, the shorter the edges between the nodes corresponding to the two data acquisition nodes are.
The fault and feature association module may be configured to establish a fault and feature association graph, wherein the fault and type association graph is configured to characterize a state dataset feature of each associated data collection node corresponding to each fault type.
In some embodiments, the fault and feature association module establishes a fault and feature association map comprising: based on the simulation data of the power equipment, determining the state data set characteristics (such as sound characteristics, temperature characteristics, current characteristics, vibration characteristics and the like) of each associated data acquisition node corresponding to each fault type, and establishing a fault and characteristic association map.
The data processing module may include a data processing center and a plurality of data processing nodes, where the data processing center is configured to determine at least one data collection node associated with each data processing node based on a node association graph, the data processing node is configured to receive a status data set collected by each associated data collection node, determine whether the data collection node collects abnormal data, if yes, mark the data collection node as an abnormal node, and upload the status data set collected by the abnormal node to the data processing center, and the data processing center is configured to determine a power equipment fault type based on the status data set, the fault-node association graph, and the fault-feature association graph collected by each abnormal node.
FIG. 5 is a flow chart illustrating a method of determining a power device fault type in accordance with one embodiment of the present application, in some embodiments, a data processing center for determining a power device fault type based on a status data set, a fault-to-node association map, and a fault-to-feature association map collected by each abnormal node, comprising:
determining at least one candidate fault type based on a state data set collected by each abnormal node and a fault and node association map;
for each candidate fault type, determining the real-time state data set characteristics of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on the state data set acquired by each abnormal node associated with the candidate fault type, and determining the fault matching value of the candidate fault type and the power equipment based on the real-time state data set characteristics and the fault and characteristic association map of each associated data acquisition node of the candidate fault type corresponding to the power equipment;
The power device fault type is determined based on the fault match value for each candidate fault type and the power device.
Specifically, the state data set characteristic of each associated data acquisition node corresponding to the candidate fault type can be determined based on the fault and characteristic association map, the cosine similarity between the real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment and the state data set characteristic of each associated data acquisition node corresponding to the candidate fault type is calculated, and the cosine similarity is used as a fault matching value of the candidate fault type and the power equipment.
In some embodiments, a candidate fault type having a fault-match value greater than a preset fault-match value threshold may be considered a current fault type for the power device.
In some embodiments, the data processing center determines a real-time status dataset characteristic of each associated data collection node of the candidate fault type for the power device based on the status dataset collected by each abnormal node associated with the candidate fault type, comprising:
Invoking a joint denoising model corresponding to the candidate fault type to perform joint denoising on state data sets acquired by each abnormal node associated with the candidate fault type, and performing joint denoising on multiple types of state data included in the state data sets acquired by each abnormal node associated with the candidate fault type to generate a state data set acquired by each abnormal node associated with the denoised candidate fault type, wherein the joint denoising model can be a machine learning model such as an artificial neural network (ARTIFICIAL NEURAL NETWORK, ANN) model, a cyclic neural network (Recurrent Neural Networks, RNN) model, a Long Short-Term Memory (LSTM) model, a bidirectional cyclic neural network (BRNN) model and the like, and each candidate fault type corresponds to one joint denoising model;
And determining the real-time state data set characteristics of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on the state data set acquired by each abnormal node associated with the denoised candidate fault type.
The data processing node is further configured to send a heartbeat data packet to the data processing center according to a preset frequency, where the heartbeat data packet may include information such as a temperature, a computational load, a remaining computing resource (e.g., a remaining CPU, a memory) of the data processing node, where the preset frequency may be determined according to the number of determined abnormal nodes, and the more the abnormal nodes, the greater the preset frequency, that is, the shorter a time interval between two heartbeat data packets;
The data processing center is used for determining the state of the data processing node based on the heartbeat data packet sent by the data processing node, for example, if the data processing center exceeds the preset time and does not receive the heartbeat data packet sent by the data processing node, the data processing node can be judged to be in an abnormal state; for another example, when the data processing center determines that the temperature of the data processing node is abnormal, the computational load is greater than a preset load threshold and/or the remaining computing resources are less than a preset remaining computing resource threshold according to the heartbeat data packet of the data processing node, the data processing node may be determined to be in an abnormal state;
the data processing center is also used for dynamically adjusting the corresponding relation between the plurality of data acquisition nodes and the plurality of data processing nodes based on the states of the data processing nodes and the node association patterns.
In some embodiments, the data processing center dynamically adjusts correspondence between the plurality of data collection nodes and the plurality of data processing nodes based on the state of the data processing nodes and the node association graph, including:
when the state of the data processing node is an abnormal state, marking the data processing node as an abnormal data processing node;
For each data acquisition node corresponding to the abnormal data processing node, determining a replacement data processing node from the data processing nodes in the normal state based on the node association map and the related information of each data processing node in the normal state, associating the data acquisition node with the replacement data processing node, and disconnecting the association relationship between the data acquisition node and the abnormal data processing node.
Specifically, the replacement data processing node is determined from the data processing nodes in the normal state based on the node association map and the related information of each data processing node in the normal state through the following flow:
Determining the priority value of each data processing node in a normal state as a replacement data processing node based on the node association map and the related information of each data processing node in the normal state;
The replacement data processing node is determined based on the priority value of each data processing node in the normal state as the replacement data processing node, for example, the data processing node in the normal state with the largest priority value is used as the replacement data processing node.
Further, the priority value of the data processing node in the normal state as the replacement data processing node is determined based on the node association map and the related information of the data processing node in the normal state based on the following formula:
Wherein, For the x-th data processing node in a normal state as a priority value of the replacement data processing node,For the degree of association between the data processing node in the normal state and the abnormal data processing node of the x-th data processing node determined based on the node association map after normalization,For the normalized computing power load of the data processing node with the x < th > in a normal state,For the remaining computing resources of the normalized xth data processing node in the normal state,For the transmission distance between the data of the normalized xth data processing node in the normal state and the abnormal data processing node,、、 All are preset weights.
Specifically, the greater the degree of association between the data processing node in the normal state and the abnormal data processing node determined based on the node association map,The larger the value of (2), the smaller the computational load of the normalized x-th data processing node in a normal state is, i.e.The greater the value of (2), the more computing resources are left for the data processing node in the x-th normal state,The larger the value of (2), the shorter the transmission distance between the data of the xth data processing node in the normal state and the abnormal data processing node is,The greater the value of (2).
A data-driven power equipment fault diagnosis system will be further described below by taking a transformer as an example.
The main components of the transformer are: body (core, winding, insulation and lead); an oil tank and a cooling device; protection devices (oil conservator, safety channel, gas relay, temperature measuring device, breather, explosion-proof pipe, etc.); an insulating sleeve; pressure regulating devices, etc.
The transformer is prone to the following faults:
1. The short circuit fault of the transformer means that the short circuit phenomenon occurs in the iron core or the winding of the transformer, and the transformer is usually stopped immediately;
2. an inter-winding short circuit fault refers to the occurrence of a short circuit between two or more windings of a transformer;
3. Ground faults, which are electrical connections between the winding or core and ground, may be caused by insulation aging, moisture intrusion, operational errors or manufacturing defects;
4. main insulation and turn-to-turn insulation faults of windings are usually caused by long-term use of transformers;
5. and (3) an insulation fault of the iron core.
Therefore, a data acquisition node can be arranged on the components such as the transformer core, the winding and the like.
Fig. 6 is a schematic diagram of a fault and node association diagram in an embodiment of the present application, where, as shown in fig. 6, the fault and node association diagram corresponding to a transformer characterizes association relations between a transformer core, data acquisition nodes set at windings, and various transformer faults.
Fig. 7 is a schematic diagram of a node association diagram in an embodiment of the present application, as shown in fig. 7, the windings and the iron core are easy to affect each other and simultaneously fail, so that a data acquisition node set at a winding position and a data acquisition node set at an iron core position in the node association diagram may be connected through edges, and the windings, the iron core, the protection device, the insulation sleeve, the voltage regulating device and the like have no association relation, and then the data acquisition node set at the winding position and the data acquisition node set at the iron core position in the node association diagram are not connected through edges.
Fig. 8 is a schematic diagram of a fault and characteristic association diagram in an embodiment of the present application, where, as shown in fig. 8, overheating, abnormal current and abnormal noise occur during a short-circuit fault of a transformer, and severe heat generation, torque reduction and abnormal noise occur during an inter-winding short-circuit fault of a transformer.
Fig. 9 is a schematic diagram showing the technical effects of a data-driven power equipment fault diagnosis system according to an embodiment of the present application, in order to verify the superiority of the data-driven power equipment fault diagnosis system according to the present application, a Long Short-Term Memory (LSTM) model is used to perform fault detection directly according to real-time status information of components of a transformer, and a convolutional neural network (Convolutional Neural Networks, CNN) directly performs fault detection according to real-time status information of components of a transformer as a comparison technique to perform a comparison experiment, where the experimental result is shown in fig. 9. According to the experimental result of fig. 9, the fault diagnosis effect of the power equipment fault diagnosis system based on data driving is obviously improved, and the system has obvious leading advantage in Root Mean Square Error (RMSE), and has important significance for improving the fault diagnosis performance of the power equipment.
FIG. 2 is a flow chart of a data-driven-based power device fault diagnosis method that may be performed by a data-driven-based power device fault diagnosis system in some embodiments, in accordance with an embodiment of the present application. As shown in fig. 2, a data-driven-based power equipment fault diagnosis method may include the following steps:
step 210, setting a plurality of data acquisition nodes in the power equipment, wherein different data acquisition nodes are used for acquiring state data sets of different components in the power equipment, and the state data sets comprise at least one type of state data;
step 220, establishing a node association graph, wherein the node association graph is used for representing association relations among a plurality of data acquisition nodes;
Step 230, establishing a fault and node association graph, wherein the fault and node association graph is used for representing association relations between various fault types and a plurality of data acquisition nodes respectively;
Step 240, establishing a fault and feature association map, wherein the fault and type association map is used for representing the state dataset features of each associated data acquisition node corresponding to each fault type;
step 250, determining at least one data acquisition node associated with each data processing node based on the node association map;
Step 260, the data processing node receives the state data set collected by each associated data collection node, judges whether the data collection node collects abnormal data, if yes, marks the data collection node as an abnormal node, and uploads the state data set collected by the abnormal node to the data processing center;
step 270, the data processing center determines the fault type of the electrical equipment based on the status data set, the fault-to-node association map, and the fault-to-feature association map collected by each abnormal node.
For further description of a data-driven-based power device fault diagnosis method, reference may be made to fig. 1 and its related description, and further description is omitted herein.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (8)
1. A data-driven-based power equipment fault diagnosis system, comprising:
The data acquisition module comprises a plurality of data acquisition nodes arranged in the power equipment, wherein different data acquisition nodes are used for acquiring state data sets of different components in the power equipment, and the state data sets comprise multiple types of state data;
The node association module is used for establishing a node association graph, wherein the node association graph is used for representing association relations among the plurality of data acquisition nodes;
The fault and node association module is used for establishing a fault and node association map, wherein the fault and node association map is used for representing association relations between various fault types and the data acquisition nodes respectively;
The fault and feature association module is used for establishing a fault and feature association map, wherein the fault and feature association map is used for representing the state data set features of each associated data acquisition node corresponding to each fault type, and specifically comprises the following steps: based on the simulation data of the power equipment, determining the state data set characteristics of each associated data acquisition node corresponding to each fault type, and establishing a fault and characteristic association map;
The data processing module comprises a data processing center and a plurality of data processing nodes, wherein the data processing center is used for determining at least one data acquisition node associated with each data processing node based on the node association graph, the data processing node is used for receiving a state data set acquired by each associated data acquisition node, judging whether the data acquisition node acquires abnormal data, if yes, marking the data acquisition node as an abnormal node, uploading the state data set acquired by the abnormal node to the data processing center, and the data processing center is used for determining the type of the power equipment fault based on the state data set acquired by each abnormal node, the fault and node association graph and the fault and feature association graph;
the data processing center determines the type of the power equipment fault based on the state data set, the fault-node association map and the fault-feature association map acquired by each abnormal node, and the method comprises the following steps:
Determining at least one candidate fault type based on a state data set collected by each abnormal node and the fault and node association map;
For each candidate fault type, determining a real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on a state data set acquired by each abnormal node associated with the candidate fault type, and determining a fault matching value of the candidate fault type and the power equipment based on the real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment and the fault and feature association map;
and determining the fault type of the power equipment based on the fault matching value of each candidate fault type and the power equipment.
2. The data-driven power equipment fault diagnosis system according to claim 1, wherein the data acquisition module sets the plurality of data acquisition nodes, comprising:
acquiring historical fault data of a plurality of sample power equipment corresponding to the power equipment, wherein the topology structure, application environment information and included fault frequency of each component of the sample power equipment;
generating a plurality of training samples based on historical fault data of a plurality of sample power devices corresponding to the power devices;
Establishing a failure rate determination model, and training the failure rate determination model by using the plurality of training samples;
Acquiring related information of the power equipment, wherein the related information of the power equipment at least comprises topological structure and application environment information of the power equipment;
Determining, by the failure rate determination model, a failure probability of each component that the electrical device includes;
And determining the installation positions of the plurality of data acquisition nodes and the type of the state data acquired by each data acquisition node based on the fault probability of each component included in the power equipment.
3. The data-driven power equipment fault diagnosis system according to claim 2, wherein the node association module establishes a node association map, comprising:
Acquiring a plurality of fault types corresponding to the power equipment;
determining a probability of occurrence of each of the fault types based on a probability of failure of each component included in the power device;
Determining the association degree between any two data acquisition nodes based on the fault and node association map and the occurrence probability of each fault type;
And establishing the node association map based on the association degree between any two data acquisition nodes.
4. A data drive based power equipment fault diagnosis system according to claim 3, wherein said fault and node association module establishes a fault and node association map comprising:
acquiring analog data of the power equipment;
determining the association degree of each fault type and each data acquisition node based on the simulation data of the power equipment;
and establishing a fault and node association map based on the association degree of each fault type and each data acquisition node.
5. A data-driven power equipment fault diagnosis system according to claim 1, wherein the data processing center determines real-time status data set characteristics of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on status data sets acquired by each of the abnormal nodes associated with the candidate fault type, comprising:
Invoking a joint denoising model corresponding to the candidate fault type to perform joint denoising on state data sets acquired by each abnormal node associated with the candidate fault type, and performing joint denoising on multiple types of state data included in the state data sets acquired by each abnormal node associated with the candidate fault type to generate a denoised state data set acquired by each abnormal node associated with the candidate fault type;
And determining the real-time state data set characteristics of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on the state data set acquired by each abnormal node associated with the candidate fault type after denoising.
6. The data-driven power equipment fault diagnosis system according to any one of claims 1 to 4, wherein the data processing node is further configured to send heartbeat packets to the data processing center at a preset frequency;
the data processing center is used for determining the state of the data processing node based on the heartbeat data packet sent by the data processing node;
The data processing center is further used for dynamically adjusting the corresponding relation between the plurality of data acquisition nodes and the plurality of data processing nodes based on the state of the data processing nodes and the node association map.
7. The data-driven power equipment fault diagnosis system according to claim 6, wherein the data processing center dynamically adjusts correspondence between the plurality of data collection nodes and the plurality of data processing nodes based on the states of the data processing nodes and the node association map, comprising:
when the state of the data processing node is an abnormal state, marking the data processing node as an abnormal data processing node;
And for each data acquisition node corresponding to the abnormal data processing node, determining a replacement data processing node from the data processing nodes in the normal state based on the node association map and the related information of each data processing node in the normal state, associating the data acquisition node with the replacement data processing node, and disconnecting the association relationship between the data acquisition node and the abnormal data processing node.
8. A data-driven-based power equipment fault diagnosis method, comprising:
Providing a plurality of data acquisition nodes in a power device, wherein different data acquisition nodes are used for acquiring state data sets of different components in the power device, and the state data sets comprise at least one type of state data;
establishing a node association graph, wherein the node association graph is used for representing association relations among the plurality of data acquisition nodes;
establishing a fault and node association graph, wherein the fault and node association graph is used for representing association relations between a plurality of fault types and a plurality of data acquisition nodes respectively;
Establishing a fault and feature association map, wherein the fault and feature association map is used for representing the state data set features of each associated data acquisition node corresponding to each fault type, and specifically comprises the following steps: based on the simulation data of the power equipment, determining the state data set characteristics of each associated data acquisition node corresponding to each fault type, and establishing a fault and characteristic association map;
Determining at least one data acquisition node associated with each data processing node based on the node association map;
The data processing node receives the state data set collected by each associated data collection node, judges whether the data collection node collects abnormal data, if yes, marks the data collection node as an abnormal node, and uploads the state data set collected by the abnormal node to a data processing center;
The data processing center determines the fault type of the power equipment based on a state data set, the fault-node association map and the fault-feature association map which are acquired by each abnormal node;
The determining the fault type of the power equipment based on the state data set, the fault-node association map and the fault-feature association map acquired by each abnormal node comprises the following steps:
Determining at least one candidate fault type based on a state data set collected by each abnormal node and the fault and node association map;
For each candidate fault type, determining a real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment based on a state data set acquired by each abnormal node associated with the candidate fault type, and determining a fault matching value of the candidate fault type and the power equipment based on the real-time state data set characteristic of each associated data acquisition node of the candidate fault type corresponding to the power equipment and the fault and feature association map;
and determining the fault type of the power equipment based on the fault matching value of each candidate fault type and the power equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410423810.1A CN118014564B (en) | 2024-04-10 | 2024-04-10 | Power equipment fault diagnosis system and method based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410423810.1A CN118014564B (en) | 2024-04-10 | 2024-04-10 | Power equipment fault diagnosis system and method based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118014564A CN118014564A (en) | 2024-05-10 |
| CN118014564B true CN118014564B (en) | 2024-06-25 |
Family
ID=90950412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410423810.1A Active CN118014564B (en) | 2024-04-10 | 2024-04-10 | Power equipment fault diagnosis system and method based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118014564B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118889924B (en) * | 2024-07-10 | 2025-02-07 | 武汉麦迪嘉机电科技有限公司 | Permanent magnet synchronous motor comprehensive control method and system based on inverter |
| CN119921477B (en) * | 2025-04-01 | 2025-06-24 | 南京工程学院 | Intelligent substation real-time monitoring system and method based on big data |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313845A (en) * | 2023-08-31 | 2023-12-29 | 慧之安信息技术股份有限公司 | Power grid fault detection auxiliary method and system based on knowledge graph |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6442542B1 (en) * | 1999-10-08 | 2002-08-27 | General Electric Company | Diagnostic system with learning capabilities |
| CN103996077B (en) * | 2014-05-22 | 2018-01-05 | 中国南方电网有限责任公司电网技术研究中心 | Electrical equipment fault prediction method based on multi-dimensional time sequence |
| US10676048B2 (en) * | 2018-10-18 | 2020-06-09 | Northrop Grumman Systems Corporation | Parametric data modeling for model based reasoners |
| CN114765451A (en) * | 2021-01-14 | 2022-07-19 | 新智数字科技有限公司 | Photovoltaic power station fault detection method based on fault knowledge graph |
| CN112990551A (en) * | 2021-02-20 | 2021-06-18 | 国电南瑞科技股份有限公司 | Cascading failure evolution path tracing and predicting method and device based on knowledge graph |
| CN114138982B (en) * | 2021-12-02 | 2024-07-19 | 华北电力大学（保定） | Knowledge graph construction method for fault diagnosis of dry-type transformer |
| CN114692875B (en) * | 2022-04-12 | 2024-09-13 | 华北电力大学 | Construction method of GIS knowledge graph for fault diagnosis |
| CN116975566A (en) * | 2023-07-27 | 2023-10-31 | 内蒙古电力(集团)有限责任公司乌海供电分公司 | Intelligent transformer monitoring system and method based on multi-source parameter analysis and diagnosis |
| CN117350377A (en) * | 2023-09-22 | 2024-01-05 | 辽宁科技大学 | An equipment fault diagnosis method and device driven by knowledge graph |
| CN117406689A (en) * | 2023-10-13 | 2024-01-16 | 中国电子科技集团公司第十四研究所 | Data driving and knowledge guiding fault diagnosis method and system |
| CN117810970A (en) * | 2023-12-13 | 2024-04-02 | 广西电网有限责任公司 | Power grid accident recovery method and system with main network self-starting function |
| CN117633694A (en) * | 2023-12-26 | 2024-03-01 | 国家电网有限公司客户服务中心 | Deep reinforcement learning-based maintenance detection method and system for power equipment |
-
2024
- 2024-04-10 CN CN202410423810.1A patent/CN118014564B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313845A (en) * | 2023-08-31 | 2023-12-29 | 慧之安信息技术股份有限公司 | Power grid fault detection auxiliary method and system based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118014564A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118014564B (en) | Power equipment fault diagnosis system and method based on data driving | |
| CN103616579B (en) | A Fault Diagnosis Method for Secondary System of Smart Substation | |
| CN117909906B (en) | Power line fault prediction system and method based on prediction model | |
| CN117110798A (en) | Fault detection method and system for intelligent power distribution network | |
| CN118101429B (en) | A method and system for diagnosing communication faults in a distribution network | |
| CN118367672A (en) | Intelligent remote monitoring method for power equipment | |
| CN119667370A (en) | Real-time fault detection and automatic repair system for power grid | |
| CN119199367B (en) | Fault Identification Method for Shunt Capacitors and Series Reactors Based on Parameter Characteristic Analysis | |
| CN114838923B (en) | Fault diagnosis model building method and fault diagnosis method for on-load tap-changer | |
| CN113740666B (en) | A method for locating root faults of alarm storm in data center power system | |
| CN118432710B (en) | Method for reporting fault of optical fiber communication link | |
| CN119374756A (en) | A power transmission equipment fault monitoring system based on optical fiber sensor | |
| CN118070029B (en) | Distribution transformer equipment fault identification system and method | |
| CN109191006A (en) | A kind of method of 110 kV main transformer N-1 risk automatically scanning of power grid analysis | |
| CN118209905A (en) | An online fault prediction method for distribution transformers based on IoT perception | |
| CN117134490A (en) | Cloud platform-based intelligent surge protector monitoring system and method | |
| CN111913135B (en) | Method for identifying deformation faults of transformer winding by Newton iteration method | |
| CN114123510A (en) | Transformer monitoring method and system based on real-time data analysis | |
| CN119619735B (en) | A method for identifying faulty sections and faulty branches of wind farm collector lines | |
| CN119125969B (en) | Method for detecting turn-to-turn short circuit fault of power transformer winding | |
| CN116777430A (en) | Novel power system-oriented line loss positioning analysis method | |
| Shi et al. | A Method for Evaluating the Status of Converter Valves Based on Siam-LSTM Neural Network | |
| CN119619730A (en) | Fault distance calculation method and system for power system distribution network | |
| CN116169788A (en) | Distribution network communication management system based on Internet of things | |
| CN119696158A (en) | Monitoring and adaptive strategy adjustment method of distribution network self-healing line and related device |
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 |