CN116703852A - Power grid overhaul risk early warning method and system - Google Patents
Power grid overhaul risk early warning method and system Download PDFInfo
- Publication number
- CN116703852A CN116703852A CN202310639761.0A CN202310639761A CN116703852A CN 116703852 A CN116703852 A CN 116703852A CN 202310639761 A CN202310639761 A CN 202310639761A CN 116703852 A CN116703852 A CN 116703852A
- Authority
- CN
- China
- Prior art keywords
- image
- model
- fault
- substation equipment
- power grid
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000010276 construction Methods 0.000 claims description 61
- 238000012549 training Methods 0.000 claims description 41
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 14
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004913 activation Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000004643 material aging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model provides a power grid overhaul risk early warning method and system, which adopts an anomaly identification model to realize the rapid identification of scene image anomalies of possible faults on the power grid site, and can improve the efficiency and accuracy of scene image anomaly identification on the site; the fault pre-judging model is utilized to realize the pre-judging of possible faults, and meanwhile, the established fault maintenance database is utilized to guide the power grid maintenance department to rapidly develop risk pre-control, so that the labor intensity of foundation fault maintenance staff can be reduced, the power grid fault recognition processing period is shortened, and the continuous and stable operation of city production life is ensured.
Description
Technical Field
The disclosure relates to the technical field of power grid overhaul, in particular to a power grid overhaul risk early warning method and system, a storage medium and equipment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Both the development of the power grid and the social progress put higher demands on the operation of the power grid, and the enhancement of the diagnosis and treatment of the power grid faults is particularly important. The power system consists of a generator, a transformer, a bus, a power transmission and distribution line and electric equipment. The electrical components and systems are typically in normal operation, but may also fail or be in abnormal operation. Along with the increasing scale of the power system, the structure is more and more complex, faults are unavoidable, in the whole power production process, the most frequent and serious faults are short-circuit faults, the reasons for the short-circuit faults are ageing or mechanical damage of insulating materials of electric equipment, overvoltage is caused by lightning strike, pole tower grounding or wire breakage is caused by natural disasters, short circuit is caused by bridging wires of birds and beasts, misoperation of operators is caused, and the like, so that new problems are brought to safe operation of the power system.
The existing power system reports the site situation by the operator on duty after the fault occurs, then the operator who receives the maintenance task obtains fault sign information from some detection amounts of the analyzed area, and the early information is analyzed and processed to judge the specific position of the fault according to the signal of the protection action, so that some simple faults of the fault occurrence area are identified, and further maintenance is performed. The process circulation period is long, and maintenance personnel are required to have rich maintenance experience; because the maintenance is carried out after the system fault occurs, the production and life of the city are seriously affected.
Disclosure of Invention
In order to solve the defects of the prior art, the disclosure provides a power grid overhaul risk early warning method and a system, which adopt an anomaly identification model to realize the rapid identification of scene image anomalies which possibly generate faults on a power grid site, further utilize the fault pre-judgment model to realize the advanced pre-judgment of the possible faults, and simultaneously utilize an established fault overhaul database to further guide a power grid overhaul department to rapidly develop risk pre-control, shorten a power grid fault identification processing period and ensure the continuous and stable operation of urban production life.
According to some embodiments, the present disclosure employs the following technical solutions:
the first aspect of the disclosure provides a power grid overhaul risk early warning method.
A power grid overhaul risk early warning method comprises the following steps:
acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; preprocessing the substation equipment image, the cable rod image and the worker construction image;
performing anomaly identification processing on the preprocessed substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image;
acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
according to the obtained pre-judging fault category, a corresponding risk pre-control scheme is called from a fault overhaul database and is transmitted to a related overhaul department;
as a further limitation, the substation equipment image, the cable pole image and the worker construction image in the target area are obtained by using high-definition camera monitoring equipment;
as a further limitation, the preprocessing of the substation equipment image, the cable pole image, and the worker construction image specifically includes: sequentially carrying out size unification, pixel processing and overturning processing on the images;
as a further limitation, training an anomaly identification model by using a deep learning network model before the anomaly identification according to the substation equipment image, the cable pole image and the worker construction image is completed and possible fault conditions and solutions are output, and establishing a unified anomaly identification model;
as a further limitation, before the abnormal recognition based on the substation equipment image, the cable pole image, and the worker construction image is completed by using the abnormal recognition model, a sample library of the substation equipment image, the cable pole image, and the worker construction image for a plurality of abnormal situation images is constructed;
as a further limitation, the training process of the anomaly identification model includes: acquiring a substation equipment image, a cable rod image and a current mapping label corresponding to a worker construction image and a training label of the image; inputting the substation equipment image and the cable pole image into an initial anomaly identification model to obtain a target prediction label corresponding to the substation equipment image, the cable pole image and the construction image of staff; generating model feedback data based on the substation equipment image, the cable pole image and the current mapping label and the target prediction label corresponding to the training label of the working personnel construction image; generating tag loss based on data change reference information corresponding to the model feedback data, adjusting a current mapping tag based on the tag loss to obtain an updated mapping tag, and taking the updated mapping tag as the current mapping tag; adjusting model parameters of an initial abnormal recognition model based on the model feedback data to obtain an updated initial abnormal recognition model, and returning to the step of inputting the substation equipment image, the cable rod image and the worker construction image into the initial abnormal recognition model until training is completed to obtain an abnormal recognition model;
as a further limitation, the structure of the initial anomaly identification model mainly comprises an input convolution module, an encoder part, a common convolution module, a decoder part and an output layer which are sequentially connected, wherein the encoder part mainly comprises a plurality of downsampling modules, the decoder part comprises a plurality of upsampling modules, and the input convolution module and the common convolution module are sequentially connected by a convolution layer, a batch normalization processing layer and a Relu activation function layer; the decoder portion restores detail and spatial information of the image by upsampling; the downsampling module extracts the image features by adopting convolution cores with different sizes to achieve the purpose of downsampling;
as a further limitation, acquiring historical image data corresponding to the fault, and establishing a power grid fault pre-judging model according to the historical image data corresponding to the fault;
as a further limitation, the power grid fault pre-judging model is constructed based on a res net50 network structure and consists of 4 convolution layer groups, 1 full connection layer and 1 Softmax layer; wherein, a single convolution layer group comprises a plurality of continuous convolution layers and 1 max pooling layer, and the aim is to extract effective image characteristic diagram;
as a further limitation, the training process of the grid fault pre-judging model includes: taking the obtained historical image data corresponding to the faults as training samples, and setting the fault historical image data corresponding to the corresponding fault types; taking the training samples as input parameters of the power grid fault pre-judging model, taking the fault types as output parameters of the power grid fault pre-judging model respectively, and training the power grid fault recognition model;
a second aspect of the present disclosure provides a grid overhaul risk early warning system.
A grid overhaul risk early warning system, comprising:
an image acquisition module configured to: acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; preprocessing the substation equipment image, the cable rod image and the worker construction image;
an anomaly identification module configured to: performing anomaly identification processing on the substation equipment image, the cable rod image and the worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the cable rod image and the worker construction image;
a failure pre-determination module configured to: acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
a risk pre-control module configured to: and according to the obtained predicted fault category, a corresponding risk pre-control scheme is called from the fault overhaul database and is transmitted to related overhaul departments.
A third aspect of the present disclosure provides a computer readable storage medium having stored thereon a program which when executed by a processor implements steps in a grid overhaul risk early warning method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor implements the steps in a grid overhaul risk early warning method according to the first aspect of the present disclosure when the program is executed.
Compared with the prior art, the beneficial effects of the present disclosure are:
the scene image anomaly possibly generating faults on the power grid site is rapidly identified by adopting the anomaly identification model, so that the efficiency and the accuracy of scene image anomaly identification on the site can be improved; the fault pre-judging model is utilized to realize the pre-judging of possible faults, and meanwhile, the established fault maintenance database is utilized to guide the power grid maintenance department to rapidly develop risk pre-control, so that the labor intensity of foundation fault maintenance staff can be reduced, the power grid fault recognition processing period is shortened, and the continuous and stable operation of city production life is ensured.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
Fig. 1 is a flowchart of a power grid overhaul risk early warning method provided in embodiment 1 of the present disclosure;
FIG. 2 is a flowchart of an anomaly identification model training process provided in embodiment 1 of the present disclosure;
the specific embodiment is as follows:
the disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1:
as shown in fig. 1, this embodiment 1 provides a power grid overhaul risk early warning method and system, which acquires a substation equipment image, a cable pole image, and a worker construction image in a target area and performs preprocessing, and adopts an anomaly recognition model to realize rapid recognition of scene image anomalies that may generate faults on a power grid site, further uses a fault pre-judgment model to realize early pre-judgment of the possible faults, and simultaneously uses an established fault overhaul database to further guide a power grid overhaul department to rapidly develop risk pre-control.
Specifically, the method comprises the following steps:
s1: image acquisition
Acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; the substation equipment image, the cable rod image and the worker construction image in the target area are acquired by using high-definition camera monitoring equipment;
s2: pretreatment of
Preprocessing the substation equipment image, the cable rod image and the worker construction image; preprocessing a substation equipment image, a cable pole image and a worker construction image, wherein the preprocessing of the substation equipment image, the cable pole image and the worker construction image comprises the steps of sequentially carrying out size unification, pixel processing and overturning processing on the images;
the method specifically comprises the following steps: scaling all the images to a uniform size; calculating the pixel average value of the images, and respectively subtracting the average value from each image; cutting out an image block with a fixed size from a random position of an image during each training iteration, and horizontally overturning the image block with a certain probability;
s3: image anomaly identification
Performing anomaly identification processing on the preprocessed substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image;
the anomaly identification model construction process based on deep learning comprises the following steps:
s3.1: constructing a substation equipment image, a cable rod image and a sample library of a plurality of abnormal condition images of a worker construction image;
the sample library is divided into three types of substation equipment, a wire rod cable and staff construction, and typical samples of normal and abnormal states of the substation equipment and the wire rod cable and typical samples of normal operation and violation operation of the staff construction are collected; the abnormal state of the transformer substation equipment comprises the state of equipment insulation material aging, mechanical damage and the like; the abnormal states of the cable rod comprise the states of cable rod deflection, surface crack, cable surface damage, loose suspension, beast stay, thunder and typhoon weather environment and the like; the staff construction violation operation comprises states of inaccurate operation mode, nonstandard using tools and the like;
s3.2: constructing an initial anomaly identification model;
the structure of the initial anomaly identification model mainly comprises an input convolution module, an encoder part, a common convolution module, a decoder part and an output layer which are sequentially connected, wherein the encoder part mainly comprises a plurality of downsampling modules, the decoder part comprises a plurality of upsampling modules, and the input convolution module and the common convolution module are sequentially connected by a convolution layer, a batch normalization processing layer and a Relu activation function layer; the decoder portion restores detail and spatial information of the image by upsampling; the downsampling module extracts the image features by adopting convolution cores with different sizes to achieve the purpose of downsampling;
s3.3: training an anomaly identification model by using the deep learning network model, and establishing a unified anomaly identification model;
the training process of the anomaly identification model comprises the following steps:
(1) Acquiring a substation equipment image, a cable rod image and a current mapping label corresponding to a worker construction image and a training label of the image;
(2) Inputting the substation equipment image and the cable pole image into an initial anomaly identification model to obtain a target prediction label corresponding to the substation equipment image, the cable pole image and the construction image of staff;
(3) Generating model feedback data based on the substation equipment image, the cable pole image and the current mapping label and the target prediction label corresponding to the training label of the working personnel construction image;
(4) Generating tag loss based on data change reference information corresponding to the model feedback data, adjusting a current mapping tag based on the tag loss to obtain an updated mapping tag, and taking the updated mapping tag as the current mapping tag;
(5) Adjusting model parameters of an initial abnormality recognition model based on the model feedback data to obtain an updated initial abnormality recognition model, and returning to the steps of inputting the initial abnormality recognition model by the substation equipment image, the cable pole image and the construction image of the staff until training is completed to obtain an abnormality recognition model;
s4: power grid fault pre-judgment
Acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
the fault types comprise three-phase short circuit, two-phase grounding short circuit and single-phase grounding short circuit faults;
the anomaly identification model construction process based on deep learning comprises the following steps:
acquiring historical image data corresponding to a fault, and establishing a power grid fault pre-judging model according to the historical image data corresponding to the fault;
the power grid fault pre-judging model is constructed based on a ResNet50 network structure and consists of 4 convolution layer groups, 1 full-connection layer and 1 Softmax layer; wherein, a single convolution layer group comprises a plurality of continuous convolution layers and 1 max pooling layer, and the aim is to extract effective image characteristic diagram;
the training process of the power grid fault pre-judging model comprises the following steps: taking the obtained historical image data corresponding to the faults as training samples, and setting the fault historical image data corresponding to the corresponding fault types; taking the training samples as input parameters of the power grid fault pre-judging model, taking the fault types as output parameters of the power grid fault pre-judging model respectively, and training the power grid fault recognition model;
s5: risk pre-control
According to the obtained pre-judging fault category, a corresponding risk pre-control scheme is called from a fault overhaul database and is transmitted to a related overhaul department;
in the embodiment, the rapid identification of scene image anomalies which possibly generate faults on the power grid site is realized by adopting the anomaly identification model, and the efficiency and the accuracy of scene image anomaly identification on the site are improved; the fault pre-judging model is utilized to realize the pre-judging of possible faults, and meanwhile, the established fault maintenance database is utilized to guide the power grid maintenance department to rapidly develop risk pre-control, so that the labor intensity of a foundation fault maintenance worker is reduced, the power grid fault recognition processing period is shortened, and the continuous and stable operation of urban production life is ensured.
Example 2:
embodiment 2 of the present disclosure provides a power grid overhaul risk early warning system, including:
an image acquisition module configured to: acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; preprocessing the substation equipment image, the cable rod image and the worker construction image;
an anomaly identification module configured to: performing anomaly identification processing on the substation equipment image, the cable rod image and the worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the cable rod image and the worker construction image;
a failure pre-determination module configured to: acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
a risk pre-control module configured to: according to the obtained pre-judging fault category, a corresponding risk pre-control scheme is called from a fault overhaul database and is transmitted to a related overhaul department;
the working method of the system is the same as that of the power grid overhaul risk early warning method provided in embodiment 1, and is not repeated here.
Example 3:
embodiment 3 of the present disclosure provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements steps in a grid overhaul risk early warning method as described in embodiment 1 of the present disclosure.
Example 4:
embodiment 5 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor implements steps in a grid overhaul risk early warning method according to embodiment 1 of the present disclosure when executing the program.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the specific embodiments of the present disclosure have been described above with reference to the drawings, it should be understood that the present disclosure is not limited to the embodiments, and that various modifications and changes can be made by one skilled in the art without inventive effort on the basis of the technical solutions of the present disclosure while remaining within the scope of the present disclosure.
Claims (10)
1. The utility model provides a power grid overhaul risk early warning method which is characterized by comprising the following steps:
acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; preprocessing the substation equipment image, the cable rod image and the worker construction image;
performing anomaly identification processing on the preprocessed substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the preprocessed cable rod image and the preprocessed worker construction image;
acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
and according to the obtained predicted fault category, a corresponding risk pre-control scheme is called from the fault overhaul database and is transmitted to related overhaul departments.
2. The grid overhaul risk early warning method according to claim 1, wherein training of an abnormality recognition model is performed by using a deep learning network model before abnormality recognition according to a substation equipment image, a cable pole image and a worker construction image is completed by using the abnormality recognition model, and possible fault conditions and solutions are output, so that a unified abnormality recognition model is established.
3. The grid overhaul risk early warning method according to claim 2, wherein a sample library of a plurality of abnormal condition images of the substation equipment image, the cable pole image, and the worker construction image is constructed before abnormal recognition according to the substation equipment image, the cable pole image, and the worker construction image is completed by using the abnormal recognition model, and possible fault conditions and solutions are output.
4. The grid overhaul risk early warning method according to claim 2, wherein the training process of the anomaly identification model comprises:
acquiring a substation equipment image, a cable rod image and a current mapping label corresponding to a worker construction image and a training label of the image;
inputting the substation equipment image and the cable pole image into an initial anomaly identification model to obtain a target prediction label corresponding to the substation equipment image, the cable pole image and the construction image of staff;
generating model feedback data based on the substation equipment image, the cable pole image and the current mapping label and the target prediction label corresponding to the training label of the working personnel construction image;
generating tag loss based on data change reference information corresponding to the model feedback data, adjusting a current mapping tag based on the tag loss to obtain an updated mapping tag, and taking the updated mapping tag as the current mapping tag;
and adjusting model parameters of the initial abnormal recognition model based on the model feedback data to obtain an updated initial abnormal recognition model, and returning to the step of inputting the substation equipment image, the cable rod image and the worker construction image into the initial abnormal recognition model until training is completed to obtain the abnormal recognition model.
5. The grid overhaul risk early warning method according to claim 1, wherein historical image data corresponding to faults are obtained, and a grid fault pre-judging model is built according to the historical image data corresponding to the faults.
6. The grid overhaul risk early warning method according to claim 5, wherein the training process of the grid fault pre-judging model comprises: taking the obtained historical image data corresponding to the faults as training samples, and setting the fault historical image data corresponding to the corresponding fault types; and taking the training samples as input parameters of the power grid fault pre-judging model, taking the fault types as output parameters of the power grid fault pre-judging model respectively, and training the power grid fault identification model.
7. The grid overhaul risk early warning method according to claim 1, wherein the preprocessing of the substation equipment image, the cable pole image and the worker construction image specifically comprises the following steps: and sequentially carrying out size unification, pixel processing and overturning processing on the images.
8. The utility model provides a power grid overhauls risk early warning system which characterized in that includes:
an image acquisition module configured to: acquiring a substation equipment image, a cable pole image and a worker construction image in a target area; preprocessing the substation equipment image, the cable rod image and the worker construction image;
an anomaly identification module configured to: performing anomaly identification processing on the substation equipment image, the cable rod image and the worker construction image by utilizing an anomaly identification model formed by advanced training, and acquiring anomaly image data corresponding to the substation equipment image, the cable rod image and the worker construction image;
a failure pre-determination module configured to: acquiring a pre-judging fault type according to the substation equipment image, the cable pole image and the image abnormal data corresponding to the worker construction image by utilizing a pre-training formed power grid fault pre-judging model;
a risk pre-control module configured to: and according to the obtained predicted fault category, a corresponding risk pre-control scheme is called from the fault overhaul database and is transmitted to related overhaul departments.
9. A computer readable storage medium having stored thereon a program, which when executed by a processor, implements the steps of a grid overhaul risk warning method as claimed in any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor performs the steps of a grid overhaul risk pre-warning method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310639761.0A CN116703852A (en) | 2023-05-30 | 2023-05-30 | Power grid overhaul risk early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310639761.0A CN116703852A (en) | 2023-05-30 | 2023-05-30 | Power grid overhaul risk early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116703852A true CN116703852A (en) | 2023-09-05 |
Family
ID=87830536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310639761.0A Pending CN116703852A (en) | 2023-05-30 | 2023-05-30 | Power grid overhaul risk early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703852A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057590A (en) * | 2023-10-11 | 2023-11-14 | 国网山东省电力公司博兴县供电公司 | Power grid overhaul management system and method |
-
2023
- 2023-05-30 CN CN202310639761.0A patent/CN116703852A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057590A (en) * | 2023-10-11 | 2023-11-14 | 国网山东省电力公司博兴县供电公司 | Power grid overhaul management system and method |
| CN117057590B (en) * | 2023-10-11 | 2024-02-02 | 国网山东省电力公司博兴县供电公司 | Power grid overhaul management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110018389B (en) | Online fault monitoring method and system for power transmission line | |
| CN109655712A (en) | A kind of distribution network line fault analysis of causes method and system | |
| CN116187593B (en) | Power distribution network fault prediction processing method, device, equipment and storage medium | |
| CN116703852A (en) | Power grid overhaul risk early warning method and system | |
| CN106443433B (en) | Breaker state monitoring system and method based on opening and closing coil current | |
| CN109061391B (en) | Power grid fault diagnosis method and system based on computer vision tidal current diagram | |
| CN103310389B (en) | Based on the overhead transmission line trouble hunting method of fault mode and Construction of Fault Tree | |
| CN104750976A (en) | Establishment method of transmission line state evaluation parameter system | |
| CN111209535B (en) | Power equipment successive fault risk identification method and system | |
| EP3751699A1 (en) | Method and apparatus for estimating a condition of an energy distribution network | |
| CN117269655B (en) | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium | |
| CN117313018A (en) | Power transmission line abnormal state identification method and system | |
| CN108573233B (en) | Power grid ceramic insulator identification method based on image processing technology | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN111537819A (en) | Distribution automation monitoring method, system, terminal and storage medium | |
| CN112162164A (en) | Cable life prediction system based on neural network | |
| CN103077289A (en) | Delimiting method of bird-caused damage risk areas of poles and towers of power transmission line | |
| CN104076222A (en) | System for evaluating state of electric transmission and transformation equipment based on tree topological structure | |
| CN111737875A (en) | Active power imbalance rate analysis and diagnosis method and system and computer equipment | |
| CN116008682B (en) | Real-time studying and judging method and system for distribution transformer high-voltage open-phase fault position | |
| CN117557244B (en) | Electric power operation and maintenance warning system based on knowledge graph | |
| CN106709158A (en) | Perform improvement method for power grid feeder automation system | |
| Qin | Construction Management Mode of Power Line Engineering in the Era of Big Data | |
| CN115578338A (en) | High-precision transformer equipment defect identification method based on MaskR-CNN algorithm framework | |
| CN117169783A (en) | Transformer winding deformation online monitoring system and method |
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 |