CN115169602A - Maintenance method and device for power equipment, storage medium and computer equipment - Google Patents
Maintenance method and device for power equipment, storage medium and computer equipment Download PDFInfo
- Publication number
- CN115169602A CN115169602A CN202210710228.4A CN202210710228A CN115169602A CN 115169602 A CN115169602 A CN 115169602A CN 202210710228 A CN202210710228 A CN 202210710228A CN 115169602 A CN115169602 A CN 115169602A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- image
- equipment
- inspection
- inspection image
- 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
Images
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Economics (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a maintenance method and device of power equipment, a storage medium and computer equipment, and mainly aims to improve the maintenance efficiency of the power equipment and reduce the personnel cost. Which comprises the following steps: acquiring a patrol inspection image acquired by an unmanned aerial vehicle; inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image; if the power equipment is determined to be contained in the inspection image according to the identification result, performing cutout processing on the inspection image to obtain a power equipment image; determining whether the electrical device has a fault based on the electrical device image; and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
Description
Technical Field
The present invention relates to the field of power technologies, and in particular, to a method and an apparatus for maintaining a power device, a storage medium, and a computer device.
Background
In order to ensure that the power transmission line on the tower pole can normally operate, the power line equipment needs to be inspected in real time, and once the equipment is found to be abnormal, operation and maintenance personnel can maintain the equipment in time.
At present, in a traditional power equipment maintenance mode, equipment is usually detected in a manual mode, and if equipment faults are found, a patrol worker can search operation and maintenance personnel on duty for maintenance. However, this kind of mode needs to arrange special personnel to patrol and detect, can greatly increased personnel's cost from this, in addition, if patrol personnel do not discover in time that equipment is out of order, fortune dimension personnel just can't arrive the scene very first time and carry out equipment maintenance to lead to maintenance efficiency lower.
Disclosure of Invention
The invention provides a maintenance method and device of power equipment, a storage medium and computer equipment, and mainly aims to improve the maintenance efficiency of the power equipment and reduce the personnel cost.
According to a first aspect of the present invention, there is provided a maintenance method of an electric power apparatus, including:
acquiring a patrol inspection image acquired by an unmanned aerial vehicle;
inputting the inspection image into a preset target identification model for target identification to obtain an identification result corresponding to the inspection image;
if the power equipment is determined to be contained in the inspection image according to the identification result, performing cutout processing on the inspection image to obtain a power equipment image;
determining whether the electrical device has a fault based on the electrical device image;
and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
According to a second aspect of the present invention, there is provided a maintenance apparatus for an electric power equipment, comprising:
the acquisition unit is used for acquiring the inspection image acquired by the unmanned aerial vehicle;
the recognition unit is used for inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image;
the matting unit is used for matting the patrol inspection image to obtain an electric power equipment image if the patrol inspection image is determined to contain the electric power equipment according to the identification result;
a determination unit configured to determine whether or not the electric device has a failure based on the electric device image;
and the generating unit is used for generating work order information corresponding to the power equipment if the power equipment has faults and sending the work order information to operation and maintenance personnel.
According to a third aspect of the present invention, there is provided a computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring a patrol inspection image acquired by an unmanned aerial vehicle;
inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image;
if the inspection image contains the power equipment according to the identification result, performing image matting on the inspection image to obtain a power equipment image;
determining whether the electrical device has a fault based on the electrical device image;
and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
According to a fourth aspect of the present invention, there is provided a computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
acquiring a patrol inspection image acquired by an unmanned aerial vehicle;
inputting the inspection image into a preset target identification model for target identification to obtain an identification result corresponding to the inspection image;
if the power equipment is determined to be contained in the inspection image according to the identification result, performing cutout processing on the inspection image to obtain a power equipment image;
determining whether the power equipment has a fault based on the power equipment image;
and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
Compared with the conventional manual maintenance mode of the power equipment, the maintenance method, the maintenance device, the storage medium and the computer equipment provided by the invention can acquire the inspection image acquired by the unmanned aerial vehicle, input the inspection image into the preset target identification model for target identification to obtain the identification result corresponding to the inspection image, perform matting on the inspection image to obtain the power equipment image if the inspection image contains the power equipment according to the identification result, judge whether the power equipment has a fault or not on the basis of the power equipment image, generate the work order information corresponding to the power equipment if the power equipment has the fault, and send the work order information to operation and maintenance personnel. Whether power equipment has a fault is judged through the image of patrolling and examining that unmanned aerial vehicle gathered from this to automatically, generate work order information when power equipment has the fault, can realize that power equipment's automation is patrolled and examined, and is intelligent with power equipment's whole fortune dimension flow, thereby can reduce personnel's consumption, reduce fortune dimension cost, improve power equipment's maintenance efficiency, in addition, use unmanned aerial vehicle replacement personnel to patrol and examine aloft, can increase the operation security.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating a maintenance method of an electrical device according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating another maintenance method for an electrical power device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram illustrating a maintenance apparatus for an electrical device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating another maintenance apparatus for electrical equipment according to an embodiment of the present invention;
fig. 5 shows a physical structure diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the drawings and embodiments. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.
Because traditional power equipment maintenance mode need arrange special personnel to patrol and detect, consequently can greatly increased personnel's cost, in addition, if patrol personnel do not in time discover equipment trouble, fortune dimension personnel just can't the very first time arrive the scene and carry out equipment maintenance to lead to maintenance efficiency lower.
In order to solve the above problem, an embodiment of the present invention provides a maintenance method for an electrical device, which is applied to a production process control management system, and as shown in fig. 1, the method includes:
101. and acquiring the patrol image acquired by the unmanned aerial vehicle.
Wherein, patrol and examine the power line image that the image was patrolled and examined the process shooting for unmanned aerial vehicle in the flight, can include trees and building etc. around power equipment, wire, the wire in this power line image.
The embodiment of the invention is mainly suitable for the scene of automatically inspecting the power equipment and intelligentizing the whole operation and maintenance process. The execution subject of the embodiment of the invention is a device or equipment capable of intelligently maintaining the electric power equipment, and the device or equipment can be specifically arranged on one side of the server.
For the embodiment of the invention, the control management system of the unmanned aerial vehicle is butted with the generation process control management system, a worker can set the routing inspection route of the unmanned aerial vehicle in the production process control management system in advance and send the routing inspection route to the control management system of the unmanned aerial vehicle, the unmanned aerial vehicle can fly according to the routing inspection route, the unmanned aerial vehicle can shoot the power line during flying inspection, and specifically shooting can be carried out according to the principle that the whole is firstly carried out, then the part is carried out, the top to the bottom is carried out, the left to the right is carried out, the front is carried out, and the back is continuously covered. In the shooting process, the unmanned aerial vehicle can shoot at preset time intervals, if one image is shot at every 0.1s, when the unmanned aerial vehicle finishes the patrol, a plurality of patrol images can be obtained, in addition, the time for shooting the image by the unmanned aerial vehicle is required to be recorded when the unmanned aerial vehicle shoots the image, and the patrol position information when the unmanned aerial vehicle shoots the image is obtained, so that the control management system of the unmanned aerial vehicle can obtain the shooting time and the patrol position information corresponding to the plurality of patrol images respectively, and sends the shooting time and the patrol position information to the generation process control management system.
Further, unmanned aerial vehicle can also carry out the video and shoot at the in-process of flight, utilize GPS system record unmanned aerial vehicle to patrol and examine positional information in different time departments simultaneously, later will patrol and examine video and unmanned aerial vehicle and patrol and examine positional information and send for generating process control management system together in different time departments, generating process control management system can be to this video of patrolling and examining and divide the frame to handle, obtain many images of patrolling and examining, meanwhile, according to many time information that the image corresponds respectively of patrolling and examining and the positional information of patrolling and examining of unmanned aerial vehicle in different time departments, can confirm that every patrols and examines positional information that the image corresponds.
It should be noted that, the control management system of the unmanned aerial vehicle may send the shot inspection image or the inspection video to the generation process control management system after the inspection is finished, and may also return the inspection image or the inspection video to the generation process control management system in real time in the inspection process, which is not specifically limited in the embodiment of the present invention.
102. And inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image.
The preset target recognition model can be a Faster R-CNN model, an SSD model, a YOLO model and the like. Taking a Faster R-CNN model as an example, an identification process is illustrated, and after acquiring a plurality of polling images, polling position information and shooting time corresponding to the polling images respectively, a generation process control management system can input any polling image into a pre-trained Faster R-CNN model for target identification to obtain a target main body contained in the polling images and frame information corresponding to the target main body. The target subject may be, among others, electrical equipment, wires, trees, buildings, etc. It should be noted that the training mode of the Faster R-CNN model is known to those skilled in the art, and is not specifically described in the embodiments of the present invention.
103. And if the inspection image contains the power equipment according to the identification result, performing cutout processing on the inspection image to obtain the power equipment image.
For the embodiment of the invention, because the unmanned aerial vehicle cannot ensure that each inspection image comprises the power equipment in the continuous shooting process, whether the inspection image comprises the power equipment or not needs to be judged according to the image identification result aiming at any inspection image, and if the inspection image does not comprise the power equipment, the follow-up processing is not carried out; and if the image is determined to contain the electric power equipment, intercepting the image of the electric power equipment from the inspection image according to the frame information corresponding to the electric power equipment so as to judge whether the electric power equipment has fault defects or not based on the image of the electric power equipment.
104. And determining whether the electric equipment has a fault or not based on the electric equipment image.
For the embodiment of the invention, after the image of the electric power equipment is acquired, whether the electric power equipment in the image has fault defects or not can be detected by using the preset fault detection model. Based on this, step 104 includes: inputting the power image into a corresponding preset fault detection model for fault detection to obtain a first probability value that the power equipment has faults and a second probability value that the power equipment does not have faults; determining that the power equipment has a fault if the first probability value is greater than the second probability value. The preset fault detection model is substantially an image classification model, and specifically may be an AlexNet model, a VGG model, or the like.
Describing a fault detection process of the power equipment by using an AlexNet model, specifically, inputting an image of the power equipment to the AlexNet model trained in advance to obtain probability values of the images of the power equipment belonging to different categories, namely a first probability value that the power equipment in the image of the power equipment has a fault and a second probability value that the power equipment in the image of the power equipment does not have the fault, and if the first probability value is greater than the second probability value, determining that the power equipment in the image of the power equipment has the fault and needs to be detected; and if the second probability value is larger than the first probability value, determining that no fault exists in the power equipment image, and continuing to process the next power equipment image.
Further, the AlexNet model may be further used to detect a specific fault type of the power device, for example, the probability value that the power device has the fault is a first probability value, the probability value that the power device has the fault of type 1 is a second probability value, and the probability value that the power device has the fault of type 2 is a third probability value, and if the third probability value is the maximum, it may be determined that the power device has the fault defect, and the fault type is fault type 2.
Further, before fault detection, a sample image of the type of power equipment may be collected and labeled according to whether the power equipment in the image has a fault, for example, if the power equipment in the sample image has a fault, the sample image is labeled as 1; if the power device does not exist in the sample image, the sample image is labeled as 0. Therefore, a sample image set can be obtained, and the AlexNet model is trained by using the sample image set.
105. And if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
For the embodiment of the invention, once the fault defect of the power equipment is determined, the corresponding work order needs to be generated and the operation and maintenance personnel needs to be sent, and the operation and maintenance personnel can immediately maintain the power equipment after receiving the work order. As an optional implementation manner, regarding the generation process of the work order information, the method includes: acquiring the inspection position information of the unmanned aerial vehicle when the inspection image is shot; matching the routing inspection position information with the equipment position information of each electric equipment in a preset electric equipment library; according to the matching result, determining identification information corresponding to the power equipment; and generating the work order information based on the identification information corresponding to the power equipment. The preset power equipment library records identification information and equipment position information of each power equipment, the identification information can be specifically the number of the power equipment, and the equipment position information can be specifically longitude information and latitude information of the power equipment.
Specifically, if the electrical equipment in the electrical equipment image has a defect fault, routing inspection position information corresponding to the routing inspection image where the electrical equipment is located is determined, the routing inspection position information is matched with equipment position information corresponding to each electrical equipment in a preset electrical equipment library, specifically, position distances between the routing inspection position information and the plurality of pieces of equipment position information can be respectively calculated, a minimum position distance is selected from the calculated plurality of position distances, the electrical equipment corresponding to the minimum position distance is the electrical equipment in the electrical equipment image, and therefore identification information of the electrical equipment in the electrical equipment image can be determined.
Further, work order information is generated according to the identification information, the fault type, the fault detection time, the detection personnel and other information of the power equipment. Specifically, the registered fault defects can be associated with power equipment to form an equipment record, and can also support generation of a fault list through alarm information linkage or manual registration, provide convenient entry of defect registration at multiple places such as equipment maintenance, fault treatment, equipment test and the like, and also manually enter and record the source of the fault defects.
According to the maintenance method of the power equipment, whether the power equipment has a fault or not is judged through the inspection image acquired by the unmanned aerial vehicle, the work order information is automatically generated when the power equipment has the fault, automatic inspection of the power equipment can be achieved, the whole operation and maintenance process of the power equipment is intelligentized, accordingly, the personnel consumption can be reduced, the operation and maintenance cost can be reduced, the maintenance efficiency of the power equipment can be improved, in addition, the unmanned aerial vehicle is used for replacing personnel to conduct high-altitude inspection, and the operation safety can be improved.
Further, in order to better describe the inspection and maintenance process of the electrical equipment, as a refinement and an extension of the foregoing embodiment, an embodiment of the present invention provides another maintenance method of the electrical equipment, as shown in fig. 2, where the method includes:
201. and acquiring the inspection image acquired by the unmanned aerial vehicle.
For the embodiment of the present invention, the specific process of acquiring the inspection image acquired by the unmanned aerial vehicle is completely the same as that in step 101, and is not described herein again.
202. And inputting the inspection image into a preset target identification model for target identification to obtain a target main body and corresponding frame information contained in the inspection image.
The frame information comprises abscissa information, ordinate information, length information and width information of a frame where the target main bodies are located, the number of the target main bodies can be one, two or more, and the target main bodies can be power equipment, wires, trees, buildings and the like. For the embodiment of the invention, the inspection image is input into the preset target identification model for target identification, and the target main body contained in the inspection image and the frame information corresponding to the target main body are obtained.
203. If the target main body comprises the power equipment, the routing inspection image is subjected to matting according to abscissa information, ordinate information, length information and width information in frame information corresponding to the power equipment to obtain the power equipment image.
For the embodiment of the invention, if the identified target body contains the electrical equipment, subsequent equipment fault detection can be performed, and before formal detection, the electrical equipment image needs to be intercepted from the patrol inspection image according to the abscissa information, the ordinate information, the length information and the width information in the frame information of the electrical equipment, so that whether the electrical equipment in the image has a defect fault or not can be judged based on the electrical equipment image.
204. And judging whether the power equipment has faults or not based on the power equipment image, if so, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
For the embodiment of the present invention, the specific process of performing fault detection and the specific process of generating work order information by using the preset fault detection model are completely the same as steps 104 and 105, and are not described herein again. Further, after the work order information is generated, the most suitable operation and maintenance personnel can be automatically selected according to the position of the fault and the positions of the operation and maintenance personnel, and by combining the natural resource condition (wind and light resources), the professional work types of the field personnel, the first busy degree and the like, and the work order information is sent by the most suitable operation and maintenance personnel. Then the operation and maintenance personnel can accept and confirm the work order arrangement, open the work order and submit the issue. Furthermore, the station terminal is provided with a positioning system, and the intelligent positioning management system has the functions of personnel walking positioning, track tracing, video real-time talkback, false entry interval alarm, near-electricity alarm, illegal behavior identification and the like (out of the contract range), can be associated with the work order, can send a navigation map of arriving at a working place to operation and maintenance personnel after the work order is handled, accurately guides the personnel to arrive at the site, can display a walking route on an electronic map of an intelligent operation and maintenance platform, and can give an alarm in time when the route deviates or the interval is wrong.
Furthermore, after the operation and maintenance personnel finish working, defects and fault handling conditions can be filled in at the handheld terminal or the PC client; if there is a component replacement, the component replacement condition can be registered; if the large part is replaced, the new spare part can be used for updating the part information in the equipment file; the identification can be performed for defects belonging to the product batch among the defects of the equipment. In addition, during fault acceptance, the maintainers carry out deletion delivery, and the on-duty staff determines the work termination or returns to the related staff for continuous processing according to the fault acceptance condition. Furthermore, the method can also carry out statistics and analysis of defect faults, inquire related defect and fault records according to information such as defect equipment, defect properties, discovery time, elimination state, equipment type, equipment manufacturer, equipment model and the like, can also carry out statistics on information such as the number of equipment defects or faults, processing time and the like, and analyze the types of the frequently-occurring defects according to the statistical results and model calculation. Meanwhile, in the processing process of the defect list and the fault list, on-site photographing and video recording are supported, and the defect list and the fault list are associated with the work list and can be automatically stored in an equipment management ledger.
In the specific application scene, unmanned aerial vehicle not only can gather at the in-process of flight and patrol and examine the image, can also gather power equipment's parameter value, judges according to the size of parameter value whether the wire has the fault defect. Based on this, the method further comprises: acquiring parameter values acquired by the unmanned aerial vehicle at different inspection positions; drawing a first lead trend graph based on the parameter values collected at the different inspection positions; and judging whether the lead has a fault or not according to the first lead trend graph and a preset parameter value range.
The parameter value collected by the unmanned aerial vehicle can be specifically a temperature value of a wire and the like, in addition, a preset parameter value range can be set according to actual business requirements, and the embodiment of the invention is not specifically limited. For example, obtain the wire temperature value that unmanned aerial vehicle when flying when the position department was patrolled and examined in the difference, later with patrolling and examining positional information as the abscissa, the temperature value size is the ordinate, draw first wire trend graph, can see the wire temperature value that the position department was patrolled and examined in the difference clearly through this first wire trend graph, whether the wire temperature value in judging first wire trend graph in proper order is in presetting the temperature range next, if the wire temperature value of a certain position department of patrolling and examining exceeds this and presets the temperature range, then explain that the wire of this position department of patrolling and examining probably has the fault defect.
Furthermore, in order to accurately identify whether the fault defect of the lead at the inspection position exists, whether the temperature values of other inspection positions adjacent to the inspection position are in an ascending trend or not needs to be analyzed, if the temperature values of the inspection positions are in the ascending trend, the fact that the lead at the inspection position has the fault is indicated, and work order information needs to be generated and sent to corresponding operation and maintenance personnel; on the contrary, if the temperature does not rise, the temperature is higher only for an isolated point, and the fault defect of the wire cannot be indicated.
In a specific application scenario, a lead trend graph can be drawn to predict the time point of the fault of the lead, and based on the time point, the method comprises the following steps: acquiring parameter values of the lead acquired by the unmanned aerial vehicle at different time nodes aiming at the same patrol position; drawing a second wire trend graph based on the parameter values at the different time nodes; determining the change trend of the parameter value at the inspection position according to the second lead trend graph; and estimating the time point of the fault of the lead at the inspection position based on the variation trend.
For example, can also be to same patrol and examine the position, collect the temperature value that unmanned aerial vehicle gathered at different time nodes, later use the time node as the abscissa, the temperature value is the ordinate, draw second wire trend graph to according to the change trend of second wire trend graph analysis this patrol and examine position department wire temperature, if the wire temperature of this patrol and examine the position is the rising trend all the time, then can estimate out the time node that the wire temperature surpassed preset temperature range. Therefore, operation and maintenance personnel can be requested to maintain as early as possible, and the fault of the lead is avoided.
205. If the target main body further comprises an environmental obstacle main body and a lead, respectively calculating the center coordinate of the frame where the environmental obstacle main body is located and the center coordinate of the frame where the lead is located according to the frame information corresponding to the environmental obstacle main body and the frame information corresponding to the lead.
Wherein, the environmental barrier body comprises trees, buildings and the like. For the embodiment of the invention, in the process of identifying the target of the routing inspection image, the target main body can be electric power equipment, and can also be an environmental obstacle main body and a lead, in order to ensure that the electric power circuit can work normally, the environmental obstacle main body needs to keep a certain distance with the lead, namely, the surrounding environment of the lead needs to be analyzed, and in the process of analyzing the environment, the distance between the environmental obstacle main body and the lead can be estimated according to the identification result of the routing inspection image.
Specifically, the center coordinate of the frame where the wire is located may be calculated according to the abscissa information, the ordinate information, the length information, and the width information in the frame information corresponding to the wire in the recognition result, and similarly, the center coordinate of the frame where the environmental obstacle main body is located may be calculated according to the abscissa information, the ordinate information, the length information, and the width information in the frame information corresponding to the environmental obstacle main body.
206. And calculating the distance between the lead and the environmental obstacle main body based on the central coordinate of the frame where the environmental obstacle main body is located and the central coordinate of the frame where the lead is located.
For the embodiment of the invention, the distance between the lead and the main body of the environmental obstacle is calculated according to the abscissa information and the ordinate information of the central point of the frame where the main body of the environmental obstacle is located, and the abscissa information and the ordinate information of the central point of the frame where the lead is located.
207. And judging whether the environment of the lead meets the safety requirement or not based on the distance.
For the embodiment of the invention, if the distance is greater than or equal to the preset distance, the safety of the environment where the wire is located is indicated, namely, the normal operation of the wire cannot be influenced by the environmental barrier; if the distance is smaller than the preset distance, the environment where the lead is located is unsafe, namely the normal operation of the lead is influenced by the environmental barrier, and at the moment, warning information can be sent to related personnel. It should be noted that, in the embodiment of the present invention, the distance between the wires may also be calculated according to the recognition result, that is, whether the wires are at a safe distance or not is determined.
According to the maintenance method of the power equipment, whether the power equipment has faults or not is judged through the inspection image acquired by the unmanned aerial vehicle, work order information is automatically generated when the power equipment has the faults, automatic inspection of the power equipment can be achieved, the whole operation and maintenance process of the power equipment is intelligentized, accordingly, the personnel consumption can be reduced, the operation and maintenance cost is reduced, the maintenance efficiency of the power equipment is improved, in addition, the unmanned aerial vehicle is used for replacing personnel to conduct high-altitude inspection, and the operation safety can be improved.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a maintenance apparatus for an electrical device, as shown in fig. 3, the apparatus includes: an acquisition unit 31, a recognition unit 32, a matting unit 33, a determination unit 34, and a generation unit 35.
The obtaining unit 31 can be used for obtaining the patrol image collected by the unmanned aerial vehicle.
The identification unit 32 may be configured to input the inspection image into a preset target identification model to perform target identification, so as to obtain an identification result corresponding to the inspection image.
The matting unit 33 may be configured to perform matting on the inspection image to obtain an image of the power device if it is determined that the inspection image includes the power device according to the identification result.
The determination unit 34 may be configured to determine whether the electrical device has a fault based on the electrical device image.
The generating unit 35 may be configured to generate work order information corresponding to the electrical device if the electrical device has a fault, and send the work order information to operation and maintenance staff.
In a specific application scenario, the identifying unit 32 may be specifically configured to input the inspection image into a preset target identification model for target identification, so as to obtain a target main body and frame information corresponding to the target main body, which are included in the inspection image.
The matting unit 33 can be specifically used for if the target body includes the power equipment, then according to the abscissa information, the ordinate information, the length information and the width information in the frame information that the power equipment corresponds, it is right to inspect the image and perform matting to obtain the power equipment image.
In a specific application scenario, as shown in fig. 4, the determining unit 34 includes: a detection module 341 and a first determination module 342.
The detecting module 341 may be configured to input the power image into a corresponding preset fault detection model for fault detection, so as to obtain a first probability value that the power device has a fault and a second probability value that the power device has no fault.
The first determining module 342 may be configured to determine that the power device has a fault if the first probability value is greater than the second probability value.
In a specific application scenario, the generating unit 35 includes: an acquisition module 351, a matching module 352, a second determination module 353, and a generation module 354.
The obtaining module 351 can be used for obtaining the inspection position information of the unmanned aerial vehicle when the image is inspected.
The matching module 352 may be configured to match the inspection position information with device position information of each electrical device in a preset electrical device library, where identification information and device position information of each electrical device are recorded in the preset electrical device library.
The second determining module 353 may be configured to determine, according to a matching result, identification information corresponding to the electrical device.
The generating module 354 may be configured to generate the work order information based on the identification information corresponding to the electrical device.
In a specific application scenario, the apparatus further includes: a calculation unit 36.
The calculating unit 36 may be configured to calculate, if the target main body further includes an environmental obstacle main body and a wire, a center coordinate of a frame where the environmental obstacle main body is located according to frame information corresponding to the environmental obstacle main body.
The calculating unit 36 may be further configured to calculate a center coordinate of a frame where the wire is located according to the frame information corresponding to the wire.
The calculating unit 36 may be further configured to calculate a distance between the lead and the environmental obstacle body based on the center coordinate of the frame where the environmental obstacle body is located and the center coordinate of the frame where the lead is located.
The determination unit 34 may be further configured to determine whether the environment in which the lead is located meets the safety requirement based on the distance.
In a specific application scenario, the apparatus further includes: a rendering unit 37.
The obtaining unit 31 may be further configured to obtain parameter values collected by the unmanned aerial vehicle at different positions of the inspection.
The drawing unit 37 may be configured to draw a first wire trend graph based on the parameter values collected at the different inspection positions.
The determining unit 34 may be further configured to determine whether the wire has a fault according to the first wire trend graph and a preset parameter value range.
In a specific application scenario, the apparatus further includes: a determination unit 38 and a prediction unit 39.
The obtaining unit 31 can also be used for obtaining the parameter values of the wire at different time nodes collected by the unmanned aerial vehicle aiming at the same patrol position.
The drawing unit 37 may be further configured to draw a second wire trend graph based on the parameter values at the different time nodes.
The determining unit 38 may be configured to determine a variation trend of the parameter value at the inspection position according to the second wire trend graph.
The estimating unit 39 may be configured to estimate a time point at which the wire at the inspection position fails based on the variation trend.
It should be noted that other corresponding descriptions of the functional modules related to the maintenance apparatus for electrical equipment provided in the embodiment of the present invention may refer to the corresponding description of the method shown in fig. 1, and are not described herein again.
Based on the method shown in fig. 1, correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following steps: acquiring a patrol inspection image acquired by an unmanned aerial vehicle; inputting the inspection image into a preset target identification model for target identification to obtain an identification result corresponding to the inspection image; if the inspection image contains the power equipment according to the identification result, performing image matting on the inspection image to obtain a power equipment image; determining whether the power equipment has a fault based on the power equipment image; and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
Based on the above embodiments of the method shown in fig. 1 and the apparatus shown in fig. 3, an embodiment of the present invention further provides an entity structure diagram of a computer device, as shown in fig. 5, where the computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43 such that when the processor 41 executes the program, the following steps are performed: acquiring a patrol inspection image acquired by an unmanned aerial vehicle; inputting the inspection image into a preset target identification model for target identification to obtain an identification result corresponding to the inspection image; if the power equipment is determined to be contained in the inspection image according to the identification result, performing cutout processing on the inspection image to obtain a power equipment image; determining whether the electrical device has a fault based on the electrical device image; and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
According to the embodiment of the invention, whether the power equipment has a fault is judged through the inspection image acquired by the unmanned aerial vehicle, the work order information is automatically generated when the power equipment has the fault, the automatic inspection of the power equipment can be realized, and the whole operation and maintenance process of the power equipment is intelligentized, so that the personnel consumption can be reduced, the operation and maintenance cost is reduced, the maintenance efficiency of the power equipment is improved, and in addition, the unmanned aerial vehicle is used for replacing personnel to perform high-altitude inspection, and the operation safety can be improved.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized in a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a memory device and executed by a computing device, and in some cases, the steps shown or described may be executed out of order, or separately as individual integrated circuit modules, or multiple modules or steps thereof may be implemented as a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method of maintaining an electrical device, comprising:
acquiring a patrol inspection image acquired by an unmanned aerial vehicle;
inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image;
if the inspection image contains the power equipment according to the identification result, performing image matting on the inspection image to obtain a power equipment image;
determining whether the power equipment has a fault based on the power equipment image;
and if the power equipment has faults, generating work order information corresponding to the power equipment, and sending the work order information to operation and maintenance personnel.
2. The method according to claim 1, wherein the step of inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image comprises the following steps:
inputting the inspection image into a preset target identification model for target identification to obtain a target main body and corresponding frame information contained in the inspection image;
if the patrol image is determined to contain the power equipment according to the identification result, the patrol image is subjected to image matting to obtain a power equipment image, and the method comprises the following steps:
and if the target main body comprises the power equipment, matting the inspection image according to abscissa information, ordinate information, length information and width information in frame information corresponding to the power equipment to obtain the power equipment image.
3. The method of claim 1, wherein determining whether the electrical device is malfunctioning based on the electrical device image comprises:
inputting the power image into a corresponding preset fault detection model for fault detection to obtain a first probability value that the power equipment has faults and a second probability value that the power equipment does not have faults;
determining that the power equipment has a fault if the first probability value is greater than the second probability value.
4. The method according to claim 1, wherein the generating work order information corresponding to the power equipment comprises:
acquiring the inspection position information of the unmanned aerial vehicle when the inspection image is shot;
matching the routing inspection position information with equipment position information of each electric equipment in a preset electric equipment library, wherein identification information and equipment position information of each electric equipment are recorded in the preset electric equipment library;
according to the matching result, determining identification information corresponding to the power equipment;
and generating the work order information based on the identification information corresponding to the power equipment.
5. The method of claim 2, further comprising:
if the target main body further comprises an environmental obstacle main body and a lead, calculating the central coordinate of a frame where the environmental obstacle main body is located according to frame information corresponding to the environmental obstacle main body;
calculating the center coordinate of the frame where the lead is located according to the frame information corresponding to the lead;
calculating the distance between the lead and the environmental obstacle body based on the central coordinate of the frame where the environmental obstacle body is located and the central coordinate of the frame where the lead is located;
and judging whether the environment of the lead meets the safety requirement or not based on the distance.
6. The method according to any one of claims 1 to 5, further comprising:
acquiring parameter values acquired by the unmanned aerial vehicle at different patrol positions;
drawing a first lead trend graph based on the parameter values collected at the different inspection positions;
and judging whether the lead has a fault or not according to the first lead trend graph and a preset parameter value range.
7. The method of any of claim 6, further comprising:
acquiring parameter values of the lead acquired by the unmanned aerial vehicle at different time nodes aiming at the same inspection position;
drawing a second wire trend graph based on the parameter values at the different time nodes;
determining the change trend of the parameter value at the inspection position according to the second lead trend graph;
and estimating the time point of the fault of the lead at the inspection position based on the variation trend.
8. A maintenance device for an electric power apparatus, comprising:
the acquisition unit is used for acquiring the inspection image acquired by the unmanned aerial vehicle;
the recognition unit is used for inputting the inspection image into a preset target recognition model for target recognition to obtain a recognition result corresponding to the inspection image;
the matting unit is used for matting the patrol inspection image to obtain an electric power equipment image if the patrol inspection image is determined to contain the electric power equipment according to the identification result;
a determination unit configured to determine whether or not the electric device has a failure based on the electric device image;
and the generating unit is used for generating work order information corresponding to the power equipment and sending the work order information to operation and maintenance personnel if the power equipment has faults.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210710228.4A CN115169602A (en) | 2022-06-22 | 2022-06-22 | Maintenance method and device for power equipment, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210710228.4A CN115169602A (en) | 2022-06-22 | 2022-06-22 | Maintenance method and device for power equipment, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115169602A true CN115169602A (en) | 2022-10-11 |
Family
ID=83487100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210710228.4A Pending CN115169602A (en) | 2022-06-22 | 2022-06-22 | Maintenance method and device for power equipment, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169602A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115333062A (en) * | 2022-10-12 | 2022-11-11 | 国网浙江省电力有限公司宁波供电公司 | Fault processing method and device for power distribution network system |
| CN116935245A (en) * | 2023-06-16 | 2023-10-24 | 国网山东省电力公司金乡县供电公司 | Long-distance communication power grid unmanned aerial vehicle inspection system and method |
| CN117673953A (en) * | 2023-12-06 | 2024-03-08 | 国网山东省电力公司莒县供电公司 | Unmanned aerial vehicle-based power line operation and maintenance system and method |
-
2022
- 2022-06-22 CN CN202210710228.4A patent/CN115169602A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115333062A (en) * | 2022-10-12 | 2022-11-11 | 国网浙江省电力有限公司宁波供电公司 | Fault processing method and device for power distribution network system |
| CN116935245A (en) * | 2023-06-16 | 2023-10-24 | 国网山东省电力公司金乡县供电公司 | Long-distance communication power grid unmanned aerial vehicle inspection system and method |
| CN117673953A (en) * | 2023-12-06 | 2024-03-08 | 国网山东省电力公司莒县供电公司 | Unmanned aerial vehicle-based power line operation and maintenance system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| CN115169602A (en) | Maintenance method and device for power equipment, storage medium and computer equipment | |
| CN111310947A (en) | Building facility operation and maintenance method, equipment, storage medium and system based on 5G | |
| CN111311967A (en) | Unmanned aerial vehicle-based power line inspection system and method | |
| CN111080775A (en) | Server routing inspection method and system based on artificial intelligence | |
| JP2017009599A (en) | System and method for non-destructive test involving expert in remote place | |
| WO2020232608A1 (en) | Transmission and distribution device diagnosis method, apparatus, and system, computing device, medium, and product | |
| CN112115927A (en) | Intelligent machine room equipment identification method and system based on deep learning | |
| CN115395646A (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN113888024A (en) | Operation monitoring method and device, electronic equipment and storage medium | |
| CN113554781A (en) | Remote inspection method and device for overhead transmission line and computer equipment | |
| CN112819988A (en) | Unmanned aerial vehicle power station intelligent inspection method and system based on 5G and network side server | |
| CN118150943B (en) | Distribution network ground fault positioning method, system, electronic equipment and storage medium | |
| CN114648708A (en) | State detection method and device of photovoltaic module, storage medium and electronic equipment | |
| CN115649501A (en) | Night driving illumination system and method for unmanned aerial vehicle | |
| CN116866512A (en) | Photovoltaic power station inspection system and operation method thereof | |
| CN117498225B (en) | Unmanned aerial vehicle intelligent power line inspection system | |
| CN114935941A (en) | Unmanned aerial vehicle autonomous inspection system based on laser point cloud | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN112911219B (en) | Method, system and equipment for identifying routing inspection route of power equipment | |
| CN113888481A (en) | Bridge deck disease detection method, system, equipment and storage medium | |
| CN115913349B (en) | Optical cable equipment abnormality positioning method and device, storage medium and terminal | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN112185047B (en) | Mountain fire condition grade evaluation method and system | |
| CN114048916A (en) | Routing inspection line determining method and device, electronic equipment and storage medium |
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 |