CN115318759A - Insulator laser cleaning method and system based on unmanned aerial vehicle - Google Patents
Insulator laser cleaning method and system based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN115318759A CN115318759A CN202210910023.0A CN202210910023A CN115318759A CN 115318759 A CN115318759 A CN 115318759A CN 202210910023 A CN202210910023 A CN 202210910023A CN 115318759 A CN115318759 A CN 115318759A
- Authority
- CN
- China
- Prior art keywords
- pollution flashover
- insulator
- aerial vehicle
- unmanned aerial
- cleaning
- 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.)
- Granted
Links
- 238000004140 cleaning Methods 0.000 title claims abstract description 159
- 239000012212 insulator Substances 0.000 title claims abstract description 137
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000003044 adaptive effect Effects 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 239000000428 dust Substances 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 7
- 239000003016 pheromone Substances 0.000 description 7
- 239000000835 fiber Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000011109 contamination Methods 0.000 description 4
- 230000002950 deficient Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 239000003507 refrigerant Substances 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000967 suction filtration Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B7/00—Cleaning by methods not provided for in a single other subclass or a single group in this subclass
- B08B7/0035—Cleaning by methods not provided for in a single other subclass or a single group in this subclass by radiant energy, e.g. UV, laser, light beam or the like
- B08B7/0042—Cleaning by methods not provided for in a single other subclass or a single group in this subclass by radiant energy, e.g. UV, laser, light beam or the like by laser
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
Abstract
The invention relates to an insulator laser cleaning method and system based on an unmanned aerial vehicle, wherein the method comprises the following steps: determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover identification model; an adaptive double-layer ant colony algorithm based on an elite strategy, and planning a cleaning path according to the pollution flashover information; and carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path. According to the insulator laser cleaning method and system based on the unmanned aerial vehicle, pollution flashover information of the insulator is obtained through the unmanned aerial vehicle, the cleaning path is planned according to the pollution flashover information, the cleaning efficiency and the cleaning precision are improved, and water resources are saved through laser cleaning.
Description
Technical Field
The invention relates to the technical field of laser cleaning, in particular to an insulator laser cleaning method and system based on an unmanned aerial vehicle.
Background
Insulators are devices mounted between conductors of different potentials or between a conductor and a ground potential member, capable of withstanding the effects of voltage and mechanical stress. The discharge activity of the surface of the insulator in the long-term use process can change a dirt layer, so that the dirt accumulation characteristic of the insulator is influenced. The pollution flashover accident of the insulator can cause serious threat to the safe operation of the power system and huge economic loss, so that the insulator needs to be cleaned regularly.
At present, most of insulator cleaning methods are to clean the positions of the insulators needing to be cleaned by utilizing charged water in a manual mode.
However, the cleaning can only be carried out remotely in order to ensure the safety of cleaning personnel, but the cleaning effect achieved by the remote washing mode is not ideal, water resources are seriously wasted, and the cleaning machine cannot be used in water-deficient areas.
Disclosure of Invention
In view of the above, it is necessary to provide an insulator laser cleaning method and system based on an unmanned aerial vehicle, so as to solve the problems of low insulator cleaning precision, poor cleaning effect and water resource waste in the prior art.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides an insulator laser cleaning method based on an unmanned aerial vehicle, which comprises the following steps:
determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover identification model;
an adaptive double-layer ant colony algorithm based on an elite strategy, and a cleaning path is planned according to pollution flashover information;
and carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
Preferably, the determining the pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover recognition model includes:
establishing an initial pollution flashover recognition model based on a YOLOV5 algorithm;
training the initial pollution flashover recognition model to obtain a target pollution flashover recognition model based on an attention mechanism;
and inputting the image information of the insulator to be cleaned into the target pollution flashover recognition model to obtain pollution flashover information of the insulator to be cleaned.
Preferably, based on the attention mechanism, training the initial pollution flashover recognition model to obtain the target pollution flashover recognition model includes:
acquiring an insulator pollution flashover picture, and preprocessing the insulator pollution flashover picture to obtain an insulator pollution flashover picture training set;
and training the initial pollution flashover recognition model according to the insulator pollution flashover picture training set to obtain a target pollution flashover recognition model.
Preferably, the pollution flashover information includes pollution flashover coordinate information; the self-adaptive double-layer ant colony algorithm based on the elite strategy and planning a cleaning path according to pollution flashover information comprises the following steps:
initializing unmanned aerial vehicle information according to the pollution flashover coordinate information and the unmanned aerial vehicle parameters;
determining the track point probability of the unmanned aerial vehicle movement according to the initialized unmanned aerial vehicle information and the unmanned aerial vehicle parameters;
and determining the cleaning path of the unmanned aerial vehicle according to the track point probability of the unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information.
Preferably, the cleaning path of the unmanned aerial vehicle is determined according to the track point probability of the unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information, and then the method comprises the following steps: and optimizing the cleaning path based on the track evaluation function to obtain a target cleaning path.
Preferably, the laser cleaning is performed on the pollution flashover part of the insulator to be cleaned according to the cleaning path, and the laser cleaning method comprises the following steps:
controlling the unmanned aerial vehicle to move to a pollution flashover part according to the cleaning path, and acquiring pollution flashover distance information;
and carrying out laser cleaning on the pollution flashover part according to the pollution flashover distance information.
Preferably, the laser cleaning of the contamination portion based on the contamination distance information includes: and after the laser cleaning is finished, recovering dust generated by the cleaning.
In a second aspect, the present invention further provides an insulator laser cleaning system based on an unmanned aerial vehicle, including:
the pollution flashover recognition module is used for determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover recognition model;
the path planning module is used for self-adapting double-layer ant colony algorithm based on the elite strategy and planning a cleaning path according to pollution flashover information;
and the cleaning module is used for carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
In a third aspect, the present invention also provides an electronic device comprising a memory and a processor, wherein,
a memory for storing a program;
and the processor is coupled with the memory and is used for executing the program stored in the memory so as to realize the steps in the insulator laser cleaning method based on the unmanned aerial vehicle in any one of the implementation modes.
In a fourth aspect, the present invention further provides a computer-readable storage medium, configured to store a computer-readable program or instruction, where the program or instruction, when executed by a processor, can implement the steps in the unmanned aerial vehicle-based insulator laser cleaning method in any one of the above-described implementation manners.
The beneficial effects of adopting the above embodiment are: according to the insulator laser cleaning method and system based on the unmanned aerial vehicle, pollution flashover image information of an insulator to be cleaned is obtained through the unmanned aerial vehicle, path planning is carried out according to the pollution flashover image information, a path track from an initial position of the unmanned aerial vehicle to an insulator pollution flashover part is obtained, the unmanned aerial vehicle moves to the insulator pollution flashover part according to the path track, and then laser is adopted for cleaning the pollution flashover part. According to the invention, the pollution flashover part of the insulator is accurately identified, then the cleaning path is planned, so that the unmanned aerial vehicle can accurately reach the pollution flashover part and then clean the pollution flashover part, the efficiency and the accuracy of cleaning the insulator are improved, the cleaning is carried out by laser, water resources are not consumed, the water resources are saved, and a feasible scheme for cleaning the insulator is provided for a water-deficient area.
Drawings
Fig. 1 is a schematic flow diagram of an embodiment of an insulator laser cleaning method based on an unmanned aerial vehicle according to the present invention;
FIG. 2 is a flow chart illustrating an embodiment of identifying pollution flashover information according to the present invention;
FIG. 3 is a schematic flow chart diagram illustrating an embodiment of planning a cleaning path according to the present invention;
fig. 4 is a schematic structural diagram of an embodiment of the unmanned aerial vehicle-based insulator laser cleaning system provided in the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention provides an insulator laser cleaning method and system based on an unmanned aerial vehicle, which are respectively explained below.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of an insulator laser cleaning method based on an unmanned aerial vehicle according to the present invention, and a specific embodiment of the present invention discloses an insulator laser cleaning method based on an unmanned aerial vehicle, including:
s101, determining pollution flashover information of the insulator to be cleaned according to image information of the insulator to be cleaned based on a pollution flashover recognition model;
s102, a self-adaptive double-layer ant colony algorithm based on an elite strategy is adopted, and a cleaning path is planned according to pollution flashover information;
and S103, carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
In the above embodiment, the image information of the insulator to be cleaned is acquired by the unmanned aerial vehicle, the image information of the insulator to be cleaned is input into the pollution flashover recognition model, the pollution flashover information of the insulator to be cleaned is obtained, the pollution flashover part of the insulator is recognized by the pollution flashover image information, and the actual coordinate information of the pollution flashover part is obtained through coordinate conversion.
And (3) carrying out path planning according to the actual coordinate information of the pollution flashover part and the initial position of the unmanned aerial vehicle by the self-adaptive double-layer ant colony algorithm of the elite strategy, and calculating a path track for cleaning the pollution flashover part reached by the unmanned aerial vehicle.
The unmanned aerial vehicle is driven to move to the pollution flashover position according to the planned cleaning path track to carry out laser cleaning, and the efficiency and the accuracy of cleaning the pollution flashover position of the insulator are improved.
Compared with the prior art, the insulator laser cleaning method based on the unmanned aerial vehicle, which is provided by the embodiment, acquires pollution flashover image information of an insulator to be cleaned through the unmanned aerial vehicle, performs path planning according to the pollution flashover image information, obtains a path track from an initial position of the unmanned aerial vehicle to a pollution flashover position of the insulator, moves the unmanned aerial vehicle to the pollution flashover position of the insulator according to the path track, and then cleans the pollution flashover position by adopting laser. According to the invention, the pollution flashover part of the insulator is accurately identified, then the cleaning path is planned, so that the unmanned aerial vehicle can accurately reach the pollution flashover part and then clean the pollution flashover part, the efficiency and the accuracy of cleaning the insulator are improved, the cleaning is carried out by laser, water resources are not consumed, the water resources are saved, and a feasible scheme for cleaning the insulator is provided for a water-deficient area.
Referring to fig. 2, fig. 2 is a schematic flow chart of an embodiment of identifying pollution flashover information according to the present invention, in some embodiments of the present invention, determining pollution flashover information of an insulator to be cleaned according to image information of the insulator to be cleaned based on a pollution flashover identification model includes:
s201, establishing an initial pollution flashover recognition model based on a YOLOV5 algorithm;
s202, training the initial pollution flashover recognition model to obtain a target pollution flashover recognition model based on an attention mechanism;
s203, inputting the image information of the insulator to be cleaned into the target pollution flashover recognition model to obtain pollution flashover information of the insulator to be cleaned.
In the above embodiment, an attention mechanism is combined with an original YOLOV5 network structure to form a new network structure, and meanwhile, a camera installed on an unmanned aerial vehicle is used to acquire images of a target object, then the images are preprocessed, all the images are labeled with label frames, a training set and a test set are further divided, and finally, a model for detecting the target object, namely a target pollution flashover recognition model, is obtained by training in a configured environment.
The ceramic wafer is identified through the depth camera installed on the unmanned aerial vehicle, and the target object is identified under the target pollution flashover identification model. And converting the camera coordinate information of all the detected target objects into real world coordinates through the depth camera, and transmitting the real world coordinates back to the vehicle-mounted controller to provide coordinate information for the unmanned aerial vehicle to perform trajectory planning.
In some embodiments of the present invention, training the initial pollution flashover recognition model to obtain the target pollution flashover recognition model based on an attention mechanism includes:
acquiring an insulator pollution flashover picture, and preprocessing the insulator pollution flashover picture to obtain an insulator pollution flashover picture training set;
and training the initial pollution flashover recognition model according to the insulator pollution flashover picture training set to obtain a target pollution flashover recognition model.
In the above embodiment, first, global average pooling is performed on the feature maps performed on the inputs, and a feature map can be obtained by the operation of global pooling (the size of the pooled convolution kernel is consistent with the size of the input feature map), where c is the number of channels; then carrying out full connection twice, wherein the number of the neurons of the first full connection layer is
Dimension reduction is carried out, and the number of the neurons of the original channel number is increased by the second full connection layer, so that more nonlinear processing processes can be increased, and complex correlation among channels can be fitted; then, an activation function layer is connected, specifically, the activation function is Sigmod, so that a characteristic diagram of 1 × 1 × c is obtained; and (3) performing full multiplication operation on the feature map with the original size and the feature map with the size of 1 multiplied by c, so that feature maps with different channel importance can be obtained.
Through multiple training, a target pollution flashover recognition model meeting the recognition requirements is finally obtained, it needs to be noted that the recognition requirements can be specifically set according to actual conditions, and the invention is not further limited herein.
Referring to fig. 3, fig. 3 is a schematic flow chart of an embodiment of planning a cleaning path according to the present invention, in some embodiments of the present invention, the pollution flashover information includes pollution flashover coordinate information; the self-adaptive double-layer ant colony algorithm based on the elite strategy and planning the cleaning path according to the pollution flashover information comprises the following steps:
s301, initializing unmanned aerial vehicle information according to the pollution flashover coordinate information and the unmanned aerial vehicle parameters;
s302, determining the track point probability of the unmanned aerial vehicle movement according to the initialized unmanned aerial vehicle information and the unmanned aerial vehicle parameters;
s303, determining the cleaning path of the unmanned aerial vehicle according to the track point probability of the unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information.
In the above embodiment, the drone information is initialized according to the pollution flashover coordinate information and the drone parameter, and the initialization formula of the heuristic value for the drone to move from point i to point j is as follows:
wherein eta is ij Is a heuristic factor, W d ，W θ Respectively distance and angle heuristics, d e Is the horizontal distance, (x, y, z), (x ' y ', (z '), (x) n ,y n ,z n ) Respectively representing the coordinates of the current point, the next selectable point and the target point, gamma is the direction angle of the current point and the target point, c 1 ，c 2 And c 3 Is a weight parameter.
Determining the track point probability of unmanned aerial vehicle movement according to the initialized unmanned aerial vehicle information and unmanned aerial vehicle parameters, wherein the probability of transfer from point i to point j of the kth unmanned aerial vehicle at time t can be calculated according to the following formula:
wherein, tau ij (t) is the i to j pheromone factor, τ is (t) is the pheromone factor from point i to the next point s, η ij (t) is a heuristic factor from point i to point j, η is (t) is a heuristic factor from point i to the next point s, alpha represents an pheromone factor, beta represents a heuristic value factor, allowed k Representing the following set of points that the drone can select at the current point. The move point j +1 may be selected by roulette.
After the man-machine finishes track point selection, determining the cleaning path of the unmanned aerial vehicle according to the track point probability of unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information, and adjusting the information on each path according to the following formula to form a complete path:
where ρ is 1 Represents the global pheromone evaporation factor, c is a custom parameter, F (0), F (k) represents the best merit function value and the current merit function value, τ ij (t + 1) is a global pheromone, τ max Is the maximum pheromone, τ min Is the smallest pheromone, | P n P end I represents the distance between the final point and the target point on the horizontal plane, ω represents the angle between the line from the current point to the target point and the X-axis, d ij Is the distance, ρ, from point i to point j 2 Is a random number from 0 to 1.
In some embodiments of the present invention, determining the cleaning path of the drone according to the trajectory point probability of the drone movement and the initialized drone information, then includes: and optimizing the cleaning path based on the track evaluation function to obtain a target cleaning path.
In the above embodiment, the quality of the trajectory is evaluated by the trajectory evaluation function. Specifically, the evaluation criterion is the horizontal distance between the starting point and the target point, and the formula is as follows:
wherein (x) i ,y i ) For unmanned aerial vehicle origin coordinates, (x) i+1 ,y i+1 ) And coordinates of a target point of the unmanned aerial vehicle.
And evaluating the quality of the plurality of tracks through a track evaluation function, and selecting the optimal cleaning path, namely the target cleaning path according to the obtained result.
In some embodiments of the present invention, laser cleaning a pollution flashover portion of an insulator to be cleaned according to a cleaning path includes:
controlling the unmanned aerial vehicle to move to a pollution flashover part according to the cleaning path, and acquiring pollution flashover distance information;
and carrying out laser cleaning on the pollution flashover part according to the pollution flashover distance information.
In the above embodiment, drive unmanned aerial vehicle removes to dirty position of dodging according to wasing the route, obtains dirty sudden strain of a muscle distance information through the laser belt cleaning device that unmanned aerial vehicle equipped to realize that unmanned aerial vehicle washs the accuracy at dirty sudden strain of a muscle position.
The laser cleaning device consists of a laser cleaning module, a displacement sensor and a controller, wherein the laser cleaning module comprises a fiber laser, a fiber laser output arm, a laser cleaning head, a fiber and cable bundle. Carry on the camera on unmanned aerial vehicle and carry out insulator filth detection and with real-time picture wireless transmission to controller through YOLOV5, displacement sensor begins to measure the laser cleaning head (being located optic fibre laser output arm end) and the surperficial distance of filth this moment, transmits the positional information of filth to the controller, and controller control fiber laser produces laser, and the laser of production is transmitted laser cleaning head and is washd the filth through optic fibre laser output arm.
If a plurality of dirt exists in a picture captured by the camera, the controller transmits position information of the dirt acquired by the camera and the displacement sensor to the controller, the controller transmits position signals of the dirt to be cleaned to the mirror vibration motor, when laser passes through a reflector on the mirror vibration motor in the laser cleaning head, the mirror vibration motor receives an instruction set for representing the currently acquired dirt positioning angle, the two reflectors deflect along the X, Y axis respectively so as to achieve the deflection of laser beams, and then laser with rated power density is focused on the dirt accurately through lens focusing, so that the laser cleaning head can perform all-around cleaning operation according to the path.
In some embodiments of the present invention, laser cleaning of the contamination portion based on the contamination distance information, then includes: and after the laser cleaning is finished, recovering dust generated by the cleaning.
In the above embodiment, after the cleaning operation is completed, the circulating pump is further required to work to convey the refrigerant liquid in the storage cavity to the inside of the refrigeration coil pipe through the liquid inlet pipe, and at this time, the heat generated by the laser cleaning operation can be transferred to the refrigerant liquid in the refrigeration coil pipe through the heat transfer effect; different storage cavities are divided in the storage box, so that the refrigerating fluid can be recycled, and the cost is reduced.
When the laser head cleans the object to be cleaned, the dust suction head is started at the same time, and generates negative pressure to suck and recover dust generated during cleaning; the sucked dust is then collected to a dust suction filtration recovery device through a suction recovery pipeline.
In order to better implement the insulator laser cleaning method based on the unmanned aerial vehicle in the embodiment of the present invention, on the basis of the insulator laser cleaning method based on the unmanned aerial vehicle, correspondingly, please refer to fig. 4, where fig. 4 is a schematic structural diagram of an embodiment of the insulator laser cleaning system based on the unmanned aerial vehicle provided by the present invention, an embodiment of the present invention provides an insulator laser cleaning system 400 based on the unmanned aerial vehicle, including:
the pollution flashover recognition module 401 is configured to determine pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover recognition model;
a path planning module 402, configured to plan a cleaning path according to pollution flashover information based on an elite policy-based adaptive double-layer ant colony algorithm;
and a cleaning module 403, configured to perform laser cleaning on a pollution flashover portion of the insulator to be cleaned according to the cleaning path.
Here, it should be noted that: the system 400 provided in the foregoing embodiment may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principle of each module or unit may refer to the corresponding content in the foregoing method embodiments, which is not described herein again.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Based on the insulator laser cleaning method based on the unmanned aerial vehicle, the invention further correspondingly provides insulator laser cleaning equipment based on the unmanned aerial vehicle, and the insulator laser cleaning equipment based on the unmanned aerial vehicle can be computing equipment such as a mobile terminal, a desktop computer, a notebook computer, a palm computer and a server. The unmanned aerial vehicle-based insulator laser cleaning device comprises a processor 510, a memory 520 and a display 530. Fig. 5 shows only some of the components of the electronic device, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The memory 520 may be an internal storage unit of the drone-based insulator laser cleaning device in some embodiments, such as a hard disk or a memory of the drone-based insulator laser cleaning device. The memory 520 may also be an external storage device of the laser cleaning device for insulator based on the drone, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the laser cleaning device for insulator based on the drone. Further, memory 520 may also include both internal and external storage units of the drone-based insulator laser cleaning device. The memory 520 is used for storing application software installed in the insulator laser cleaning device based on the unmanned aerial vehicle and various data, for example, program codes installed in the insulator laser cleaning device based on the unmanned aerial vehicle, and the like. The memory 520 may also be used to temporarily store data that has been output or is to be output. In an embodiment, the memory 520 stores an insulator laser cleaning program 540 based on an unmanned aerial vehicle, and the insulator laser cleaning program 540 based on the unmanned aerial vehicle can be executed by the processor 510, so as to implement the insulator laser cleaning method based on the unmanned aerial vehicle according to the embodiments of the present application.
The display 530 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, and the like in some embodiments. Display 530 is used to display information at the drone-based insulator laser cleaning device and to display a visual user interface. Components 510-530 of the drone-based insulator laser cleaning device communicate with each other via a system bus.
In one embodiment, the steps in the drone-based insulator laser cleaning method described above are implemented when processor 510 executes drone-based insulator laser cleaning program 540 in memory 520.
The present embodiment also provides a computer-readable storage medium, on which an unmanned aerial vehicle-based insulator laser cleaning program is stored, and when executed by a processor, the unmanned aerial vehicle-based insulator laser cleaning program implements the following steps:
determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover identification model;
an adaptive double-layer ant colony algorithm based on an elite strategy plans a cleaning path according to pollution flashover information;
and carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
In summary, according to the insulator laser cleaning method and system based on the unmanned aerial vehicle provided by the embodiment, the pollution flashover image information of the insulator to be cleaned is acquired through the unmanned aerial vehicle, the path planning is performed according to the pollution flashover image information, the path track from the initial position of the unmanned aerial vehicle to the pollution flashover position of the insulator is obtained, the unmanned aerial vehicle moves to the pollution flashover position of the insulator according to the path track, and then the pollution flashover position is cleaned by laser. According to the invention, the pollution flashover part of the insulator is accurately identified, then the cleaning path is planned, so that the unmanned aerial vehicle can accurately reach the pollution flashover part and then clean the pollution flashover part, the efficiency and the accuracy of cleaning the insulator are improved, the cleaning is carried out by laser, water resources are not consumed, the water resources are saved, and a feasible scheme for cleaning the insulator is provided for a water-deficient area.
While the invention has been described with reference to specific preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the following claims.
Claims (10)
1. The utility model provides an insulator laser cleaning method based on unmanned aerial vehicle which characterized in that includes:
determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover identification model;
an adaptive double-layer ant colony algorithm based on an elite strategy, and planning a cleaning path according to the pollution flashover information;
and carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
2. The laser cleaning method for the insulator based on the unmanned aerial vehicle as claimed in claim 1, wherein the determining of the pollution flashover information of the insulator to be cleaned based on the pollution flashover recognition model and according to the image information of the insulator to be cleaned comprises:
establishing an initial pollution flashover recognition model based on a YOLOV5 algorithm;
training the initial pollution flashover recognition model to obtain a target pollution flashover recognition model based on an attention mechanism;
and inputting the image information of the insulator to be cleaned into the target pollution flashover recognition model to obtain the pollution flashover information of the insulator to be cleaned.
3. The unmanned aerial vehicle-based insulator laser cleaning method according to claim 2, wherein training the initial pollution flashover recognition model based on the attention mechanism to obtain a target pollution flashover recognition model comprises:
acquiring an insulator pollution flashover picture, and preprocessing the insulator pollution flashover picture to obtain an insulator pollution flashover picture training set;
and training the initial pollution flashover recognition model according to the insulator pollution flashover picture training set to obtain a target pollution flashover recognition model.
4. The unmanned-aerial-vehicle-based insulator laser cleaning method according to claim 1, wherein the pollution flashover information comprises pollution flashover coordinate information; the adaptive double-layer ant colony algorithm based on the elite strategy and planning the cleaning path according to the pollution flashover information comprises the following steps:
initializing unmanned aerial vehicle information according to the pollution flashover coordinate information and the unmanned aerial vehicle parameters;
determining the track point probability of the unmanned aerial vehicle movement according to the initialized unmanned aerial vehicle information and the unmanned aerial vehicle parameters;
and determining the cleaning path of the unmanned aerial vehicle according to the track point probability of the unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information.
5. The unmanned aerial vehicle-based insulator laser cleaning method according to claim 4, wherein the determining of the cleaning path of the unmanned aerial vehicle according to the trajectory point probability of the unmanned aerial vehicle movement and the initialized unmanned aerial vehicle information comprises: and optimizing the cleaning path based on a track evaluation function to obtain a target cleaning path.
6. The unmanned aerial vehicle-based insulator laser cleaning method according to claim 1, wherein the laser cleaning of the pollution flashover part of the insulator to be cleaned according to the cleaning path comprises:
controlling the unmanned aerial vehicle to move to a pollution flashover part according to the cleaning path to obtain pollution flashover distance information;
and carrying out laser cleaning on the pollution flashover part according to the pollution flashover distance information.
7. The unmanned aerial vehicle-based insulator laser cleaning method according to claim 6, wherein the laser cleaning of the pollution flashover part according to the pollution flashover distance information comprises the following steps: and after the laser cleaning is finished, recovering dust generated by the cleaning.
8. The utility model provides an insulator laser cleaning system based on unmanned aerial vehicle which characterized in that includes:
the pollution flashover recognition module is used for determining pollution flashover information of the insulator to be cleaned according to the image information of the insulator to be cleaned based on the pollution flashover recognition model;
the path planning module is used for self-adapting double-layer ant colony algorithm based on the elite strategy and planning a cleaning path according to the pollution flashover information;
and the cleaning module is used for carrying out laser cleaning on the pollution flashover part of the insulator to be cleaned according to the cleaning path.
9. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled with the memory, is configured to execute the program stored in the memory to implement the steps in the method for laser cleaning insulator based on drone of any one of the above claims 1 to 7.
10. A computer-readable storage medium for storing a computer-readable program or instructions, which when executed by a processor, is capable of implementing the steps of the method for laser cleaning insulator based on drone of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210910023.0A CN115318759B (en) | 2022-07-29 | 2022-07-29 | Unmanned aerial vehicle-based insulator laser cleaning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210910023.0A CN115318759B (en) | 2022-07-29 | 2022-07-29 | Unmanned aerial vehicle-based insulator laser cleaning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115318759A true CN115318759A (en) | 2022-11-11 |
| CN115318759B CN115318759B (en) | 2024-04-09 |
Family
ID=83920318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210910023.0A Active CN115318759B (en) | 2022-07-29 | 2022-07-29 | Unmanned aerial vehicle-based insulator laser cleaning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115318759B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160669A (en) * | 2015-08-21 | 2015-12-16 | 马鞍山市安工大工业技术研究院有限公司 | Method for detecting and locating insulator defects in power transmission line image via a drone |
| CN109086848A (en) * | 2018-08-31 | 2018-12-25 | 深圳市研本品牌设计有限公司 | Clean the localization method and system of unmanned plane |
| CN109919345A (en) * | 2017-12-12 | 2019-06-21 | 北京京东尚科信息技术有限公司 | Picking paths planning method and device |
| CN110180839A (en) * | 2019-06-27 | 2019-08-30 | 清华大学 | A kind of laser cleaner and laser cleaning method |
| CN112090869A (en) * | 2020-09-08 | 2020-12-18 | 临沂大学 | Method and device for cleaning rusty spot by using laser of unmanned aerial vehicle and unmanned aerial vehicle |
| CN112615301A (en) * | 2020-12-10 | 2021-04-06 | 拓航科技有限公司 | Unmanned aerial vehicle electric power inspection video identification laser obstacle clearing system |
| CN112835375A (en) * | 2021-01-08 | 2021-05-25 | 中国科学技术大学 | Insulator cleaning method, system, equipment and storage medium based on unmanned aerial vehicle |
| CN112947480A (en) * | 2021-03-24 | 2021-06-11 | 武汉理工大学 | Mobile robot path planning method, storage medium and system |
| CN113145538A (en) * | 2021-03-25 | 2021-07-23 | 中国科学技术大学 | Insulator cleaning control method and system |
| CN113972586A (en) * | 2021-10-29 | 2022-01-25 | 国网山东省电力公司梁山县供电公司 | High-voltage transmission line unmanned aerial vehicle carrying laser foreign matter removing system and method |
| DE102020134868B3 (en) * | 2020-12-23 | 2022-04-07 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Drone laser cleaning device and method of operating the same |
-
2022
- 2022-07-29 CN CN202210910023.0A patent/CN115318759B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160669A (en) * | 2015-08-21 | 2015-12-16 | 马鞍山市安工大工业技术研究院有限公司 | Method for detecting and locating insulator defects in power transmission line image via a drone |
| CN109919345A (en) * | 2017-12-12 | 2019-06-21 | 北京京东尚科信息技术有限公司 | Picking paths planning method and device |
| CN109086848A (en) * | 2018-08-31 | 2018-12-25 | 深圳市研本品牌设计有限公司 | Clean the localization method and system of unmanned plane |
| CN110180839A (en) * | 2019-06-27 | 2019-08-30 | 清华大学 | A kind of laser cleaner and laser cleaning method |
| CN112090869A (en) * | 2020-09-08 | 2020-12-18 | 临沂大学 | Method and device for cleaning rusty spot by using laser of unmanned aerial vehicle and unmanned aerial vehicle |
| CN112615301A (en) * | 2020-12-10 | 2021-04-06 | 拓航科技有限公司 | Unmanned aerial vehicle electric power inspection video identification laser obstacle clearing system |
| DE102020134868B3 (en) * | 2020-12-23 | 2022-04-07 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Drone laser cleaning device and method of operating the same |
| CN112835375A (en) * | 2021-01-08 | 2021-05-25 | 中国科学技术大学 | Insulator cleaning method, system, equipment and storage medium based on unmanned aerial vehicle |
| CN112947480A (en) * | 2021-03-24 | 2021-06-11 | 武汉理工大学 | Mobile robot path planning method, storage medium and system |
| CN113145538A (en) * | 2021-03-25 | 2021-07-23 | 中国科学技术大学 | Insulator cleaning control method and system |
| CN113972586A (en) * | 2021-10-29 | 2022-01-25 | 国网山东省电力公司梁山县供电公司 | High-voltage transmission line unmanned aerial vehicle carrying laser foreign matter removing system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115318759B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102433743B1 (en) | Map building and location tracking of robots | |
| US10823576B2 (en) | Systems and methods for robotic mapping | |
| Liao et al. | Maptr: Structured modeling and learning for online vectorized hd map construction | |
| CN109755995B (en) | Robot automatic charging docking method based on ROS robot operating system | |
| US11717959B2 (en) | Machine learning methods and apparatus for semantic robotic grasping | |
| WO2020062835A1 (en) | Robot and automatic recharging method and system therefor, electronic device and storage medium | |
| US10611028B1 (en) | Map building and positioning of robot | |
| US9616568B1 (en) | Generating a grasp affordance for an object based on a thermal image of the object that is captured following human manipulation of the object | |
| US20190121365A1 (en) | Systems and methods for training a robot to automomously travel a route | |
| CN109725327B (en) | Method and system for building map by multiple machines | |
| CN205219101U (en) | Service robot of family | |
| CN109602356A (en) | A kind of clean robot, intelligent method for supplementing water and moisturizing station | |
| CN109978272B (en) | Path planning system and method based on multiple omnidirectional mobile robots | |
| CN111872935A (en) | Robot control system and control method thereof | |
| CN110825088A (en) | Multi-view vision guiding ship body cleaning robot system and cleaning method | |
| US20230311335A1 (en) | Natural language control of a robot | |
| CN112894758A (en) | Robot cleaning control system, method and device and computer equipment | |
| Liu | A robust and efficient lidar-inertial-visual fused simultaneous localization and mapping system with loop closure | |
| CN117053793A (en) | Water quality monitoring and inspection method, device and equipment based on sea-air cross-domain cooperation | |
| CN112123338A (en) | Transformer substation intelligent inspection robot system supporting deep learning acceleration | |
| CN114089752A (en) | Autonomous exploration method for robot, and computer-readable storage medium | |
| Li et al. | FC-SLAM: Federated learning enhanced distributed visual-LiDAR SLAM in cloud robotic system | |
| CN115318760B (en) | Unmanned aerial vehicle laser cleaning method and system for power transmission tower | |
| CN115318759B (en) | Unmanned aerial vehicle-based insulator laser cleaning method and system | |
| CN114091515A (en) | Obstacle detection method, obstacle detection device, electronic apparatus, 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 | ||
| GR01 | Patent grant |