A photovoltaic panel cleaning control method, device and electronic equipment

Abstract

This specification discloses a photovoltaic panel cleaning control method, device, and electronic device. The method includes acquiring an inspection image and identifying photovoltaic panel areas within the image; determining a first distance based on the remaining water level in a drone's water tank, and setting a target area within the photovoltaic panel area; in response to the presence of stains on the photovoltaic panel area, generating a first control command when the stains are completely within the target area, the first control command controls the drone to stop moving along the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the first distance; generating a second control command controls the drone to adjust the water gun spray angle so that the water gun nozzle faces the stain, and then the water gun sprays cleaning liquid. In this embodiment, water consumption can be saved, preventing the liquid in the water tank from being completely consumed before the inspection ends, resulting in higher overall cleaning efficiency and quality.

Description

Technical Field

[0001] The embodiments in this specification pertain to the field of photovoltaic panel cleaning, and specifically relate to a photovoltaic panel cleaning control method, apparatus, and electronic equipment. Background Technology

[0002] The cleaning process for photovoltaic panels generally involves manual cleaning, traditional mechanical cleaning, and drone cleaning. Manual cleaning poses risks due to high-altitude operations, resulting in poor safety and low efficiency. Traditional mechanical cleaning relies on rail or vehicle-mounted equipment, which lacks flexibility and can easily scratch the surface of the photovoltaic panels. Drone cleaning currently typically involves manually controlling the drones to spray water, lacking sufficient automation and prone to water waste or blind spots, leading to issues of "over-cleaning" or "under-cleaning." Therefore, current photovoltaic panel cleaning methods still have shortcomings in terms of efficiency and precision. Summary of the Invention

[0003] Embodiments of this disclosure provide a photovoltaic panel cleaning control method, apparatus, and electronic device, aimed at solving one or more of the above-mentioned problems and other potential problems.

[0004] According to a first aspect of this disclosure, a photovoltaic panel cleaning control method is provided. The method includes acquiring inspection images continuously captured by a drone moving along an inspection route, and identifying photovoltaic panel areas in the inspection images based on an image recognition model; determining a first distance based on the remaining water volume in the drone's water tank, and setting a target area within the photovoltaic panel area such that the distance between the boundary of the target area and the center point of the image in the vertical direction of the image is the first distance; in response to the presence of stains in the photovoltaic panel area, when the stains are completely within the target area, generating a first control command to control the drone to stop moving along the inspection route and move horizontally along the image until the distance between the stains and the drone is no greater than the first distance; generating a second control command to control the drone to adjust the water gun spray angle so that the water gun outlet faces the stains and the water gun sprays cleaning liquid.

[0005] According to a second aspect of this disclosure, a photovoltaic panel cleaning control device is provided. The device includes an image acquisition module configured to acquire inspection images continuously captured by a drone moving along an inspection route, and to identify photovoltaic panel areas in the inspection images based on an image recognition model; an area setting module configured to determine a first distance based on the remaining water volume in the drone's water tank, and to set a target area within the photovoltaic panel area such that the distance between the boundary of the target area and the center point of the image in the vertical direction of the image is the first distance; a first control module configured to generate a first control command in response to the presence of stains in the photovoltaic panel area, when the stains are completely within the target area, the first control command controlling the drone to stop moving along the inspection route and move horizontally along the image until the distance between the stains and the drone is no greater than the first distance; and a second control module configured to generate a second control command controlling the drone to adjust the water gun spray angle so that the water gun outlet faces the stains and the water gun sprays cleaning liquid.

[0006] According to a third aspect of this disclosure, an electronic device is provided, including one or more processors and a memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform a method provided according to a first scheme.

[0007] According to a fourth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided according to the first aspect.

[0008] The solution provided in this specification can identify stains on photovoltaic panels during inspection using an image recognition model. Once the stain is in the target area, the position of the drone is adjusted based on a first distance, allowing the drone to precisely control the water gun to spray the stain. This automates the inspection and cleaning process. Furthermore, the water gun spray range is dynamically adjusted based on the remaining water in the tank, saving water consumption and preventing the liquid in the tank from being depleted before the inspection ends. This results in higher overall cleaning efficiency and quality. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic flowchart of a photovoltaic panel cleaning control method according to some embodiments of the present disclosure is shown;

[0011] Figure 2 A schematic diagram of the structure of a photovoltaic panel cleaning control device according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic block diagram of an electronic device according to some embodiments of the present disclosure is shown. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] The terms “comprising” and “having”, and any variations thereof, in this specification, claims, and the foregoing drawings are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. Depending on the context, the word “if” as it applies herein may be interpreted as “when”, “in response to determination”, or “in response to detection”.

[0015] Figure 1 A schematic flowchart of a photovoltaic panel cleaning control method 100 according to some embodiments of this disclosure is shown. Method 100 can be executed by a terminal, which may include, but is not limited to, mobile phones, tablets, desktop computers, servers, etc. Figure 1 As shown, in method 100, step 102 can acquire inspection images continuously captured by the drone as it moves along the inspection route, and identify the photovoltaic panel area in the inspection images based on an image recognition model.

[0016] In this embodiment, based on the specific inspection scenario conducted by the drone, an inspection route can be pre-planned for that scenario, allowing the drone to move along the route during normal inspections. The drone can employ RTK+GPS dual-antenna positioning to achieve centimeter-level positioning and real-time coordinate updates. While moving along the inspection route, the drone continuously acquires inspection images via its onboard camera. Based on a pre-trained image recognition model used to identify photovoltaic panels and stains in the images, the photovoltaic panel area can be determined within the inspection images. For example, the YOLOv8 model can be used as the image recognition model.

[0017] In method 100, step 104 can determine a first distance based on the remaining water in the drone's water tank, and set a target area within the photovoltaic panel area so that the distance between the boundary of the target area and the center point of the image in the vertical direction of the image is the first distance.

[0018] In this embodiment, the drone is also equipped with a water gun and a water tank, allowing the drone to control the water gun to spray cleaning liquid (such as water or neutral detergent) from the water tank to clean stains. When the water tank is full, the water gun can spray a wider range, reducing the frequency of drone movement, thus saving drone power and reducing the total time spent on inspection and cleaning. When the water tank is low, to avoid the water running out before the inspection is completed, the spray range of the water gun can be narrowed, reducing waste during the cleaning process. Therefore, a database storing the mapping relationship between the remaining water in the tank and a first distance can be pre-set based on the specific circumstances of the actual scenario and historical experience, where the remaining water in the tank is directly proportional to the first distance. Based on the first distance, a target area can be divided in the photovoltaic panel area. The target area can be regarded as the middle area divided by two horizontal dividing lines in the inspection image, and the distance between the dividing line (i.e., the boundary of the target area) and the center point of the image in the vertical direction of the image is the first distance. When the drone is at a high altitude and the image covers a large number of photovoltaic panels at the same time, if the drone is directly controlled to spray water for cleaning as soon as stains are identified in the image, it is easy to cause the stains that need to be cleaned to be far away from the current position of the drone. This not only wastes water but also results in low cleaning accuracy. Therefore, a target area will be further divided within the photovoltaic panel area based on the first distance, and the corresponding cleaning operation will be carried out after the identified stains enter the target area.

[0019] In method 100, step 106 may respond to the presence of stains in the photovoltaic panel area and generate a first control command when the stains are completely within the target area. The first control command is used to control the drone to stop moving on the inspection route and move along the horizontal direction of the image until the distance between the stains and the drone is no greater than a first distance.

[0020] In this embodiment, based on the target area, the photovoltaic panel area in the image can be roughly divided into three segments: upper, middle, and lower, with the middle segment being the target area. As the drone moves along the inspection route, when it detects new stains in the photovoltaic panel area, the stains should be located in the upper segment of the photovoltaic panel area. Direct cleaning at this point would be less effective, so the drone is controlled to continue its normal inspection movement. When the image recognition model detects that the stain is completely within the target area, a corresponding first control command is generated to stop the drone's movement on the inspection route. Simultaneously, when dividing the target area based on the first distance determined by the remaining water in the tank, the boundary is only defined vertically. This means that if the stain is far from the image center point (i.e., the drone's location) in the horizontal direction, the water gun still needs to spray a considerable distance for cleaning. Therefore, the drone is also controlled to move laterally along the horizontal direction of the image from the stopped position until the distance between the drone and the stain is no greater than the first distance. The reason for adopting this control method is that when the liquid in the water tank is sufficient, the cleaning range of the drone is large, and the stains are not necessarily in the more peripheral areas. This means that the drone does not need to leave the inspection route for additional movement in many cases. Therefore, this method can reduce unnecessary movement of the drone and the distance it needs to move when it must move, improve inspection efficiency, save power, and avoid stains that may be missed due to movement.

[0021] In method 100, step 108 can generate a second control command to control the drone to adjust the water gun spray angle so that the water gun outlet is directed toward the stain and the water gun sprays cleaning liquid.

[0022] In this embodiment, once the distance between the drone and the stain is no greater than a first distance, the water gun spray angle is adjusted according to the stain's position in the image, allowing the drone to control the water gun to spray cleaning liquid. By default, without adjustment, the water gun's spray intensity can be fixed or varied based on the remaining water in the tank, depending on actual needs.

[0023] As an example, the formula for calculating the water gun spray angle can be:

[0024]

[0025] Here, data represents the relative pixel value of the identified stain based on the center of the image pixel.

[0026] In one possible implementation, the method further includes:

[0027] Obtain the array parameters of the photovoltaic panel array, and query the initial number of photovoltaic panels in the initial image based on the array parameters. The array parameters include the size parameters of a single photovoltaic panel, the arrangement of photovoltaic panels, and the spacing between photovoltaic panels under the arrangement.

[0028] A third control command is generated to control the drone to move to the initial position and then adjust the drone's altitude until the initial number of photovoltaic panels are completely covered in the initial image.

[0029] In this embodiment, the arrangement of photovoltaic panels may differ in different scenarios, such as single-panel spacing, side-by-side arrangement, or multi-row spacing. Different arrangement methods may result in different numbers of photovoltaic panels being covered in the image acquired at the same height. Therefore, a parameter query database can be pre-constructed based on actual needs and historical experience. This database pre-sets reasonable initial quantities for different array parameters through testing. The initial quantity setting can be based on covering as many photovoltaic panels as possible to improve inspection efficiency while avoiding the drone being too far from the edge of the image. By obtaining the array parameters of the photovoltaic panel array that needs to be inspected, the initial quantity can be determined by the parameter query database. Then, the drone's height at the initial point is adjusted according to this initial quantity so that the initial image can exactly cover the initial number of photovoltaic panels. The current height is then used as the drone's inspection height.

[0030] In one possible implementation, in response to the presence of a stain in the photovoltaic panel area, when the stain is completely within the target area, a first control command is generated, including:

[0031] In response to the presence of stains in the photovoltaic panel area, a first control command is generated when the stains are completely within the target area for the first consecutive frame number.

[0032] In this embodiment, to avoid misidentification by the image recognition model and waste of liquid in the water tank, the continuously collected inspection images can be continuously judged. Only when the stain is detected in the target area within the first consecutive frame number will the first control command be generated.

[0033] In one possible implementation, a first control command is generated to control the drone to stop moving along the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than a first distance, including:

[0034] The second distance is determined based on the drone's remaining battery power, and the second distance is inversely proportional to the remaining battery power.

[0035] In response to the second distance not being greater than the first distance, a first control command is generated. The first control command is used to control the drone to stop moving on the inspection route and move along the horizontal direction of the image until the distance between the stain and the drone is not greater than the first distance.

[0036] In response to the second distance being greater than the first distance, a fourth control command is generated. The fourth control command is used to control the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the second distance.

[0037] In this embodiment, in addition to the remaining water in the tank, the remaining battery power of the drone should also be considered. This is to prevent the drone from consuming power faster than expected due to frequent additional movements on long inspection routes, making it difficult for the drone to complete all inspection tasks. Therefore, a second distance is determined based on the remaining battery power. Similar to the first distance, the specific mapping relationship between the remaining battery power and the second distance can be set and adjusted according to actual needs, as long as the overall trend is inversely proportional. The lower the remaining battery power, the larger the second distance, so that the water gun can cover a wider area, allowing the drone to move less or not at all, thus saving more power. After determining the second distance, it is compared with the first distance and the second distance. If the second distance is not greater than the first distance, it is considered that the distance the drone needs to move will not exceed the safe distance determined based on the remaining battery power, and the drone movement can be directly controlled based on the first distance. If the second distance is greater than the first distance, it means that the distance the drone needs to move to meet the first distance exceeds the safe distance determined based on the remaining battery power (i.e., the second distance). In this case, low power consumption will be prioritized, and the drone movement will be controlled based on the second distance.

[0038] In one possible implementation, after generating the second control command, the method further includes:

[0039] After the second frame, in response to the presence of stains in the target area, the intensity of the drone's water gun spray is increased;

[0040] After the third frame, in response to the presence of stains in the target area, the drone is controlled to stop spraying water and mark the stains.

[0041] In this embodiment, the specific values ​​of the second and third frame numbers can be adjusted and set according to actual needs. After the second frame, if stains still exist in the target area, the stains are considered stubborn. At this time, the drone can be controlled to increase the pressure of the water pressure valve to increase the water gun spray intensity. The specific method of increasing the water gun spray intensity can be to increase the intensity to a fixed level, or to increase the intensity by a specified percentage based on the current water gun spray intensity. If stains are still detected after the third frame, it means that increasing the intensity cannot completely clean them. In this case, to avoid wasting a lot of water and affecting subsequent inspection operations, the location of the stain will be marked according to the drone coordinates when the inspection image containing the stain was collected. After the inspection operation is completed, the staff will control the drone to clean it separately.

[0042] In one possible implementation, the method further includes:

[0043] In response to the absence of unmarked stains in the target area, a fifth control command is generated. This fifth control command is used to control the drone to return to the inspection route and continue moving along the inspection route.

[0044] In this embodiment, when no more unmarked stains are identified in the target area, it is considered that the stains have been cleaned. At this time, a fifth control command will be generated to make the drone move laterally along the horizontal direction of the image, return to the inspection route, and continue to move along the inspection route to complete the subsequent inspection work.

[0045] In one possible implementation, the method further includes:

[0046] Based on historical image data, a training set is determined. The training set includes inspection image samples and corresponding recognition image samples. The recognition image samples are marked with photovoltaic panel samples and stain samples.

[0047] Based on the inspection image samples, the initial model generates the predicted recognition image;

[0048] Using the identified image samples as supervision signals, the initial model is trained for at least one round to obtain the image recognition model.

[0049] In this embodiment, based on historical image data, historically collected inspection image samples and stain recognition results for these inspection image samples can be obtained. Specifically, the inspection image samples correspond to recognized image samples labeled with photovoltaic panel samples and stain samples in the images. Training and testing sets can be constructed using these inspection and recognition image samples. To accurately identify different types of stains, the training set should cover as many image samples as possible corresponding to various stains. The initial model can be, for example, a YOLOv8 model. During training the initial model using the training set, the model's generator can generate predicted recognition images based on the inspection image samples. The generator loss can be obtained by comparing the recognized image samples and the predicted recognition images. This generator loss is then used to assess the loss of the predicted recognition images. The loss assessment can utilize a comparison loss function (e.g., a labeled smoothed cross-entropy loss function). The generator loss can be a large value, and it can then be backpropagated to the generator to guide the optimization of its parameters, achieving one round of supervised training of the generator. This training process can be iterated round after round until the generator can produce more accurate predicted and recognized images, that is, until the loss value calculated by the loss function is smaller. After training, the image recognition model can output the recognized image.

[0050] Figure 2Schematic diagrams of a photovoltaic panel cleaning control device 200 according to some embodiments of this disclosure are shown. The various embodiments in this specification are described in a progressive manner; similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments. Figure 2 As shown, the device 200 includes an image acquisition module 201, configured to acquire inspection images continuously captured by the drone as it moves along the inspection route, and to identify the photovoltaic panel area in the inspection image based on an image recognition model; an area setting module 202, configured to determine a first distance based on the remaining water in the drone's water tank, and to set a target area within the photovoltaic panel area such that the distance between the boundary of the target area and the center point of the image in the vertical direction of the image is the first distance; a first control module 203, configured to generate a first control command in response to the presence of stains in the photovoltaic panel area, when the stains are completely within the target area, the first control command being used to control the drone to stop moving on the inspection route and to move horizontally along the image until the distance between the stains and the drone is no greater than the first distance; and a second control module 204, configured to generate a second control command, the second control command being used to control the drone to adjust the water gun spray angle so that the water gun outlet is facing the stains and the water gun sprays cleaning liquid.

[0051] In one possible implementation, the device further includes a parameter query module configured to acquire array parameters of the photovoltaic panel array, query the initial number of photovoltaic panels in the initial image based on the array parameters, the array parameters including the size parameters of a single photovoltaic panel, the arrangement of photovoltaic panels, and the spacing between photovoltaic panels in the arrangement; and generate a third control command, which is used to control the drone to move to the initial position and then adjust the drone's altitude until the initial number of photovoltaic panels is completely covered in the initial image.

[0052] In one possible implementation, the first control module 203 is further configured to generate a first control command in response to the presence of a stain in the photovoltaic panel area when the stain is completely within the target area for a first consecutive frame number.

[0053] In one possible implementation, the first control module 203 is further configured to determine a second distance based on the remaining battery power of the drone, the second distance being inversely proportional to the remaining battery power; in response to the second distance being no greater than the first distance, generating a first control command to control the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the first distance; in response to the second distance being greater than the first distance, generating a fourth control command to control the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the second distance.

[0054] In one possible implementation, the second control module 204 is further configured to, after the second frame, increase the water gun spray intensity of the drone in response to the presence of stains in the target area; and after the third frame, control the drone to stop water gun spraying and mark the stains in response to the presence of stains in the target area.

[0055] In one possible implementation, the device further includes a return module configured to generate a fifth control command in response to the absence of unmarked stains in the target area. The fifth control command is used to control the drone to return to the inspection route and continue moving along the inspection route.

[0056] In one possible implementation, the device further includes a model training module configured to determine a training set based on historical image data. The training set includes inspection image samples and corresponding recognition image samples, wherein the recognition image samples are marked with photovoltaic panel samples and stain samples. Based on the inspection image samples, a predicted recognition image is generated from an initial model. Using the recognition image samples as supervision signals, the initial model is trained for at least one round to obtain an image recognition model.

[0057] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this specification is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0058] Figure 3 A block diagram of an electronic device 300 that can implement various embodiments of the present disclosure is shown. For example... Figure 3 As shown, the electronic device 300 includes a processor 310, a disk drive 320, an input / output interface 330, a network interface 340, and a memory 350. The processor 310, disk drive 320, input / output interface 330, network interface 340, and memory 350 can communicate with each other via a communication bus 360.

[0059] The processor 310 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs in order to implement the technical solution provided in this application.

[0060] The memory 350 can be implemented in the form of ROM (Read Only Memory), RAM (Read Access Memory), static memory, dynamic storage devices, etc. The memory 350 can store the operating system 351 used to control the operation of the electronic device 300, and the basic input / output system (BIOS) 352 used to control the low-level operations of the electronic device 300. Additionally, it can store a web browser 353, a data storage management system 354, etc. In summary, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 350 and is called and executed by the processor 310.

[0061] Input / output interface 330 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, vibrators, indicator lights, etc.

[0062] Network interface 340 is used to connect a communication module (not shown in the figure) to enable communication and interaction between the device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0063] Bus 360 includes a pathway for transmitting information between various components of the device, such as processor 310, disk drive 320, input / output interface 330, network interface 340, and memory 350.

[0064] It should be noted that although the above-described device only shows the processor 310, disk drive 320, input / output interface 330, network interface 340, memory 350, bus 360, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the method of this application, and does not necessarily include all the components shown in the figures.

[0065] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0066] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0067] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for cleaning and controlling photovoltaic panels, characterized in that, The method includes: Acquire inspection images continuously captured by the drone as it moves along the inspection route, and identify the photovoltaic panel area in the inspection images based on an image recognition model; A first distance is determined based on the remaining water in the drone's water tank. A target area is set within the photovoltaic panel area so that the distance between the boundary of the target area and the center point of the image in the vertical direction of the image is the first distance. In response to the presence of stains in the photovoltaic panel area, when the stains are completely within the target area, a first control command is generated. The first control command is used to control the drone to stop moving on the inspection route and move along the horizontal direction of the image until the distance between the stains and the drone is no greater than the first distance. A second control command is generated to control the drone to adjust the water gun spray angle so that the water gun outlet is directed toward the stain and the water gun sprays cleaning liquid. The step of generating a first control command, which controls the drone to stop moving along the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the first distance, includes: The second distance is determined based on the drone's remaining battery power, and the second distance is inversely proportional to the remaining battery power. In response to the second distance not being greater than the first distance, a first control command is generated. The first control command is used to control the drone to stop moving on the inspection route and move along the horizontal direction of the image until the distance between the stain and the drone is not greater than the first distance. In response to the second distance being greater than the first distance, a fourth control command is generated, which controls the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the second distance.

2. The photovoltaic panel cleaning control method according to claim 1, characterized in that, The method further includes: Obtain the array parameters of the photovoltaic panel array, and query the initial number of photovoltaic panels in the initial image based on the array parameters. The array parameters include the size parameters of a single photovoltaic panel, the arrangement of photovoltaic panels, and the spacing between photovoltaic panels under the arrangement. A third control command is generated, which controls the drone to move to the initial position and then adjusts the drone's altitude until the initial number of photovoltaic panels are completely covered in the initial image.

3. The photovoltaic panel cleaning control method according to claim 1, characterized in that, In response to the presence of a stain in the photovoltaic panel area, when the stain is completely within the target area, a first control command is generated, including: In response to the presence of stains in the photovoltaic panel area, a first control command is generated when the stains are completely within the target area for a first consecutive number of frames.

4. The photovoltaic panel cleaning control method according to claim 1, characterized in that, After generating the second control command, the method further includes: After the second frame, in response to the presence of stains in the target area, the intensity of the drone's water gun spray is increased; After the third frame, in response to the presence of stains in the target area, the drone is controlled to stop spraying water and mark the stains.

5. The photovoltaic panel cleaning control method according to claim 1, characterized in that, The method further includes: In response to the absence of unmarked stains in the target area, a fifth control command is generated to control the drone to return to the inspection route and continue moving along the inspection route.

6. The photovoltaic panel cleaning control method according to claim 1, characterized in that, The method further includes: Based on historical image data, a training set is determined, which includes inspection image samples and corresponding recognition image samples. The recognition image samples are marked with photovoltaic panel samples and stain samples. Based on the inspection image samples, a predicted recognition image is generated from the initial model; Using the identified image samples as supervision signals, the initial model is trained for at least one round to obtain an image recognition model.

7. A photovoltaic panel cleaning control device, characterized in that, The device includes: The image acquisition module is configured to acquire inspection images continuously captured by the drone as it moves along the inspection route, and to identify the photovoltaic panel area in the inspection images based on an image recognition model. The region setting module is configured to determine a first distance based on the remaining water in the water tank of the drone, and set a target region within the photovoltaic panel area, such that the distance between the boundary of the target region and the center point of the image in the vertical direction of the image is the first distance; The first control module is configured to generate a first control command in response to the presence of a stain in the photovoltaic panel area when the stain is completely within the target area. The first control command is used to control the drone to stop moving on the inspection route and move along the horizontal direction of the image until the distance between the stain and the drone is not greater than the first distance. The second control module is configured to generate a second control command, which is used to control the drone to adjust the water gun spray angle so that the water gun outlet is directed toward the stain and the water gun sprays cleaning liquid. The first control module is further configured to determine a second distance based on the remaining battery power of the drone, the second distance being inversely proportional to the remaining battery power; in response to the second distance being no greater than the first distance, a first control command is generated, the first control command being used to control the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the first distance; in response to the second distance being greater than the first distance, a fourth control command is generated, the fourth control command being used to control the drone to stop moving on the inspection route and move horizontally along the image until the distance between the stain and the drone is no greater than the second distance.

8. An electronic device, characterized in that, include: One or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the photovoltaic panel cleaning control method according to any one of claims 1-6.

9. A computer program product, characterized in that, The system includes a computer program that, when executed by a processor, implements a photovoltaic panel cleaning control method according to any one of claims 1-6.

Images