Planning design method of photovoltaic power generation system and related products

Abstract

The invention provides a planning and designing method of a photovoltaic power generation system and a related product. The planning design method of the photovoltaic power generation system comprises the following steps: acquiring geographic information data of a to-be-planned area; controlling the unmanned aerial vehicle to perform macro-scale cruise shooting on the to-be-planned area according to the geographic information data to obtain a macro image of the to-be-planned area; identifying the macroscopic image, and determining one or more alternative construction areas with photovoltaic module arrangement conditions; controlling the unmanned aerial vehicle to carry out survey shooting on each alternative construction area to obtain survey images; and carrying out photovoltaic module arrangement design according to the survey image. According to the scheme, the unmanned aerial vehicle determines one or more alternative construction areas from the to-be-planned area at a time, the planning efficiency is improved, the workload of survey personnel is reduced, the planning and design difficulty is reduced, the design intelligence degree is improved, and the planning and design process is simplified.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic system design, and in particular to a planning and design method for a photovoltaic power generation system and related products. Background Art

[0002] In recent years, with the increasingly urgent problems of energy shortage and environmental pollution, in order to adapt to the needs of the new stage of ecological civilization construction, human sustainable development, and high-quality development, the development of clean energy has received increasing attention.

[0003] However, the traditional energy system has problems such as uncoordinated planning and design, and imperfect policies and systems. The regional integrated energy system that performs well in improving energy efficiency, reducing environmental pollution and mitigating climate change has become a new direction for future development in the energy field.

[0004] Regional Integrated Energy (RIES) has excellent effects in promoting the integration of source, grid, load and storage, multi-energy coupling and complementary development by coupling power and electricity load systems, and has become an important way to improve energy efficiency. Distributed power generation system is the core of regional integrated energy system. It converts clean energy into electrical energy, realizes local production and consumption of energy, and saves transmission and distribution costs and energy consumption. Therefore, how to plan and build distributed power generation system has become a research hotspot in related fields.

[0005] Photovoltaic power generation is an important part of distributed power generation systems, and its design and planning requires a lot of field survey work. The design process of traditional photovoltaic power generation systems requires surveying personnel to conduct on-site surveys in the early stage, and then the designers will conduct photovoltaic design based on the results of the on-site survey and provide design drawings to the construction party. This on-site survey, planning and design method has a large survey task, a long design cycle, and high design costs, which makes it difficult to meet the project construction progress and results requirements. The design of photovoltaic power generation projects only targets one design object at a time, and the design work is highly repetitive and the design efficiency is low, which seriously affects the construction progress of distributed photovoltaic power generation systems. Summary of the invention

[0006] An object of the present invention is to efficiently complete the planning and design work of a photovoltaic power generation system in an area to be planned.

[0007] Another object of the present invention is to simultaneously complete the layout design of multiple photovoltaic modules.

[0008] Another further object of the present invention is to improve the accuracy of surveying.

[0009] In particular, the present invention provides a planning and design method for a photovoltaic power generation system. The method comprises:

[0010] Obtain geographic information data of the area to be planned;

[0011] According to the geographic information data, the UAV is controlled to cruise and shoot the area to be planned at a macro scale to obtain a macro image of the area to be planned;

[0012] Identify the macro image and determine one or more candidate construction areas that meet the conditions for arranging photovoltaic modules;

[0013] The drone is controlled to survey and photograph each candidate construction area to obtain a survey image; and the photovoltaic module layout design is performed based on the survey image.

[0014] Optionally, the step of obtaining geographic information data of the area to be planned includes:

[0015] Get the boundary range of the area to be planned;

[0016] The geographic information data within the boundary range is queried from the geographic information data source through a preset application program interface.

[0017] Optionally, the step of controlling the drone to perform macro-scale cruise photography of the planned area according to the geographic information data includes:

[0018] Preliminary analysis of geographic information data to initially identify areas of interest that are larger than the minimum paving area for photovoltaic modules;

[0019] Design the drone's macro shooting plan based on the location and area of ​​the area of ​​interest. The macro shooting plan includes: flight route, flight altitude, flight speed, and shooting parameters;

[0020] The drone is controlled to execute the macro shooting plan to shoot and obtain a macro image.

[0021] Optionally, the step of controlling the drone to execute the macro shooting scheme to shoot includes:

[0022] Acquire images captured by the drone executing a macro shooting plan;

[0023] Performing a quality check on the image to determine whether the image meets the macroscopic object recognition condition, which is used to perform object recognition on the region of interest;

[0024] If satisfied, the drone is controlled to continue executing the macro shooting plan;

[0025] If not, the images and their corresponding positions that do not meet the macro object recognition conditions are marked.

[0026] Optionally, after the step of marking the images that do not meet the macroscopic object recognition condition and their corresponding positions, the method further includes:

[0027] The macroscopic shooting scheme is adjusted to obtain a mesoscopic shooting scheme, and the mesoscopic shooting scheme is used to reshoot images whose marks do not meet the macroscopic object recognition condition;

[0028] After completing the macroscopic shooting plan, the drone is controlled to execute the mesoscopic shooting plan to replace the images marked as not meeting the macroscopic object recognition conditions.

[0029] Optionally, the step of identifying the macro image includes:

[0030] Extracting a recognition target image centered on the region of interest from the macro image;

[0031] Perform object recognition on the target image to determine whether the area of ​​interest has the conditions for arranging photovoltaic modules;

[0032] If the conditions for PV panel layout are met, the area of ​​interest will be marked as an alternative construction area.

[0033] Optionally, the steps of controlling the drone to survey and photograph each candidate construction area include:

[0034] Segmenting an initial image of a candidate construction area from a macroscopic image;

[0035] Setting marker points on the initial image, dividing the initial image into objects based on the marker points, so as to at least determine the installation object, and estimate the area and terrain characteristics of the installation object;

[0036] Design a microscopic shooting plan based on the area and terrain characteristics of the installation object;

[0037] The UAV is controlled to survey and photograph the installation object according to the microscopic shooting plan to obtain a survey image of the installation object.

[0038] Optionally, the step of designing the layout of photovoltaic components according to the survey image includes:

[0039] Generate a three-dimensional model of the candidate construction area based on the survey images;

[0040] Analyze the three-dimensional model to obtain survey characteristic data of the photovoltaic panel laying area;

[0041] Perform simulation design on the photovoltaic panel laying area according to the survey characteristic data to obtain one or more alternative construction plans;

[0042] The model of the alternative construction plan is superimposed on the three-dimensional model of the alternative construction area to generate a display model of the photovoltaic project to be built.

[0043] Optionally, the step of generating a three-dimensional model of the candidate construction area according to the survey image includes:

[0044] Discretize the survey image using set grid points to generate point cloud data of candidate construction areas;

[0045] Use point cloud data to construct the surface and obtain the surface model;

[0046] Perform object recognition on survey images to determine object boundaries;

[0047] Compare the object boundary with the surface model and perform contour segmentation on the surface model;

[0048] The surface model after contour segmentation is visualized to obtain a three-dimensional model.

[0049] Optionally, the step of visualizing the surface model after contour segmentation to obtain a three-dimensional model includes:

[0050] The surface model after contour segmentation is subjected to object entity processing to obtain contour surfaces of multiple objects;

[0051] Collect color and pattern features of multiple objects in survey images;

[0052] The appearance of the contour surfaces of multiple objects is processed according to color and pattern characteristics to obtain a three-dimensional model of the candidate construction area.

[0053] According to another aspect of the present invention, there is also provided a computer program product, comprising a computer program, which implements the steps of any of the above-mentioned photovoltaic power generation system planning and design methods when executed by a processor.

[0054] According to another aspect of the present invention, there is also provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned planning and design methods for a photovoltaic power generation system are implemented.

[0055] According to another aspect of the present invention, a computer device is provided, which includes a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of any of the above-mentioned photovoltaic power generation system planning and design methods.

[0056] The planning and design method of the photovoltaic power generation system of the present invention uses a drone to cruise and photograph the area to be planned at a macro scale, identifies the macro image obtained by the cruise photography, and determines one or more candidate construction areas that meet the conditions for arranging photovoltaic components. The drone determines one or more candidate construction areas from the area to be planned at one time, thereby improving planning efficiency and reducing the workload of surveyors.

[0057] Furthermore, the planning and design method of the photovoltaic power generation system of the present invention, by means of the characteristics of UAVs being flexible and low-cost, solves the problems of increased survey difficulty and inaccurate survey data caused by harsh on-site environments.

[0058] Furthermore, the planning and design method of the photovoltaic power generation system of the present invention pre-analyzes the geographic information data and preliminarily identifies the area of ​​interest whose area is larger than the minimum laying area of ​​the photovoltaic components; the macro-shooting plan of the drone is designed in a targeted manner according to the location and area of ​​the area of ​​interest, so that the shooting method of the drone conforms to the geographical characteristics of the area to be planned, which is conducive to reducing the complexity of subsequent data processing.

[0059] Furthermore, the planning and design method of the photovoltaic power generation system of the present invention further generates a three-dimensional model of the candidate construction area based on the survey image, and superimposes the model of the alternative construction plan on the three-dimensional model of the candidate construction area to generate a display model of the household photovoltaic system. The construction owner can quickly and intuitively obtain the photovoltaic construction results, reduce the survey cost, and greatly facilitate the further promotion of household photovoltaic systems.

[0060] Furthermore, the planning and design method of the photovoltaic power generation system of the present invention improves the intelligence of the design by developing and utilizing survey images, automatically setting landmark points and designing aerial photography plans, further reduces the operations of survey personnel, streamlines the survey operation process, and shortens the survey time.

[0061] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0063] Figure 1 is a schematic diagram of a design system architecture of a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention;

[0064] Figure 2 is a schematic diagram of a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention;

[0065] Figure 3 It is a schematic diagram of a drone performing macroscopic cruising photography of a planned area in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention;

[0066] Figure 4is a schematic diagram of identifying a macro image in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention;

[0067] Figure 5 is a schematic diagram of surveying and photographing a candidate construction area in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention;

[0068] Figure 6 is a schematic diagram of photovoltaic assembly layout design based on survey images in a photovoltaic power generation system planning and design method according to an embodiment of the present invention;

[0069] Figure 7 It is a schematic diagram of a process of generating a three-dimensional model of a candidate construction area in a planning and design method of a photovoltaic power generation system according to an embodiment of the present invention;

[0070] Figure 8 is a schematic diagram of a computer program product according to an embodiment of the present invention;

[0071] Fig. 9 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention; and

[0072] Fig.10 is a schematic block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0073] It should be understood by those skilled in the art that the embodiments described below are only some embodiments of the present invention, rather than all embodiments of the present invention, and these embodiments are intended to explain the technical principles of the present invention, rather than to limit the protection scope of the present invention. Based on the embodiments provided by the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should still fall within the protection scope of the present invention.

[0074] Figure 1 The schematic diagram of the design system architecture of the photovoltaic power generation system planning and design method according to an embodiment of the present invention is shown in FIG. The design system may include: a drone 10 , a wireless communication device 20 , a data processing device 30 , and an interactive terminal 40 .

[0075] The drone 10 may include: a flight control system, a positioning system, an aerial photography system, and a measurement system. The flight control system is used to adjust the flight attitude (including altitude, speed, and direction) of the drone, and the positioning system is used to obtain the location information of the drone 10, which may use positioning devices such as GPS and Beidou. The aerial photography system is used to photograph the target during flight. In order to realize the functions of the method of this embodiment, the aerial photography system uses a camera with adjustable focal length and shooting parameters that meet the design requirements. The measurement system is used to record the flight process of the drone 10 and collect status data such as flight altitude, flight attitude, and shooting parameters.

[0076] The drone 10 exchanges data with the data processing device 30 through the wireless communication device 20, and transmits its own flight data and the data of the airborne equipment (positioning system, aerial photography system, and measurement system) to the data processing device 30. The data processing device 30 collects and processes the data provided by the drone 10 to complete the flight control of the drone 10. With the characteristics of the drone's flexibility and low cost, it completes the functions that cannot be achieved by traditional manual surveys, greatly improving the processing efficiency.

[0077] The wireless communication device 20 can select a communication method according to actual communication conditions, such as 5G, Wi-Fi, Bluetooth, etc. The interactive terminal 40 is data-connected to the drone 10 and the data processing device 30, respectively, and can display the interface generated by the drone 10 and the data processing device 30, and serve as an interactive device with survey and design personnel to provide manual instructions to the drone 10 and the data processing device 30, and adjust the operating status and processing results of the drone 10 and the data processing device 30. The interactive terminal 40 may include a personal computer, a smart phone, a tablet computer, or other dedicated electronic client devices with a survey application installed.

[0078] The photovoltaic power generation system can be a distributed photovoltaic power generation system arranged in an area to be planned (such as an office park, industrial park, village, residential area), which can be arranged on the surface of a building (such as a roof, wall, awning surface), an open exposed surface (slope, ground, water surface), etc. In an area to be planned, there can be multiple areas that can be used to arrange a photovoltaic power generation system, and the types of areas can be the same or different. For example, for a certain office park, the roof of an office building, the roof of a parking lot awning, the slope of a ditch, etc. can all be used as layout objects for photovoltaic components. In the prior art, different layout objects need to be surveyed and designed one by one. The method of this embodiment uses a drone 10 to achieve an overall survey of an area to be planned, thereby improving the efficiency of planning and design.

[0079] This embodiment first provides a planning and design method for a photovoltaic power generation system, which can be executed by the above-mentioned data processing device 30 to complete the site selection, planning, surveying and design work of the area to be planned. Figure 2 Schematic diagram of a photovoltaic power generation system planning and design method according to an embodiment of the present invention. The photovoltaic power generation system planning and design method may generally include:

[0080] Step S201, obtain geographic information data of the area to be planned. A method for obtaining geographic information data is: obtain the boundary range of the area to be planned; query the geographic information data within the boundary range from the geographic information data source through a preset application program interface. The boundary range of the area to be planned can be delineated on the map by the planner of the photovoltaic power generation system, or it can be determined by input geographic coordinates or regional division. The shape of the boundary range of the area to be planned may be irregular, so it is necessary to design the survey route in a targeted manner. Geographic information data refers to digital information about the position, shape, size and distribution characteristics of ground and near-surface features, which may include spatial position data (latitude and longitude coordinates, altitude, etc., used to accurately locate the position of geographical elements), attribute data (used to describe the non-spatial characteristics of entities, such as land use, building type, road registration, population, etc.), terrain data (data reflecting the undulating morphology of the surface, such as digital elevation model (DEM), contour lines), remote sensing image data (satellite remote sensing images), vector data (geometric elements such as points, lines, and surfaces that accurately represent geographic boundaries and networks), and raster data (regular grids divided into spaces, used to represent continuous changes in temperature, rainfall, etc.). The geographic information data can be obtained by querying a specific geographic information data source, which may use a third-party platform such as OpenStreetMap (OSM), Google Maps, NASA WorldWind, AutoNavi Map Open Platform, Baidu Maps, or other geographic mapping platforms. In this embodiment, an application programming interface (API) can be developed in advance to call the query results of the above-mentioned geographic information data source.

[0081] The geographic information data obtained above does not contain all the information for planning and designing the photovoltaic power generation system. Therefore, the method of this embodiment further uses a drone to conduct a further survey based on the geographic information data.

[0082] Step S202, according to the geographic information data, the drone is controlled to perform macroscopic cruising photography of the area to be planned, and a macroscopic image of the area to be planned is obtained. The macroscopic scale of the macroscopic cruising photography is relative to the subsequent further refined drone photography. The macroscopic photography requires the ability to obtain the overall situation of the area to be planned and meet the requirements of identifying the selected construction area.

[0083] Step S203, identifying the macro image to determine one or more candidate construction areas that meet the conditions for arranging photovoltaic modules.

[0084] Step S204, controlling the drone to survey and photograph each candidate construction area to obtain a survey image;

[0085] Step S205 , designing the layout of photovoltaic modules according to the survey image.

[0086] The method of the above embodiment uses a drone to cruise and photograph the area to be planned at a macro scale, identifies the macro images obtained by the cruise photography, and determines one or more candidate construction areas that meet the conditions for arranging photovoltaic modules. The drone determines one or more candidate construction areas from the area to be planned at one time, which improves planning efficiency and reduces the workload of surveyors.

[0087] Figure 3 1 is a schematic diagram of a drone performing macroscopic cruising photography of a planned area in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention. The cruising photography process may include:

[0088] Step S301, pre-analyze the geographic information data, and preliminarily identify the areas of interest that are larger than the minimum laying area of ​​the photovoltaic modules. The minimum laying area of ​​the photovoltaic modules can be set according to the area required by the minimum capacity construction unit in the photovoltaic power generation system. Since the construction of photovoltaic modules that are too small may increase the cost of electrical cable connection and the difficulty of control, before planning and design, the minimum capacity construction unit can be determined according to the power load and area size of the planned area. In this embodiment, the area of ​​interest refers to the key area for focusing on data collection, processing and visualization, that is, the area that may be used to arrange photovoltaic modules or the area that has an impact on the area where photovoltaic modules are arranged.

[0089] Step S302, designing a macro shooting plan of the drone according to the location and area of ​​the region of interest, the macro shooting plan including: flight route, flight altitude, flight speed, and shooting parameters.

[0090] Step S303, controlling the drone to execute a macro shooting scheme to shoot, so as to obtain a macro image.

[0091] Step S304, when the drone executes the macro shooting scheme, an image captured by the drone executing the macro shooting scheme is obtained.

[0092] Step S305, perform a quality check on the image to determine whether the image meets the macroscopic object recognition condition, which is used to identify the object in the region of interest. If it is satisfied, the drone is controlled to continue to execute the macroscopic shooting plan. The macroscopic object recognition condition may include a success rate of an object of a set scale, and the set scale may be set according to the size of a single photovoltaic unit in the photovoltaic module.

[0093] Step S306: if the image does not meet the macroscopic object recognition condition, mark the image and its corresponding position that do not meet the macroscopic object recognition condition.

[0094] Step S307, the macroscopic shooting scheme is adjusted to obtain a mesoscopic shooting scheme, which is used to re-shoot images whose marks do not meet the macroscopic object recognition conditions. Compared with the macroscopic shooting scheme, the mesoscopic shooting scheme can be set to have a denser flight route, a lower flight altitude, and a lower flight speed, so as to obtain a mesoscopic image with a range that can better reflect the details of the object than the macroscopic image.

[0095] Step S308, after completing the macro shooting plan, controlling the drone to execute the meso shooting plan to replace the images marked as not meeting the macro object recognition condition.

[0096] The above macro shooting scheme is designed according to the area of ​​interest obtained by pre-analysis of geographic information data, and the drone can obtain the macro images required for design planning more efficiently and accurately. Considering that the macro image may not meet the macro object recognition conditions, the images and positions that do not meet the macro object recognition conditions are marked, and the meso images obtained by the subsequent execution of the meso shooting scheme are used to supplement them, which not only fully improves the shooting efficiency but also meets the accuracy of image target recognition. Compared with the existing drone cruise shooting method, it is more flexible and more load-bearing for the planning and design of photovoltaic power generation systems.

[0097] Figure 4 1 is a schematic diagram of identifying a macro image in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention. The macro image identification process may include:

[0098] Step S401, extracting a recognition target image centered on the region of interest from the macro image; the recognition target image includes both the region of interest and the environmental area outside the region of interest that may affect the operation or construction of the photovoltaic module. The process of recognizing the target image can use target detection algorithms such as YOLO and CenterNet, use heat maps to predict the center point of the object, and obtain relevant attributes of the object, such as height, width, posture and orientation, through center point feature regression.

[0099] Step S402, object recognition is performed on the recognition target image to determine whether the region of interest meets the conditions for photovoltaic module layout; the photovoltaic module layout conditions may include: the shape of the region of interest meets the shape requirements of the photovoltaic module, the area of ​​the region of interest meets the area requirements of the photovoltaic module, the orientation of the region of interest meets the light-facing requirements of the photovoltaic module, and the occlusion of the region of interest does not affect the light-receiving requirements of the photovoltaic module. Object recognition of the recognition target image includes both the recognition of the region where the photovoltaic module is arranged and the recognition of the surrounding environment area.

[0100] Step S403: if the conditions for arranging photovoltaic modules are met, the area of ​​interest is marked as a candidate construction area.

[0101] After the above-mentioned macro image recognition, one or more candidate construction areas are obtained, that is, the site selection and screening of the candidate construction areas are completed. This process can efficiently complete the planning work of an area to be planned. After determining the candidate construction area, the method of this embodiment can also generate a three-dimensional model of the candidate construction area based on the survey image, and superimpose the model of the alternative construction plan on the three-dimensional model of the alternative construction area to generate a display model of the household photovoltaic system. Construction owners can quickly and intuitively obtain photovoltaic construction results, reduce survey costs, and greatly facilitate the further promotion of household photovoltaic systems. Figure 5 This is a schematic diagram of surveying and photographing a candidate construction area in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention. The surveying and photographing process may include:

[0102] Step S501, segmenting an initial image of the candidate construction area from the macro image. The initial survey shooting can be performed using the default cruise mode of the drone. For example, the drone shoots the candidate construction area at a certain height in a preset scanning shooting mode (such as flying back and forth along a straight line). The initial image obtained is used to gain a general understanding of the area to be built.

[0103] Step S502, set marker points for the initial image, and divide the initial image into objects based on the marker points. At least the installation object can be determined, and the regional area and terrain characteristics of the installation object can be estimated. The marker points can be obtained by analyzing the initial image, for example, by finding obvious marker points using pixel threshold segmentation, edge detection, regional growth clustering, machine learning model classification, etc. The marker points may include points such as demarcation points, edge points, feature intensity change points, cluster centers or representative points. In addition to the installation objects (installation roofs, installation walls, idle ground, etc.), the objects obtained by object division may also include the basic objects of the installation objects (installed building objects, walls, supports, etc.). The estimated regional area and terrain characteristics of the installation object are used for the design of the microscopic shooting plan, not the final survey results.

[0104] Step S503, designing a microscopic shooting plan according to the area and terrain characteristics of the installation object.

[0105] Step S504, control the drone to survey and photograph the installation object according to the microscopic shooting scheme, and obtain a survey image of the installation object. The survey image can be multiple images at different angles, reflecting the conditions at different angles of the candidate construction area. Compared with the macroscopic shooting scheme and the mesoscopic shooting scheme, the microscopic shooting scheme conducts a closer survey and photography around the installation object from multiple angles, and it can perform surround photography at different heights.

[0106] The survey image of the installation object can be obtained by stitching the survey image of the installation object and the survey image of the surrounding environment object. In some embodiments, the survey image stitching method includes: performing angle matching on the survey image of the installation object and the survey image of the surrounding environment object to find multiple pairs of matching images; performing grayscale histogram equalization processing and geometric distortion elimination on the multiple pairs of matching images to obtain multiple groups of images to be stitched; extracting feature information from the multiple groups of images to be stitched, stitching and fusing the images according to the feature information, and obtaining survey images of the candidate construction areas from multiple angles.

[0107] Angle matching can be done by searching for images with similar shooting directions and shooting ranges through the flight records of drones. The matching images found have similar angles, which can reduce the image calculations (including image translation, scaling, and twisting) in the stitching process and improve processing efficiency. Grayscale histogram equalization and geometric distortion elimination can eliminate the problems caused by geometric distortion and color brightness differences in image processing.

[0108] Feature information is extracted from multiple groups of images to be spliced, and an image transformation model can be established based on the matched features, and finally transformation mapping is performed. The transformation mapping of the method of this embodiment first uses point, line and angle features to estimate the homography matrix of the global transformation, and pre-aligns the spliced ​​images; then the image is gridded, and the grid deformation is constrained by the energy function to achieve grid refinement alignment. Since the shooting angle is matched in advance, the complexity of the image transformation model can be reduced. The image alignment process can use a feature-based image registration method. Alignment is performed by adding feature line segments and feature points of the shooting angle, which greatly reduces the amount of calculation. For example, the scale-invariant feature transformation algorithm (ScaleInvariant Feature Transform, referred to as SIFT) can be used to determine the feature points of the image and the angle information of the feature points; for example, the line segment detector (LSD) can be used to extract the straight line characteristics of the image.

[0109] Image stitching and fusion are performed based on feature information to convert each pixel of the transformed image into the same image, and then the image fusion method is used to perform pixel fusion on the transition area of ​​the stitched image to optimize the image stitching quality.

[0110] The survey images obtained in the above steps reflect the characteristics of the installation object and the surrounding environment objects from different angles. Compared with the prior art where surveyors manually set up marker points and aerial photography points for the candidate construction area, the accuracy is higher and the dependence on the surveyor's operation is reduced.

[0111] The above steps use drones to take pictures of the candidate construction area to obtain survey images. With the help of the drone's flexibility and low cost, the field survey results can be obtained quickly and efficiently. On this basis, a three-dimensional model of the candidate construction area is further generated based on the survey image; the three-dimensional model is analyzed to obtain survey feature data of the photovoltaic panel laying area, solving the problem of increased survey difficulty and inaccurate survey data caused by the harsh on-site environment. Figure 6 This is a schematic diagram of photovoltaic assembly layout design based on survey images in a photovoltaic power generation system planning and design method according to an embodiment of the present invention. The layout design process may include:

[0112] Step S601, generating a three-dimensional model of a candidate construction area according to the survey image;

[0113] Step S602, analyzing the three-dimensional model to obtain survey feature data of the photovoltaic panel laying area;

[0114] Step S603, performing simulation design on the photovoltaic panel laying area according to the survey characteristic data to obtain one or more alternative construction plans;

[0115] Step S604: superimpose the model of the alternative construction solution on the three-dimensional model of the alternative construction area to generate a display model of the photovoltaic project to be built.

[0116] By superimposing the model of the alternative construction plan on the three-dimensional model of the alternative construction area, the design method of this embodiment generates a display model of the household photovoltaic system. Construction owners can quickly and intuitively obtain the results of the photovoltaic construction, reduce survey costs, and greatly facilitate the further promotion of household photovoltaic systems. For the alternative construction areas of photovoltaic systems with complex terrain, traditional terrain and edge measurement methods are difficult to operate, have low accuracy, and have low data transmission efficiency with computer automatic design software. The planning and design method of the photovoltaic power generation system of this embodiment achieves more efficient surveying by optimizing the shooting process and data processing process of the drone.

[0117] Figure 7The present invention is a schematic diagram of a process for generating a three-dimensional model of a candidate construction area in a planning and design method for a photovoltaic power generation system according to an embodiment of the present invention. The step of generating a three-dimensional model of a candidate construction area may include:

[0118] Step S701, discretize the survey image using set grid points to generate point cloud data of the candidate construction area. One discretization method is: discretize using three-dimensional space grid points, and then sample a point in each grid point. Each small grid contains several points, and the point closest to the center point of the grid is taken as the discrete sampling point.

[0119] Step S702, using the point cloud data to construct a surface to obtain a surface model; the data captured by the drone can be processed to obtain sufficient point cloud data. Through surface construction, a surface model in the form of a point cloud can be obtained.

[0120] Step S703, perform object recognition on the survey image to determine the object boundary. The object recognition results include: installation objects (installation roofs, installation walls, vacant ground, etc.), basic objects of installation objects (installed building objects, walls, supports, etc.), surrounding environment objects, etc.

[0121] Step S704: compare the object boundary with the surface model and perform contour segmentation on the surface model.

[0122] Step S705, visualize the surface model after contour segmentation to obtain a three-dimensional model. The specific visualization process may include: performing object entity processing on the surface model after contour segmentation to obtain contour surfaces of multiple objects; collecting color and pattern features of multiple objects in the survey image; performing appearance processing on the contour surfaces of multiple objects according to the color and pattern features to obtain a three-dimensional model of the candidate construction area.

[0123] An optional process of visualizing a surface model after contour segmentation to obtain a three-dimensional model may include: performing object entity processing on the surface model after contour segmentation to obtain contour surfaces of multiple objects; collecting color and pattern features of multiple objects in the survey image; performing appearance processing on the contour surfaces of multiple objects according to the color and pattern features to obtain a three-dimensional model of the candidate construction area. The three-dimensional model of the candidate construction area finally obtained is similar to the actual visual state of the candidate construction area, which is convenient for the construction owner of the photovoltaic system to intuitively understand the situation of the candidate construction area. After obtaining the three-dimensional model of the alternative construction area, it also includes: performing data statistics on the three-dimensional model to obtain data information of the three-dimensional model; assigning attribute information to multiple objects of the three-dimensional model. The data information of the three-dimensional model includes: coordinates, elevation data, area, length, height, slope, orientation, etc., which can be read from the three-dimensional model. Object attribute information includes: project name, object type, etc.

[0124] The above-mentioned step S603 of simulating the design of the photovoltaic panel laying area may include: performing technical indicator estimation calculations and economic indicator estimation calculations of various optional photovoltaic laying methods for the photovoltaic panel laying area according to the survey characteristic data; and performing performance comparison of different photovoltaic laying methods according to the results of the technical indicator estimation calculations and the economic indicator estimation calculations. According to the performance comparison results, one or more alternative construction plans are selected from various optional photovoltaic laying methods; the unit model and installation model of the photovoltaic panel are retrieved, and the unit model and the installation model are spliced ​​according to the alternative construction plan to obtain the model of the alternative construction plan, and the model of the alternative construction plan is spliced ​​on the three-dimensional model of the alternative construction area.

[0125] In the above simulation design process, technical indicators may include: installed capacity (kWp), comprehensive reduction coefficient (%), annual utilization hours (h), annual average power generation (MWh) and multi-year average utilization hours (h). The technical indicator estimation calculation process may include: determining the installed capacity of each solar photovoltaic panel arrangement method, determining the installed capacity restriction conditions based on the grid access equipment information obtained, and re-modifying the photovoltaic laying method to reduce the installed capacity if the installed capacity of various optional photovoltaic laying methods exceeds the installed capacity restriction conditions; determining the comprehensive reduction coefficient based on the type of solar photovoltaic panels; calculating the annual power generation of the photovoltaic power station based on the parameters such as the photovoltaic power station lighting resource conditions, installed capacity, comprehensive reduction coefficient and array maintenance rate under different installation methods; converting the annual utilization hours based on the calculated annual power generation of the photovoltaic system; calculating the multi-year average power generation and the multi-year average annual utilization hours based on the annual utilization hours of the photovoltaic power station and the comprehensive reduction coefficient.

[0126] The economic indicator estimation calculation estimates investment and financial indicators based on various optional photovoltaic laying methods, such as the failure rate and maintenance cost of various optional photovoltaic laying methods, component price (yuan / Wp), total static investment, static investment per unit of electricity, and financial rate of return.

[0127] The alternative construction plans can be output according to the advantages and disadvantages of different indicators. The optional photovoltaic laying methods may include: solar cell types (monocrystalline silicon, polycrystalline silicon, amorphous silicon), installation methods (such as fixed installation, single-axis tracking, dual-axis tracking), photovoltaic panel inclination, photovoltaic panel spacing, etc.

[0128] After one or more alternative construction plans are determined, the model of the alternative construction plan may be superimposed on the three-dimensional model of the alternative construction area. The process may include:

[0129] The specific steps of superimposing the model of the alternative construction scheme on the three-dimensional model of the alternative construction area may include: retrieving the unit model and the installation model of the photovoltaic panel; splicing the unit model and the installation model according to the alternative construction scheme to obtain the model of the alternative construction scheme; and splicing the model of the alternative construction scheme on the three-dimensional model of the alternative construction area.

[0130] The above-mentioned photovoltaic power generation system planning and design method superimposes the model of the alternative construction plan on the three-dimensional model of the alternative construction area to generate a display model of the household photovoltaic system. The construction owner can quickly and intuitively obtain the photovoltaic construction results, reduce the survey cost, and greatly facilitate the further promotion of household photovoltaic systems.

[0131] By surveying and designing the candidate construction areas in the planned area one by one, the design effects of multiple photovoltaic projects to be built are obtained. In some embodiments, all photovoltaic projects to be built in the planned area can be integrated and displayed on the overall model of the planned area, so as to achieve an intuitive display of the overall photovoltaic power generation system in the planned area. In some embodiments, the planning and design method of the photovoltaic power generation system can also cluster all photovoltaic projects to be built, determine the distance between the power generation of the photovoltaic project and the grid access equipment and the power load, and further optimize the number and location of photovoltaic projects.

[0132] This embodiment also provides a computer program product 112 , a computer readable storage medium 113 , and a computer device 114 . Figure 8 is a schematic diagram of a computer program product 112 according to one embodiment of the present invention, Fig. 9 is a schematic diagram of a computer-readable storage medium 113 according to an embodiment of the present invention, Fig.10 is a schematic block diagram of a computer device 114 according to one embodiment of the present invention.

[0133] The computer program product 112 includes a computer program 111, which implements the steps of any of the above-mentioned methods for planning and designing a photovoltaic power generation system when executed by the processor 310. The computer-readable storage medium 113 stores the above-mentioned computer program 111, which implements the steps of any of the above-mentioned methods for planning and designing a photovoltaic power generation system when executed by the processor 310. The computer device 114 may include a memory 320, a processor 310, and a computer program 111 stored in the memory 320 and running on the processor 310.

[0134] The computer program 111 used to perform the operations of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, configuration data of an integrated circuit, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages.

[0135] The computer program 111 may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, in order to perform various aspects of the present invention, electronic circuits including, for example, programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuits.

[0136] In the description of this embodiment, the computer program product 112 is a related product including the computer program 111 .

[0137] For the purposes of the description of this embodiment, the computer-readable storage medium 113 is a tangible device capable of retaining and storing the computer program 111, which may be any device that can contain, store, communicate, propagate or transmit the program 111 for use with or in conjunction with an instruction execution system, device or apparatus. More specific examples (a non-exhaustive list) of the computer-readable storage medium 113 include the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination of the foregoing.

[0138] At this point, those skilled in the art should recognize that, although multiple exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications that conform to the principles of the present invention can still be directly determined or derived based on the content disclosed in the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and recognized as covering all these other variations or modifications.

Claims

1. A planning and design method for a photovoltaic power generation system, characterized in that include: Obtain geographic information data of the area to be planned; Controlling the drone to perform macroscopic cruising photography of the area to be planned according to the geographic information data to obtain a macroscopic image of the area to be planned; Identify the macro image to determine one or more candidate construction areas that meet the conditions for arranging photovoltaic modules; Controlling the drone to survey and photograph each of the candidate construction areas to obtain a survey image; as well as The photovoltaic assembly layout is designed according to the survey image.

2. The planning and design method of a photovoltaic power generation system according to claim 1, wherein: The step of obtaining geographic information data of the area to be planned includes: Obtaining the boundary range of the area to be planned; The geographic information data within the boundary is queried from the geographic information data source through a preset application program interface.

3. The planning and design method of a photovoltaic power generation system according to claim 1, wherein: The step of controlling the drone to perform macroscopic cruising photography of the area to be planned according to the geographic information data comprises: Preliminarily analyzing the geographic information data to preliminarily identify an area of ​​interest that is larger than the minimum paving area of ​​the photovoltaic modules; Designing a macro shooting scheme of the drone according to the location and area of ​​the region of interest, wherein the macro shooting scheme includes: a flight route, a flight altitude, a flight speed, and shooting parameters; The drone is controlled to execute the macro shooting scheme to shoot, so as to obtain the macro image.

4. The planning and design method for a photovoltaic power generation system according to claim 3, wherein: The step of controlling the drone to execute the macro shooting scheme to shoot includes: Acquire an image captured by the drone executing the macro shooting scheme; Performing a quality check on the image to determine whether the image satisfies a macroscopic object recognition condition, wherein the macroscopic object recognition condition is used to perform object recognition on the region of interest; If the conditions are met, the drone is controlled to continuously execute the macro shooting scheme; If not, the image and its corresponding position are marked as not meeting the macro object recognition condition.

5. The planning and design method for a photovoltaic power generation system according to claim 4, wherein: After the step of marking the images and their corresponding positions that do not meet the macroscopic object recognition condition, the method further includes: The macroscopic shooting scheme is adjusted to obtain a mesoscopic shooting scheme, wherein the mesoscopic shooting scheme is used to reshoot the image whose mark does not satisfy the macroscopic object recognition condition; After completing the macroscopic shooting scheme, the drone is controlled to execute the mesoscopic shooting scheme to replace the image marked as not satisfying the macroscopic object recognition condition.

6. The planning and design method for a photovoltaic power generation system according to claim 3, wherein: The step of identifying the macro image comprises: Extracting a recognition target image centered on the region of interest from the macro image; Performing object recognition on the recognition target image to determine whether the region of interest meets the photovoltaic assembly arrangement conditions; If the photovoltaic module layout conditions are met, the area of ​​interest is marked as a candidate construction area.

7. The planning and design method for a photovoltaic power generation system according to claim 1, wherein: The step of controlling the drone to survey and photograph each candidate construction area includes: Segmenting an initial image of the candidate construction area from the macro image; Setting marker points on the initial image, and dividing the initial image into objects based on the marker points to at least determine the installation object, and estimate the area and terrain characteristics of the installation object; Design a microscopic shooting plan according to the area and terrain characteristics of the installation object; The unmanned aerial vehicle is controlled to perform survey and photography around the installation object according to the microscopic photography scheme to obtain a survey image of the installation object.

8. The planning and design method for a photovoltaic power generation system according to claim 7, wherein: The step of designing the layout of photovoltaic components according to the survey image comprises: generating a three-dimensional model of the candidate construction area according to the survey image; Analyzing the three-dimensional model to obtain survey characteristic data of the photovoltaic panel laying area; Performing simulation design on the photovoltaic panel laying area according to the survey characteristic data to obtain one or more alternative construction plans; The model of the alternative construction scheme is superimposed on the three-dimensional model of the alternative construction area to generate a display model of the photovoltaic project to be built.

9. The planning and design method of a photovoltaic power generation system according to claim 8, characterized in that: The step of generating the three-dimensional model of the candidate construction area according to the survey image comprises: discretize the survey image using set grid points to generate point cloud data of the candidate construction area; Using the point cloud data to construct a surface to obtain a surface model; Performing object recognition on the survey image to determine the object boundary; Comparing the object boundary with the surface model, and performing contour segmentation on the surface model; The surface model after contour segmentation is visualized to obtain the three-dimensional model.

10. The planning and design method of a photovoltaic power generation system according to claim 9, characterized in that: The step of visualizing the surface model after contour segmentation to obtain the three-dimensional model comprises: Performing object entity processing on the surface model after the contour segmentation to obtain contour surfaces of multiple objects; collecting color and pattern features of the plurality of objects in the survey image; The appearance of the contour surfaces of the multiple objects is processed according to the color and pattern features to obtain a three-dimensional model of the candidate construction area.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for planning and designing a photovoltaic power generation system according to any one of claims 1 to 10 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that When the computer program is executed by a processor, the steps of the photovoltaic power generation system planning and design method described in any one of claims 1 to 10 are implemented.

13. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the photovoltaic power generation system planning and design method according to any one of claims 1 to 10.

Images