A view hierarchy-based photovoltaic power station monitoring point control method and system

Abstract

The application relates to the technical field of photovoltaic power stations, and discloses a control method and system for a monitoring point of a photovoltaic power station based on view grading, which comprises the following steps: acquiring infrared image data and visible light image data of a photovoltaic module, and determining first positioning data of a thermal abnormal point; based on the first positioning data and second positioning data of each monitoring device in the photovoltaic power station, dividing each monitoring device into a main monitoring device and an auxiliary monitoring device; acquiring vertical elevation data of the thermal abnormal point, and determining first control instructions of the main monitoring device and second control instructions of the auxiliary monitoring device based on the vertical elevation data and the first positioning data; controlling the main monitoring device based on the first control instructions, controlling the auxiliary monitoring device based on the second control instructions, performing target image acquisition on the thermal abnormal point, positioning the thermal abnormal point through infrared and visible light fusion, dividing the main and auxiliary monitoring devices based on the geometric relationship of sight lines and differentially configuring control instructions, and realizing multi-view synchronous acquisition and brightness consistency compensation.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power plant technology, and more specifically, to a control method and system for monitoring points in a photovoltaic power plant based on view hierarchy. Background Technology

[0002] Photovoltaic power plant module thermal anomaly monitoring refers to the technical means of identifying abnormal temperature areas on the surface of photovoltaic modules through imaging technology, locating fault points, and ensuring power generation efficiency. It is widely used in the operation and maintenance of centralized and distributed photovoltaic power plants.

[0003] Existing technologies mostly employ fixed monitoring points or single-point inspection by drones, using single-view infrared thermal imagers to collect component temperature distribution images for anomaly identification. However, the layout of monitoring equipment in existing technologies does not consider the spatial differences of thermal anomaly points, resulting in insufficient image resolution when the viewpoint is obstructed or the observation angle is poor. In addition, the lack of a coordinated control mechanism between the main and auxiliary monitoring equipment leads to time asynchrony issues in multi-view image acquisition, affecting the accuracy of stereoscopic observation. Furthermore, the attenuation of light intake caused by tilted shooting is not effectively compensated, resulting in a mismatch between the brightness of the auxiliary viewpoint image and the main viewpoint, affecting the quality of multi-view fusion and the accuracy of fault diagnosis. Summary of the Invention

[0004] To address the aforementioned technical issues, this application aims to provide a control method and system for photovoltaic power plant monitoring points based on view hierarchy. This method locates thermal anomaly points by fusing infrared and visible light, divides primary and secondary monitoring equipment based on line-of-sight geometry, and differentiates control commands to achieve multi-view synchronous acquisition and brightness consistency compensation.

[0005] To achieve the above objectives, the present invention provides a control method for monitoring points of a photovoltaic power plant based on view hierarchy, comprising: Acquire infrared image data and visible light image data of photovoltaic modules, and determine the first location data of thermal anomaly points based on the infrared image data and the visible light image data; Based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into main monitoring devices and auxiliary monitoring devices. Obtain the vertical elevation data of the thermal anomaly point, and determine the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first positioning data; Based on the first control command, the main monitoring device is controlled, and based on the second control command, the auxiliary monitoring device is controlled to perform target image acquisition on the thermal anomaly point.

[0006] Further, infrared image data and visible light image data of the photovoltaic module are acquired, and first location data of the thermal anomaly point is determined based on the infrared image data and the visible light image data, including: Temperature field gradient analysis is performed on the infrared image data to extract regions of abrupt temperature changes as candidate thermal anomaly regions. The visible light image data is divided into a photovoltaic module array grid, and a mapping relationship is established between each segmented region and the physical number of the module. The candidate thermal anomaly region is registered to the corresponding segmented region of the visible light image data, and the first location data of the thermal anomaly point is obtained by querying the preset geographic coordinate mapping table based on the component physical number.

[0007] Furthermore, based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into main monitoring devices and auxiliary monitoring devices, including: Based on the first positioning data and each of the second positioning data, calculate the line-of-sight pitch angle and line-of-sight horizontal azimuth angle of each monitoring device relative to the thermal anomaly point; Monitoring devices whose line-of-sight pitch angle is greater than a preset pitch angle threshold and whose line-of-sight horizontal azimuth angle is less than a preset azimuth angle threshold are identified as candidate monitoring devices. The monitoring device with the largest line-of-sight pitch angle is selected from the candidate monitoring devices as the main monitoring device, and the remaining candidate monitoring devices are selected as the auxiliary monitoring devices.

[0008] Further, the vertical elevation data of the thermal anomaly point is acquired, and based on the vertical elevation data and the first positioning data, a first control command for the main monitoring device and a second control command for the auxiliary monitoring device are determined, including: Based on the first positioning data, the first ground projection distance between the thermal anomaly point and the main monitoring device and the second ground projection distance between the thermal anomaly point and the auxiliary monitoring device are determined. Calculate the projection difference between the first ground projection spacing and the second ground projection spacing, and determine the image transmission time difference based on the projection difference and the vertical elevation data; A first pointing angle is determined based on the vertical elevation data and the first ground projection spacing, and a second pointing angle is determined based on the vertical elevation data and the second ground projection spacing. A first acquisition resolution is determined based on the first ground projection spacing, and a second acquisition resolution is determined based on the second ground projection spacing; The first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity are used as the first control command; The second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference are used as the second control command.

[0009] Further, controlling the main monitoring device based on the first control command and controlling the auxiliary monitoring device based on the second control command includes: Send a first control command to the main monitoring device, the first control command including the first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity; In response to the first control command, the main monitoring device adjusts the gimbal attitude and lens focal length, and then performs main-view image acquisition on the thermal anomaly point.

[0010] Furthermore, it also includes: Send a second control command to the auxiliary monitoring device. The second control command includes the second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference. The auxiliary monitoring device responds to the second control command by adjusting the gimbal attitude and lens focal length, and after delaying the image transmission time difference, performs auxiliary viewpoint image acquisition on the thermal anomaly point.

[0011] Further, target image acquisition is performed on the thermal anomaly points, including: A time synchronization benchmark for data acquisition between the main monitoring device and the auxiliary monitoring device is established based on the image transmission time difference. The main monitoring device acquires the main view image at the time of acquisition synchronization, and the auxiliary monitoring device acquires the auxiliary view image after the time difference of image transmission is delayed. The frames are aligned and fused to generate the multi-view joint image of the thermal anomaly point.

[0012] Furthermore, it also includes: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

[0013] To achieve the above objectives, the present invention also provides a control system for photovoltaic power plant monitoring points based on view hierarchy, comprising: The data positioning module is used to acquire infrared image data and visible light image data of photovoltaic modules, and determine the first positioning data of thermal anomaly points based on the infrared image data and the visible light image data. The device division module is used to divide each monitoring device into a main monitoring device and an auxiliary monitoring device based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station. The instruction generation module is used to acquire the vertical elevation data of the thermal anomaly point, and determine the first control instruction of the main monitoring device and the second control instruction of the auxiliary monitoring device based on the vertical elevation data and the first positioning data. The monitoring and control module is used to control the main monitoring device based on the first control command and the auxiliary monitoring device based on the second control command to perform target image acquisition on the thermal anomaly point.

[0014] Furthermore, it also includes: The compensation matching module is used for: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The system acquires infrared and visible light image data of photovoltaic modules to determine the first location data of thermal anomalies. Based on the first location data and the second location data of each monitoring device in the photovoltaic power station, the monitoring devices are divided into main monitoring devices and auxiliary monitoring devices. The system acquires the vertical elevation data of the thermal anomalies and determines the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first location data. The system controls the main monitoring device based on the first control command and the auxiliary monitoring device based on the second control command to perform target image acquisition on the thermal anomalies. The system locates the thermal anomalies by fusing infrared and visible light. The system divides the main and auxiliary monitoring devices based on the line-of-sight geometry and configures the control commands differently to achieve multi-view synchronous acquisition and brightness consistency compensation. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a control method for photovoltaic power plant monitoring points based on view hierarchy is shown in an embodiment of the present invention. Figure 2 A schematic diagram of a control system for photovoltaic power plant monitoring points based on view hierarchy is shown in an embodiment of the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0018] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0021] The following is a description of preferred embodiments of the present invention in conjunction with the accompanying drawings.

[0022] like Figure 1 As shown, an embodiment of the present invention discloses a control method for monitoring points of a photovoltaic power plant based on view hierarchy, comprising: S110: Acquire infrared image data and visible light image data of photovoltaic modules, and determine the first location data of thermal anomaly points based on the infrared image data and the visible light image data; In some embodiments of this application, infrared image data and visible light image data of a photovoltaic module are acquired, and first location data of thermal anomalies are determined based on the infrared image data and the visible light image data, including: Temperature field gradient analysis is performed on the infrared image data to extract regions of abrupt temperature changes as candidate thermal anomaly regions. The visible light image data is divided into a photovoltaic module array grid, and a mapping relationship is established between each segmented region and the physical number of the module. The candidate thermal anomaly region is registered to the corresponding segmented region of the visible light image data, and the first location data of the thermal anomaly point is obtained by querying the preset geographic coordinate mapping table based on the component physical number.

[0023] Specifically, infrared image data is acquired by an infrared thermal imager mounted on a drone, while visible light image data is simultaneously acquired by a high-definition visible light camera mounted on the same drone. When determining the initial location data for thermal anomalies, a temperature field gradient analysis is first performed on the infrared image data: the Sobel operator is used to calculate the temperature gradient amplitude, and a temperature gradient threshold of 5 degrees Celsius per meter is set (this threshold is determined statistically based on the uniformity of surface temperature distribution during normal operation of photovoltaic modules; the surface temperature difference of normal modules is usually less than 3 degrees Celsius per meter, and a difference exceeding 5 degrees Celsius per meter indicates the presence of hot spots or bypass diode failures). Connected regions with gradient amplitudes exceeding this threshold are marked as candidate thermal anomaly regions. Simultaneously, the visible light image data is divided into a grid of photovoltaic module arrays: based on the straight-line features of the module borders (Hough transform detection, angular resolution 1 degree). An array grid is established with a resolution of 1 pixel to divide the image into sub-regions corresponding to physical components. A mapping relationship is established between each segmented region and the physical number of the component (e.g., A-01-03 represents the 1st row and 3rd column of region A). Candidate thermal anomaly regions are registered to the corresponding segmented regions of the visible light image data through affine transformation (based on UAV GPS coordinates and camera intrinsic and extrinsic parameter calibration). Based on the component physical number, a preset geographic coordinate mapping table is queried (this table is stored in the power station GIS database and contains the WGS84 coordinates of the four corner points of each component). The coordinates of the component center point are taken as the first positioning data (longitude, latitude, and altitude) of the thermal anomaly point.

[0024] This application's solution uses dual-modal fusion positioning of infrared temperature gradient and visible light grid mapping to convert thermal anomaly areas in the image space into precise locations in the power plant's geographic coordinate system. This solves the problem of unclear fault location caused by the lack of component identification in single infrared images, and establishes a unique correspondence between thermal anomaly points and physical component numbers and geographic coordinates, providing a spatial reference for subsequent monitoring equipment scheduling.

[0025] S120: Based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into a main monitoring device and an auxiliary monitoring device; In some embodiments of this application, based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into a main monitoring device and an auxiliary monitoring device, including: Based on the first positioning data and each of the second positioning data, calculate the line-of-sight pitch angle and line-of-sight horizontal azimuth angle of each monitoring device relative to the thermal anomaly point; Monitoring devices whose line-of-sight pitch angle is greater than a preset pitch angle threshold and whose line-of-sight horizontal azimuth angle is less than a preset azimuth angle threshold are identified as candidate monitoring devices. The monitoring device with the largest line-of-sight pitch angle is selected from the candidate monitoring devices as the main monitoring device, and the remaining candidate monitoring devices are selected as the auxiliary monitoring devices.

[0026] Specifically, the monitoring equipment consists of pan-tilt-zoom (PTZ) high-definition cameras deployed within the photovoltaic power station. The second positioning data (longitude, latitude, and installation height) of each monitoring device is measured and calibrated using a total station with an accuracy of ±0.05 meters and stored in the equipment management database. Based on the first positioning data (coordinates of the thermal anomaly point) and each second positioning data point, the line-of-sight elevation angle θ and horizontal azimuth angle φ of each monitoring device relative to the thermal anomaly point are calculated: Elevation angle θ = arctan((H_device - H_target) / D_horizontal), where H_device is the installation height of the monitoring device, H_target is the height of the thermal anomaly point (elevation of the module surface), and D_horizontal is the horizontal ground projection distance between the device and the thermal anomaly point; the horizontal azimuth angle φ is the angle between the device's optical axis projected onto the horizontal plane and the due north direction. Monitoring devices with a line-of-sight pitch angle greater than a preset pitch angle threshold of 30 degrees (this threshold ensures that the monitoring equipment observes the surface of the module from a top-down angle, avoiding occlusion between modules caused by looking up; 30 degrees is the minimum pitch angle to ensure the visibility of surface targets in engineering practice) and an angle between the horizontal azimuth of the line of sight and the normal direction of the surface of the thermal anomaly point (for photovoltaic modules installed 15 degrees south of east, the normal direction is an azimuth angle of 195 degrees) less than a preset azimuth angle threshold of 45 degrees (this threshold ensures that the monitoring equipment is within the visible cone of the front of the module, avoiding image distortion and reflection interference caused by side observation) are identified as candidate monitoring devices. From the candidate monitoring devices, the monitoring device with the largest line-of-sight pitch angle is selected as the primary monitoring device (the largest pitch angle means the vertical viewing angle is closest to directly above, resulting in the least image perspective distortion and the highest resolution). The remaining candidate monitoring devices are designated as auxiliary monitoring devices (providing supplementary side-view perspectives for stereoscopic observation and occlusion compensation).

[0027] This application's solution uses line-of-sight geometric constraint screening and pitch angle maximization optimization to ensure that the main monitoring equipment is always in the optimal vertical observation position of the thermal anomaly point, while auxiliary monitoring equipment is distributed to supplement the lateral viewpoint, thus constructing a multi-view observation system with main and auxiliary equipment working together to solve the problems of blind spots and uneven resolution caused by the rigid layout of fixed monitoring points.

[0028] S130: Obtain the vertical elevation data of the thermal anomaly point, and determine the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first positioning data; In some embodiments of this application, obtaining the vertical elevation data of the thermal anomaly point, and determining the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first positioning data, includes: Based on the first positioning data, the first ground projection distance between the thermal anomaly point and the main monitoring device and the second ground projection distance between the thermal anomaly point and the auxiliary monitoring device are determined. Calculate the projection difference between the first ground projection spacing and the second ground projection spacing, and determine the image transmission time difference based on the projection difference and the vertical elevation data; A first pointing angle is determined based on the vertical elevation data and the first ground projection spacing, and a second pointing angle is determined based on the vertical elevation data and the second ground projection spacing. A first acquisition resolution is determined based on the first ground projection spacing, and a second acquisition resolution is determined based on the second ground projection spacing; The first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity are used as the first control command; The second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference are used as the second control command.

[0029] Specifically, vertical elevation data is obtained by fusing RTK-GNSS module on a UAV with lidar point cloud data, characterizing the altitude of the thermal anomaly point relative to the power station's reference elevation surface. Based on the first positioning data, the first ground projection distance D1 (horizontal Euclidean distance, in meters) between the thermal anomaly point and the main monitoring equipment, and the second ground projection distance D2 between the thermal anomaly point and the auxiliary monitoring equipment are determined. Based on the vertical elevation data ΔH and the first ground projection distance D1, the first pointing tilt angle α1 = arctan(ΔH / D1) is determined. This tilt angle is the angle at which the gimbal tilt axis of the monitoring equipment needs to be adjusted so that the optical axis is aligned with the thermal anomaly point; similarly, the second pointing tilt angle α2 = arctan(ΔH / D2) is determined. The first acquisition resolution is determined based on the first ground projection spacing D1: resolution is inversely proportional to distance. A baseline distance of 50 meters corresponds to a baseline resolution of 1080P. When D1 is less than or equal to 50 meters, the first acquisition resolution is 1080P; when D1 is greater than 50 meters but less than or equal to 100 meters, it drops to 720P (1280×720 pixels); and when D1 is greater than 100 meters, it drops to 480P (640×480 pixels). This classification is based on the spatial resolution attenuation characteristic of optical imaging systems with distance (at the same focal length, doubling the distance halves the resolution). Similarly, the second acquisition resolution is determined based on D2. The projection difference ΔD = |D1-D2| between the first ground projection spacing D1 and the second ground projection spacing D2 is calculated. Based on the projection difference ΔD, the image transmission time difference Δt = ΔD×0.001 is determined to compensate for the acquisition time deviation caused by the different spatial positions of the main and auxiliary equipment.

[0030] This application's solution uses geometric coupling calculation of ground projection spacing and vertical elevation to transform spatial position differences into quantifiable control commands (tilt angle, clarity, time difference), ensuring that the control parameters of the main and auxiliary monitoring equipment strictly correspond to the actual spatial coordinates of the thermal anomaly points. This avoids pointing deviations and image blurring caused by manual adjustments based on experience, and ensures geometric consistency and temporal synchronization of multi-view acquisition.

[0031] S140: Based on the first control command, control the main monitoring device and based on the second control command, control the auxiliary monitoring device to perform target image acquisition on the thermal anomaly point.

[0032] In some embodiments of this application, controlling the main monitoring device based on the first control command and controlling the auxiliary monitoring device based on the second control command includes: Send a first control command to the main monitoring device, the first control command including the first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity; In response to the first control command, the main monitoring device adjusts the gimbal attitude and lens focal length, and then performs main-view image acquisition on the thermal anomaly point.

[0033] In some embodiments of this application, it also includes: Send a second control command to the auxiliary monitoring device. The second control command includes the second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference. The auxiliary monitoring device responds to the second control command by adjusting the gimbal attitude and lens focal length, and after delaying the image transmission time difference, performs auxiliary viewpoint image acquisition on the thermal anomaly point.

[0034] Specifically, a first control command is sent to the main monitoring device. This command is encapsulated via the ONVIF protocol and includes a first pointing tilt angle α1 and a first optical focal length f1 corresponding to the first acquisition resolution (obtained from a resolution level lookup table: 1080P corresponds to a focal length of 50mm, 720P to 35mm, and 480P to 25mm; this correspondence is determined by the optical parameter calibration of the monitoring device). A second control command is sent to the auxiliary monitoring device, including a second pointing tilt angle α2, a second optical focal length f2 corresponding to the second acquisition resolution, and an image transmission time difference Δt (in milliseconds, with an accuracy of 1 millisecond). Responding to the first control command, the main monitoring device drives the pan-tilt motor to adjust the tilt angle to α1 within 200 milliseconds, and simultaneously drives the zoom motor to adjust the focal length to f1. After aligning the optical axis with the thermal anomaly point, it performs main-view image acquisition (exposure time is automatically adjusted, ISO 100 to ISO 800 range). The auxiliary monitoring equipment responds to the second control command, synchronously adjusts the pan-tilt attitude and lens focal length, and triggers exposure after a delay Δt (i.e., Δt milliseconds after the main equipment starts exposure) to perform auxiliary viewpoint image acquisition on thermal anomalies.

[0035] This application's solution uses protocol-based control command encapsulation and precise timing delay triggering to enable the main and auxiliary monitoring devices to form a collaborative acquisition mode of "main device taking pictures first, auxiliary device taking pictures after a delay," which solves the problem of random misalignment of acquisition time caused by multiple devices operating independently, and lays the timing foundation for subsequent frame alignment and image fusion.

[0036] In some embodiments of this application, target image acquisition is performed on the thermal anomaly points, including: A time synchronization benchmark for data acquisition between the main monitoring device and the auxiliary monitoring device is established based on the image transmission time difference. The main monitoring device acquires the main view image at the time of acquisition synchronization, and the auxiliary monitoring device acquires the auxiliary view image after the time difference of image transmission is delayed. The frames are aligned and fused to generate the multi-view joint image of the thermal anomaly point.

[0037] Specifically, a synchronization reference T0 is established between the main monitoring device and the auxiliary monitoring device based on the image transmission time difference Δt (taking the exposure start time of the main device as the reference zero point); the main view image acquired by the main monitoring device at time T0 and the auxiliary view image acquired by the auxiliary monitoring device at time T0+Δt are aligned in frame time, with the alignment accuracy controlled within ±1 frame; the scale-invariant feature transform (SIFT) algorithm is used to extract feature points (such as component border corners and busbar intersections) in the two images, and mismatched points are removed by the RANSAC algorithm (1000 iterations, error threshold of 3 pixels), and the homography transformation matrix between the two views is calculated; based on the homography matrix, the auxiliary view image is projected onto the main view image plane, and a weighted average fusion (main view weight 0.6, auxiliary view weight 0.4) is used to generate a multi-view joint image of thermal anomalies. This joint image combines the high-resolution frontal details of the main view and the side-view stereo information of the auxiliary view.

[0038] This application's solution unifies asynchronously acquired multi-view images to the same spatiotemporal reference by frame-time alignment and geometric projection fusion, generating a joint image containing depth cues. This solves the ambiguity problem of single-view images being unable to distinguish between hot spots on the component surface and shadow occlusion on the back panel, and improves the reliability of determining the cause of thermal anomalies.

[0039] In some embodiments of this application, it also includes: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

[0040] Specifically, based on the angle between the second pointing tilt angle α2 and the horizontal reference plane (i.e., |α2|), the tilt compensation coefficient k = 1 / cos(|α2|) of the auxiliary monitoring device is determined. This coefficient represents the magnification factor of the effective imaging area during tilted shooting relative to that during upright shooting. When |α2| is greater than 45 degrees, the value of k is greater than 1.414, indicating a significant attenuation of the effective light intake. The exposure time and photosensitive gain of the auxiliary monitoring device are dynamically adjusted based on the compensation coefficient k: the exposure time is adjusted to t_aux = t_main × k, where t_main is the automatic exposure time of the main monitoring device (in milliseconds); the photosensitive gain is adjusted to G_aux = G_main × k, where G_main is the automatic photosensitive gain of the main monitoring device (in decibels). This compensation ensures that the average brightness of the auxiliary viewing angle image matches that of the main viewing angle image, avoiding image dimness caused by the increased optical path length and reduced effective light-receiving area of ​​the sensor due to tilted shooting. This guarantees that the brightness consistency of the auxiliary viewing angle image matches that of the main viewing angle image.

[0041] This application's solution uses trigonometric geometry to convert the pitch angle into a light intake compensation coefficient, dynamically adjusting the exposure parameters of auxiliary equipment. This solves the problem of image brightness mismatch caused by differences in observation angles during multi-view fusion, ensuring the brightness continuity of the multi-view joint image at the fusion boundary and improving the accuracy of thermal anomaly region segmentation and feature extraction.

[0042] To further illustrate the technical concept of this invention, the technical solution of this invention will now be described in conjunction with specific application scenarios.

[0043] Correspondingly, such as Figure 2 As shown, this application also provides a control system for photovoltaic power plant monitoring points based on view hierarchy, including: The data positioning module 210 is used to acquire infrared image data and visible light image data of photovoltaic modules, and determine the first positioning data of thermal anomaly points based on the infrared image data and the visible light image data. The device division module 220 is used to divide each monitoring device into a main monitoring device and an auxiliary monitoring device based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station. The instruction generation module 230 is used to acquire the vertical elevation data of the thermal anomaly point, and determine the first control instruction of the main monitoring device and the second control instruction of the auxiliary monitoring device based on the vertical elevation data and the first positioning data. The monitoring and control module 240 is used to control the main monitoring device based on the first control command and the auxiliary monitoring device based on the second control command to perform target image acquisition on the thermal anomaly point.

[0044] In some embodiments of this application, it also includes: The compensation matching module is used for: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

[0045] In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0046] Although the invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the embodiments disclosed in this invention can be combined with each other in any way. The fact that not all of these combinations are described in this specification is merely for the sake of brevity and resource conservation.

[0047] It will be understood by those skilled in the art that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A control method for monitoring points of a photovoltaic power plant based on view hierarchy, characterized in that, include: Acquire infrared image data and visible light image data of photovoltaic modules, and determine the first location data of thermal anomaly points based on the infrared image data and the visible light image data; Based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into main monitoring devices and auxiliary monitoring devices. Obtain the vertical elevation data of the thermal anomaly point, and determine the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first positioning data; Based on the first control command, the main monitoring device is controlled, and based on the second control command, the auxiliary monitoring device is controlled to perform target image acquisition on the thermal anomaly point.

2. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Acquire infrared and visible light image data of photovoltaic modules, and determine first location data of thermal anomalies based on the infrared and visible light image data, including: Temperature field gradient analysis is performed on the infrared image data to extract regions of abrupt temperature changes as candidate thermal anomaly regions. The visible light image data is divided into a photovoltaic module array grid, and a mapping relationship is established between each segmented region and the physical number of the module. The candidate thermal anomaly region is registered to the corresponding segmented region of the visible light image data, and the first location data of the thermal anomaly point is obtained by querying the preset geographic coordinate mapping table based on the component physical number.

3. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station, each monitoring device is divided into main monitoring devices and auxiliary monitoring devices, including: Based on the first positioning data and each of the second positioning data, calculate the line-of-sight pitch angle and line-of-sight horizontal azimuth angle of each monitoring device relative to the thermal anomaly point; Monitoring devices whose line-of-sight pitch angle is greater than a preset pitch angle threshold and whose line-of-sight horizontal azimuth angle is less than a preset azimuth angle threshold are identified as candidate monitoring devices. The monitoring device with the largest line-of-sight pitch angle is selected from the candidate monitoring devices as the main monitoring device, and the remaining candidate monitoring devices are selected as the auxiliary monitoring devices.

4. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Obtain the vertical elevation data of the thermal anomaly point, and determine the first control command of the main monitoring device and the second control command of the auxiliary monitoring device based on the vertical elevation data and the first positioning data, including: Based on the first positioning data, the first ground projection distance between the thermal anomaly point and the main monitoring device and the second ground projection distance between the thermal anomaly point and the auxiliary monitoring device are determined. Calculate the projection difference between the first ground projection spacing and the second ground projection spacing, and determine the image transmission time difference based on the projection difference and the vertical elevation data; A first pointing angle is determined based on the vertical elevation data and the first ground projection spacing, and a second pointing angle is determined based on the vertical elevation data and the second ground projection spacing. A first acquisition resolution is determined based on the first ground projection spacing, and a second acquisition resolution is determined based on the second ground projection spacing; The first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity are used as the first control command; The second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference are used as the second control command.

5. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Controlling the main monitoring device based on the first control command and controlling the auxiliary monitoring device based on the second control command includes: Send a first control command to the main monitoring device, the first control command including the first pointing tilt angle and the first optical focal length corresponding to the first acquisition clarity; In response to the first control command, the main monitoring device adjusts the gimbal attitude and lens focal length, and then performs main-view image acquisition on the thermal anomaly point.

6. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 5, characterized in that, Also includes: Send a second control command to the auxiliary monitoring device. The second control command includes the second pointing tilt angle, the second optical focal length corresponding to the second acquisition clarity, and the image transmission time difference. The auxiliary monitoring device responds to the second control command by adjusting the gimbal attitude and lens focal length, and after delaying the image transmission time difference, performs auxiliary viewpoint image acquisition on the thermal anomaly point.

7. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Perform target image acquisition on the thermal anomaly points, including: A time synchronization benchmark for data acquisition between the main monitoring device and the auxiliary monitoring device is established based on the image transmission time difference. The main monitoring device acquires the main view image at the time of acquisition synchronization, and the auxiliary monitoring device acquires the auxiliary view image after the time difference of image transmission is delayed. The frames are aligned and fused to generate the multi-view joint image of the thermal anomaly point.

8. The control method for photovoltaic power plant monitoring points based on view hierarchy according to claim 1, characterized in that, Also includes: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

9. A control system for photovoltaic power plant monitoring points based on view hierarchy, applied to the control method for photovoltaic power plant monitoring points based on view hierarchy as described in any one of claims 1-8, characterized in that, include: The data positioning module is used to acquire infrared image data and visible light image data of photovoltaic modules, and determine the first positioning data of thermal anomaly points based on the infrared image data and the visible light image data. The device division module is used to divide each monitoring device into a main monitoring device and an auxiliary monitoring device based on the first positioning data and the second positioning data of each monitoring device in the photovoltaic power station. The instruction generation module is used to acquire the vertical elevation data of the thermal anomaly point, and determine the first control instruction of the main monitoring device and the second control instruction of the auxiliary monitoring device based on the vertical elevation data and the first positioning data. The monitoring and control module is used to control the main monitoring device based on the first control command and the auxiliary monitoring device based on the second control command to perform target image acquisition on the thermal anomaly point.

10. The control system for photovoltaic power plant monitoring points based on view hierarchy according to claim 9, characterized in that, Also includes: The compensation matching module is used for: The viewing angle tilt compensation coefficient of the auxiliary monitoring device is determined based on the angle between the second pointing tilt angle and the horizontal reference plane. The exposure time and photosensitive gain of the auxiliary monitoring equipment are dynamically compensated based on the aforementioned viewing angle tilt compensation coefficient.

Images