Photovoltaic equipment automatic operation and maintenance management system and method based on computer vision

Abstract

The invention discloses a photovoltaic equipment automatic operation and maintenance management system and method based on computer vision, and relates to the technical field of photovoltaic equipment operation and maintenance management, and the method specifically comprises the following steps: obtaining the operation state information of each power generation assembly in a photovoltaic panel in real time when the photovoltaic panel is affected by dynamic shielding, and carrying out the analysis after obtaining, evaluating the power generation efficiency reduction degree of each power generation assembly in the photovoltaic panel due to dynamic shielding, and dividing each power generation assembly in the photovoltaic panel into a low-influence assembly, a medium-influence assembly and a high-influence assembly; and according to the division result of each power generation assembly in the photovoltaic panel, constructing a power generation efficiency optimization mechanism, and respectively carrying out different optimization measures on the low-influence assembly, the medium-influence assembly and the high-influence assembly. According to the method, the problem that evaluation and optimization are affected by dynamic shielding of the photovoltaic equipment is solved, and accurate improvement of power generation efficiency and stable adaptation of system operation are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic equipment operation and maintenance management, and specifically relates to a computer vision-based automated operation and maintenance management system and method for photovoltaic equipment. Background Art

[0002] Photovoltaic equipment refers to a device that converts solar energy into electrical energy through photovoltaic panels and is widely used in the field of solar power generation. The operation of photovoltaic equipment depends on multiple components, such as photovoltaic panels, inverters, battery energy storage systems, etc. The stability of its performance directly affects the power generation efficiency and energy utilization rate. With the continuous expansion of the scale of photovoltaic power generation, the traditional manual operation and maintenance mode can no longer meet the requirements of efficient and precise management. Manual inspections are not only time-consuming and labor-intensive, but also due to the complexity of the environment, it is often difficult to detect potential faults or problems in real time, resulting in increased downtime and operation and maintenance costs. Therefore, the automated operation and maintenance management of photovoltaic equipment has become an inevitable trend. Through the introduction of computer vision technology, automated operation and maintenance can monitor the operating status of equipment in real time and use image recognition algorithms to accurately locate equipment faults, such as problems like stains, cracks, or blockages, avoiding the limitations of manual inspections. Computer vision technology can not only detect equipment all-weather and without dead angles, but also adapt to complex lighting changes and environmental factors, significantly improving the accuracy and timeliness of fault diagnosis. Based on computer vision-based automated operation and maintenance management, it can significantly reduce labor costs, improve operation and maintenance efficiency, ensure that photovoltaic equipment can operate efficiently and stably under various environmental conditions, and thus guarantee the continuous and stable output of photovoltaic power generation.

[0003] Existing computer vision-based automated operation and maintenance management technologies for photovoltaic equipment collect real-time images of the operating status of photovoltaic equipment by mounting high-resolution cameras or drones and transmit the captured images to the background for processing. The background system relies on deep learning and image recognition algorithms to analyze the surface of photovoltaic panels in the images, automatically identify possible fault features, such as abnormal conditions like stains, cracks, hot spots, blockages, etc., and generate a fault diagnosis report by annotating and classifying the abnormal areas. At the same time, these systems can combine environmental monitoring data (such as light intensity, temperature, wind speed, etc.) to comprehensively evaluate the operating environment of photovoltaic equipment and predict potential risks or trends in operating efficiency changes. Some advanced technologies also introduce environmental adaptability correction algorithms to improve the accuracy of fault recognition under different weather and lighting conditions by performing dynamic lighting adjustment, contrast enhancement, etc. on the images. Finally, the system pushes the analysis results to the operation and maintenance personnel through the cloud data analysis platform, provides specific maintenance suggestions or automatically generates maintenance work orders, thereby realizing the efficient, precise, and fully automated operation and maintenance management of photovoltaic equipment and significantly improving the overall operating efficiency and reliability of the equipment.

[0004] The existing technologies have the following deficiencies: During the operation of a photovoltaic device, when clouds move rapidly or obstacles in the environment (such as tree branches) swing, each power generation component in the photovoltaic panel, which is the core power generation unit, will be affected by dynamic shading, resulting in uneven light intensity and frequent changes in the local shading area and duration. This dynamic shading directly acts on the power generation components in the photovoltaic panel, causing fluctuations in its power generation efficiency in a short period of time. At the same time, the shading range and change speed are difficult to predict due to complex environmental conditions, thus forming the characteristics of dynamic shading. Since multiple power generation components of the photovoltaic device are interconnected, the efficiency fluctuations of a single power generation component will further affect the overall operation balance of the device. However, the existing computer vision-based automated operation and maintenance management technology for photovoltaic devices mainly relies on static image information, and can only roughly estimate the impact of shading on the overall photovoltaic device, lacking the ability to dynamically capture and accurately evaluate the downward trend of the power generation efficiency of each power generation component in the photovoltaic panel. This technical limitation will result in power generation components with high shading losses not being identified and optimized in time, and effective shading compensation measures cannot be taken, which not only reduces the overall power generation efficiency of the photovoltaic device, but also exacerbates the material aging and performance degradation of the photovoltaic panel due to some power generation components being in a high shading state for a long time, thereby increasing the later operation and maintenance costs and repair difficulties.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a computer vision-based automated operation and maintenance management system and method for photovoltaic devices to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: A computer vision-based automated operation and maintenance management method for photovoltaic devices, specifically including the following steps: During the operation of the photovoltaic device, use computer vision technology to detect in real time whether there is a phenomenon of dynamic shading on the surface of the photovoltaic panel, which is the core power generation unit. When it is detected that there is a phenomenon of dynamic shading on the surface of the photovoltaic panel, determine each power generation component used for power generation in the photovoltaic panel; Obtain in real time the operation state information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic shading, and analyze it after obtaining, evaluate the degree of power generation efficiency decline of each power generation component in the photovoltaic panel caused by dynamic shading, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components, and high-impact components; According to the classification results of each power generation component in the photovoltaic panel, construct a power generation efficiency optimization mechanism, and take different optimization measures for low-impact components, medium-impact components, and high-impact components respectively; During the process of optimizing each power generation component in the photovoltaic panel by the power generation efficiency optimization mechanism, the optimization adjustment feedback information of each power generation component is obtained in real time, analyzed after acquisition, evaluated whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component reaches the expectation, and the power generation efficiency optimization mechanism is optimized according to the evaluation result; Comprehensively monitor and analyze the influence of dynamic shading on the photovoltaic panel, the implementation effect of the optimization measures, and the overall operation data of the photovoltaic equipment, continuously improve the power generation efficiency optimization mechanism, and improve the operation efficiency and dynamic adaptability of the photovoltaic equipment.

[0008] Preferably, the operation state information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic shading is obtained in real time, analyzed after acquisition, the degree of power generation efficiency decline of each power generation component in the photovoltaic panel caused by dynamic shading is evaluated, and each power generation component in the photovoltaic panel is divided into low-impact components, medium-impact components and high-impact components, which specifically include the following steps: Obtain the operation state information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic shading in real time, and perform preprocessing after acquisition; Extract the light shading characteristic information and power generation power fluctuation characteristic information in the preprocessed operation state information, analyze after extraction, and generate the shading intensity index and power generation power fluctuation coefficient of each power generation component respectively; Construct a power generation efficiency decline evaluation model for the generated shading intensity index and power generation power fluctuation coefficient of each power generation component, generate the power generation evaluation coefficient of each power generation component by weighted summation, analyze after generation, evaluate the degree of power generation efficiency decline of each power generation component in the photovoltaic panel caused by dynamic shading, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components.

[0009] Preferably, the acquisition logic of the shading intensity index and power generation power fluctuation coefficient of each power generation component is as follows: Extract the light shading characteristic information in the preprocessed operation state information, specifically including the proportion of the shaded area of each power generation component surface in the total surface at different times during a period of time when the photovoltaic panel is affected by dynamic shading, the light intensity received by each power generation component, and the change rate of the light intensity received by each power generation component, and use functions 、 and to represent them respectively according to the time series, is the time point, represents during a period of time when the photovoltaic panel is affected by dynamic shading the proportion of the shaded area of the th power generation component surface in the total surface at the Indicates the light intensity received by the th power generation component at a certain moment during the process of the photovoltaic panel being affected by dynamic shading, Indicates the change rate of the light intensity received by the th power generation component at a certain moment during the process of the photovoltaic panel being affected by dynamic shading. The defined time period is , , where is a positive integer; ; Calculate the shading intensity index of each power generation component. The specific calculation formula is as follows: In the formula, is the shading intensity index of the th power generation component; Extract the power generation power fluctuation characteristic information from the preprocessed operating state information, specifically including the actual power output value of each power generation component at different moments during the process of the photovoltaic panel being affected by dynamic shading, the change range of the actual power output value, and the maximum power output value of each power generation component under standard test conditions. And represent the actual power output value and the change range of the actual power output value of each power generation component at different moments during the process of the photovoltaic panel being affected by dynamic shading in time series with functions and respectively. Indicates the actual power output value of the th power generation component at a certain moment during the process of the photovoltaic panel being affected by dynamic shading, Indicates the change range of the actual power output value of the th power generation component at a certain moment during the process of the photovoltaic panel being affected by dynamic shading. Calibrate the maximum power output value of the th power generation component under standard test conditions as ; Calculate the power generation power fluctuation coefficient of each power generation component. The specific calculation formula is as follows: In the formula, is the power generation power fluctuation coefficient of the th power generation component.

[0010] Preferably, for the shading intensity index and the power generation power fluctuation coefficient of each generated power generation component, a power generation efficiency decline evaluation model is constructed, and the power generation evaluation coefficient of each power generation component is generated by weighted summation , according to the formula: , where and are the non-zero weight coefficients of the shading intensity index and the power generation power fluctuation coefficient of each power generation component respectively, and ; Compare the generated power generation evaluation coefficient of each power generation component with the pre-set power generation evaluation coefficient threshold interval , evaluate the degree of power generation efficiency decline of each power generation component in the photovoltaic panel due to dynamic shading according to the comparison result, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components. The specific comparison analysis and division are as follows: If , the degree of power generation efficiency decline of this power generation component in the photovoltaic panel due to dynamic shading is low, and this power generation component is divided into low-impact components; If , the degree of power generation efficiency decline of this power generation component in the photovoltaic panel due to dynamic shading is medium, and this power generation component is divided into medium-impact components; If , the degree of power generation efficiency decline of this power generation component in the photovoltaic panel due to dynamic shading is high, and this power generation component is divided into high-impact components.

[0011] Preferably, according to the division results of each power generation component in the photovoltaic panel, a power generation efficiency optimization mechanism is constructed, specifically: according to the division results of low-impact components, medium-impact components and high-impact components, different optimization adjustment parameters are set respectively to form a power generation efficiency optimization mechanism; this optimization mechanism is based on the dynamic feedback of the power generation evaluation coefficient of each power generation component and the shading intensity index and the power generation power fluctuation coefficient, and through the pre-set optimization rules, automatically determines the operation parameter adjustment method and adjustment range of the component; Different optimization measures are taken for low-impact components, medium-impact components and high-impact components respectively, specifically: The optimization measure for low-impact components is: use the operation maintenance parameters in the optimization mechanism to maintain the current operation state without parameter adjustment; The optimization measure for medium-impact components is: use the operation adjustment parameters in the optimization mechanism to clearly adjust the operation parameters of the power generation component, including re-setting the current-voltage characteristic value and implementing the shading compensation strategy to reduce the impact of dynamic shading on the power generation performance; The optimization measures for high-impact components are as follows: Use the operation optimization parameters in the optimization mechanism to focus on adjusting the operation mode of the power generation components, including dynamically changing the distribution of the shaded areas, reallocating the operation load of the components, and implementing full-coverage compensation measures for the shaded areas to ensure the restoration of power generation performance.

[0012] Preferably, during the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the optimization adjustment feedback information of each power generation component is obtained in real time, analyzed after acquisition, evaluated whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component reaches the expectation, and the power generation efficiency optimization mechanism is optimized according to the evaluation result. The specific steps are as follows: During the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the optimization adjustment feedback information of each power generation component is obtained in real time and preprocessed after acquisition; Extract the optimization output characteristic information and optimization response characteristic information from the optimization adjustment feedback information of each preprocessed power generation component, analyze after extraction, and respectively generate the optimization output consistency index and optimization response sensitivity coefficient of each power generation component; Construct an optimization effect evaluation model for the generated optimization output consistency index and optimization response sensitivity coefficient of each power generation component, generate the optimization evaluation coefficient of each power generation component through weighted summation, analyze after generation, evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component reaches the expectation, and optimize the power generation efficiency optimization mechanism according to the evaluation result.

[0013] Preferably, the acquisition logic of the optimization output consistency index and optimization response sensitivity coefficient of each power generation component is as follows: Extract the optimization output characteristic information from the optimization adjustment feedback information of each preprocessed power generation component, specifically including the actual output power of each power generation component at different moments within a period of time during the optimization process, the change range of the actual output power, and the target power value set by the power generation efficiency optimization mechanism for each power generation component, and respectively calibrate them as 、 and , represents the actual output power of the th power generation component at the th moment within a period of time during the optimization process, represents the change range of the actual output power of the th power generation component at the th moment within a period of time during the optimization process, represents the target power value set by the power generation efficiency optimization mechanism for the th power generation component, , , and are all positive integers; Calculate the optimization output consistency index of each power generation component. The specific calculation formula is as follows: In the formula, is the optimization output consistency index of the th power generation component; Extract the optimization response characteristic information in the optimized adjustment feedback information of each preprocessed power generation component, specifically including the percentage change in the ratio of the actual input energy to the output energy of each power generation component at different times during a period in the optimization process, the change rate of the power generation efficiency of each power generation component, and the time interval from receiving the optimization instruction to achieving the adjustment effect of each power generation component, and calibrate them as , and , represents the percentage change in the ratio of the actual input energy to the output energy of the th power generation component at the th moment during a period in the optimization process, represents the change rate of the power generation efficiency of the th power generation component at the th moment during a period in the optimization process, represents the time interval from receiving the optimization instruction to achieving the adjustment effect of the th power generation component in the optimization process; Calculate the optimization response sensitivity coefficient of each power generation component. The specific calculation formula is as follows: In the formula, is the optimization response sensitivity coefficient of the th power generation component.

[0014] Preferably, construct an optimization effect evaluation model for the generated optimization output consistency index and the optimization response sensitivity coefficient of each power generation component, and generate the optimization evaluation coefficient of each power generation component through weighted summation. According to the formula: , where and are the non-zero weight coefficients of the optimization output consistency index and the optimization response sensitivity coefficient of each power generation component respectively, and ; The generated optimization evaluation coefficient Compare with the optimization evaluation coefficient thresholds of each preset power generation component Compare with them, evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectation according to the comparison result, and optimize the power generation efficiency optimization mechanism according to the evaluation result. The specific comparison and analysis are as follows: If , the optimization effect of the power generation efficiency optimization mechanism on this power generation component meets the expectation, and there is no need to optimize the power generation efficiency optimization mechanism; If , the optimization effect of the power generation efficiency optimization mechanism on this power generation component does not meet the expectation, and it is necessary to optimize the power generation efficiency optimization mechanism, specifically including: readjusting the operation parameter setting in the optimization strategy; improving the feedback information processing mechanism to enhance the real-time performance and accuracy of the optimization adjustment; dynamically updating the optimization effect evaluation model to adapt to the current conditions based on new operation data; optimizing the execution process to ensure that the power generation efficiency optimization mechanism can improve the power generation performance of each power generation component by reducing the response delay and improving the execution efficiency of the optimization instruction.

[0015] Preferably, the computer vision-based automated operation and maintenance management system for photovoltaic equipment includes a dynamic occlusion detection module, an operation status evaluation module, a power generation efficiency optimization module, an optimization effect feedback module, and a comprehensive monitoring and improvement module; The dynamic occlusion detection module, during the operation of the photovoltaic equipment, uses computer vision technology to detect in real time whether there is a dynamic occlusion phenomenon on the surface of the photovoltaic panel, which is the core power generation unit. When detecting a dynamic occlusion phenomenon on the surface of the photovoltaic panel, determine each power generation component used for power generation in the photovoltaic panel; The operation status evaluation module, in real time, obtains the operation status information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic occlusion, and analyzes it after obtaining it, evaluates the degree of power generation efficiency decline of each power generation component in the photovoltaic panel caused by dynamic occlusion, and divides each power generation component in the photovoltaic panel into low-impact components, medium-impact components, and high-impact components; The power generation efficiency optimization module, according to the classification result of each power generation component in the photovoltaic panel, constructs a power generation efficiency optimization mechanism, and takes different optimization measures for low-impact components, medium-impact components, and high-impact components respectively; The optimization effect feedback module, during the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, obtains the optimization adjustment feedback information of each power generation component in real time, and analyzes it after obtaining it, evaluates whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectation, and optimizes the power generation efficiency optimization mechanism according to the evaluation result; Comprehensive monitoring and improvement module, which comprehensively monitors and analyzes the impact of dynamic shading of photovoltaic panels, the implementation effect of optimization measures, and the overall operation data of photovoltaic equipment, continuously improves the power generation efficiency optimization mechanism, and enhances the operation efficiency and dynamic adaptability of photovoltaic equipment.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are as follows: 1. By using computer vision technology, the present invention realizes real-time detection of dynamic shading of photovoltaic equipment and accurate identification of the state of power generation components, significantly improving the capture ability and analysis accuracy of dynamic shading. Combining the acquisition and modeling of the shading intensity index and the power generation power fluctuation coefficient, it can accurately evaluate the impact of dynamic shading on the power generation efficiency of each power generation component and classify components with different degrees of influence. By implementing differentiated optimization measures for low-impact components, medium-impact components, and high-impact components, such as operating parameter adjustment and shading compensation, it further ensures the improvement of the overall power generation performance of photovoltaic panels. At the same time, during the optimization implementation process, the system evaluates and real-time optimizes the power generation efficiency optimization mechanism through dynamic analysis of optimization adjustment feedback information, realizing closed-loop management of the operating state of photovoltaic equipment. This technical effect of multi-link linkage provides stable and efficient operation guarantee for photovoltaic equipment in a complex dynamic environment.

[0017] 2. The present invention adopts a calculation model of the shading intensity index and the power generation power fluctuation coefficient, comprehensively quantifies the impact of dynamic shading on power generation components, and provides a scientific basis for classification and optimization. Another advantage is intelligence. Through the automatic adjustment of the power generation efficiency optimization mechanism and the dynamic update of the optimization effect evaluation model, the photovoltaic equipment can continuously optimize its operation strategy according to real-time operation data, enhancing the system's self-adaptability and decision-making ability.

[0018] 3. The present invention covers the whole process from shading detection to optimization adjustment, forming a closed-loop management from problem identification to solution. Differentiated optimization measures effectively improve the overall power generation efficiency, reduce equipment aging and maintenance costs, and enhance the adaptability of the system in a dynamic environment. Compared with the prior art, this solution not only improves performance but also achieves better economic benefits. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a flow schematic diagram of the photovoltaic equipment automatic operation and maintenance management system and method based on computer vision of the present invention.

[0021] Figure 2 This is a schematic diagram of the modules of the computer vision-based automated operation and maintenance management system and method for photovoltaic devices of the present invention. Detailed implementation manners

[0022] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0023] The present invention provides a Figure 1 computer vision-based automated operation and maintenance management method for photovoltaic devices as shown below, which specifically includes the following steps: During the operation of the photovoltaic device, use computer vision technology to continuously detect whether there is a dynamic occlusion on the surface of the photovoltaic panel, which is the core power generation unit. When it is detected that there is a dynamic occlusion on the surface of the photovoltaic panel, determine each power generation component used for power generation in the photovoltaic panel; Continuously detect whether there is a dynamic occlusion on the surface of the photovoltaic panel through computer vision technology, which specifically includes: arranging high-precision cameras in the installation area of the photovoltaic device for real-time image acquisition, and performing preprocessing on the images such as denoising, color correction, and edge enhancement. Using the image segmentation algorithm of the convolutional neural network, divide the image into a normal power generation area and a suspected occlusion area, and further analyze whether there is occlusion in combination with brightness changes, texture features, and boundary characteristics. At the same time, perform temporal analysis on consecutive frame images, extract the occlusion trajectory and duration, and comprehensively capture the range, intensity, and change characteristics of the dynamic occlusion. Dynamic occlusion mainly refers to the occlusion phenomenon on the surface of the photovoltaic panel caused by factors such as cloud movement and tree branch shaking, which is characterized by continuously changing occlusion range, intensity, and duration, and has a significant impact on power generation efficiency.

[0024] After detecting the dynamic occlusion phenomenon, further determine the power generation components in the photovoltaic panel and their occlusion states. Through the region positioning algorithm, match the surface image of the photovoltaic panel with the power generation component partition model, accurately identify the corresponding region of each component in the image, and verify the analysis results in combination with operation data such as light intensity distribution or temperature change. At the same time, through the cross-analysis of the relationship between the dynamic occlusion trajectory and the component position, locate the occluded components and the occlusion degree, so as to eliminate the interference of non-power generation areas such as the frame or bracket, and ensure the accuracy of the identification.

[0025] Accurately identifying the occluded power generation components is the key to ensuring the efficient operation of photovoltaic equipment. Dynamic occlusion can lead to a decrease in component efficiency, affecting not only individual components but also potentially spreading to other components, reducing the overall power generation efficiency and stability. If the occluded components cannot be accurately identified, it will be difficult to evaluate their performance and implement targeted optimizations, potentially resulting in uncompensated occlusion losses in a timely manner, increasing equipment aging and operation and maintenance costs. This technical solution combines computer vision and component recognition technologies to provide high-quality data support for subsequent evaluation and optimization, ensuring the stable and efficient operation of the equipment in a dynamic environment.

[0026] Real-time obtain the operation status information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic occlusion, and analyze it after obtaining. Evaluate the degree of decrease in power generation efficiency of each power generation component in the photovoltaic panel caused by dynamic occlusion, and classify each power generation component in the photovoltaic panel into low-impact components, medium-impact components, and high-impact components; In this embodiment, real-time obtain the operation status information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic occlusion, and analyze it after obtaining. Evaluate the degree of decrease in power generation efficiency of each power generation component in the photovoltaic panel caused by dynamic occlusion, and classify each power generation component in the photovoltaic panel into low-impact components, medium-impact components, and high-impact components, which specifically includes the following steps: Real-time obtain the operation status information of each power generation component in the photovoltaic panel during the process of the photovoltaic panel being affected by dynamic occlusion, and perform preprocessing after obtaining; Real-time obtain the operation status information of each power generation component in the photovoltaic panel during the process of being affected by dynamic occlusion can be achieved by combining a variety of sensors on the photovoltaic equipment and computer vision technology. Specifically, first, arrange high-precision cameras on the surface of the photovoltaic panel to continuously collect the surface images of the photovoltaic panel and capture the image features of dynamic occlusion; at the same time, equip light intensity sensors and power monitoring modules to respectively record the light intensity and actual power generation data of each power generation component in real time. These data have time series characteristics and can reflect the change process of dynamic occlusion and power fluctuations. The image data collected by the camera is processed in real time through computer vision algorithms to segment the photovoltaic panel into regions of each power generation component, and then identify and label the lighting conditions and occlusion regions of each power generation component; at the same time, the data of the light intensity sensor is combined with the image processing results to mark the lighting level of each power generation component; the data of the power monitoring module is used to obtain the change of power generation. In these ways, the lighting conditions, occlusion conditions, and power generation power fluctuation information of each power generation component are integrated into operation status information and updated in real time to adapt to dynamic environmental changes.

[0027] After the operating status information is acquired, it needs to be preprocessed to ensure the accuracy and efficiency of subsequent analysis. The main goal of preprocessing is to eliminate noise and redundant information in the data, improve data quality, and standardize the data format for unified analysis. The specific preprocessing operations include the following aspects: First, image data preprocessing. Noise interference in the image is eliminated through denoising algorithms (such as Gaussian filtering), the contour of the power generation component area in the image is enhanced using edge detection algorithms, and the feature information of the power generation component area is extracted using image segmentation algorithms. Second, light intensity data preprocessing. The sliding window averaging method is used to smooth the fluctuations of the light intensity and eliminate the errors caused by short-term random changes. Third, power generation power data preprocessing. Anomaly detection (such as removing outliers that significantly exceed the normal range) and interpolation completion (such as using linear interpolation algorithms to complete missing data for cases where the data acquisition interval is too large) are performed on the power data. Through these preprocessing steps, the operating status information can be transformed into high-quality and standardized analysis inputs, providing reliable data support for subsequent feature information extraction and parameter calculation.

[0028] Extract the light occlusion characteristic information and power generation power fluctuation characteristic information from the preprocessed operating status information, and perform analysis after extraction to generate the occlusion intensity index and power generation power fluctuation coefficient for each power generation component respectively; Extracting the light occlusion characteristic information and power generation power fluctuation characteristic information from the preprocessed operating status information can be achieved by combining data analysis and computer vision techniques. First, for the light occlusion characteristic information, from the preprocessed image data, using region segmentation algorithms in computer vision (such as segmentation models based on convolutional neural networks), the surface of the photovoltaic panel is segmented into specific areas of each power generation component, and the occlusion area boundary of each component is identified; further, the occlusion area ratio is obtained by calculating the pixel ratio of the occlusion area. At the same time, combined with the data of the light intensity sensor, the light intensity level and its relative change amount in the occlusion area are analyzed, and the light change rate within a period of time is calculated, so as to extract the light occlusion characteristic information, including data such as the occlusion area ratio, light intensity distribution, and light change rate. Second, for the power generation power fluctuation characteristic information, from the time series data of the power generation power monitoring module, statistical and signal processing algorithms are used to calculate the power fluctuation amplitude. For example, the principal components of the power change frequency are extracted through fast Fourier transform, or the standard deviation of the power fluctuation is calculated after smoothing the noise through moving average filtering; at the same time, the deviation ratio of the real-time power is calculated according to the reference maximum power, and the above results are comprehensively generated to obtain the key data reflecting the power generation power fluctuation characteristic. Through such an information extraction method, two types of characteristic information can be efficiently separated from the operating status information, providing accurate inputs for subsequent parameter calculation.

[0029] Construct a power generation efficiency decline evaluation model for the occlusion intensity index and power generation power fluctuation coefficient of each generated power generation component, generate the power generation evaluation coefficient of each power generation component through weighted summation, and analyze it after generation to evaluate the degree of power generation efficiency decline of each power generation component in the photovoltaic panel due to dynamic occlusion, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components.

[0030] In this embodiment, the acquisition logic of the occlusion intensity index and power generation power fluctuation coefficient of each power generation component is as follows: Extract the light occlusion characteristic information in the preprocessed operation state information, specifically including the proportion of the occluded area of each power generation component surface to the total surface at different times during a period when the photovoltaic panel is affected by dynamic occlusion, the light intensity received by each power generation component, and the change rate of the light intensity received by each power generation component, and use functions , and to represent them respectively according to the time series, is the time point, represents that during a period when the photovoltaic panel is affected by dynamic occlusion at the th time, the proportion of the occluded area of the th power generation component surface to the total surface, represents that during a period when the photovoltaic panel is affected by dynamic occlusion at the th time, the light intensity received by the th power generation component, represents that during a period when the photovoltaic panel is affected by dynamic occlusion at the th time, the change rate of the light intensity received by the th power generation component, and the defined time period is To obtain the three types of data, namely "the proportion of the shaded area on the surface of each power generation component in the total surface area, the light intensity received by each power generation component, and the change rate of the light intensity received by each power generation component" in real time, it can be achieved by combining computer vision technology and light sensors. Specifically, first, a high-precision camera installed on the photovoltaic device continuously captures images of the photovoltaic panel surface. Using image segmentation technology in computer vision, the surface of the photovoltaic panel is divided into independent areas of each power generation component, and the shaded parts on the surface of each component are detected. By calculating the ratio of the pixel area of the shaded part to the total pixel area of the power generation component, the proportion of the shaded area on the surface of each power generation component in the total surface area is determined in real time. Secondly, light intensity sensors installed on each power generation component can record the light intensity data received by the current component in real time, and these data will be aggregated through the sensor network to the central processing system for analysis. Finally, the change rate of the light intensity is achieved by analyzing the differences between the light intensity data at adjacent time points. The system processes the light intensity data of multiple consecutive samplings, extracts the change trend of the light intensity over time, and thus generates the change rate of the light intensity of each power generation component. This method of combining the camera and light sensors ensures a full-range dynamic monitoring of the shading and light conditions on the surface of the photovoltaic panel, providing accurate basic data for subsequent shading intensity analysis.

[0031] Compare the light intensities received by each power generation component at different moments within a period of time during the process of the photovoltaic panel being affected by dynamic shading, and calibrate the maximum value among them as ; Calculate the shading intensity index of each power generation component. The specific calculation formula is as follows: In the formula, is the shading intensity index of the th power generation component; Calculating the shading intensity index of each power generation component is to comprehensively quantify the influence degree of dynamic shading on the light conditions of a single power generation component and provide a reliable numerical basis for subsequent power generation efficiency evaluation. This formula captures the spatial, intensity, and dynamic change characteristics of shading through multi-level operation steps. Specifically, the integral operation is used to accumulate the shading effect within a given time period to reflect the dynamic change characteristics and time distribution of shading; the shading area ratio describes the spatial range of the shaded area on the surface of the photovoltaic panel, reflecting the spatial influence degree of shading; is a non-linear function that uses exponential operation to amplify the normalized value of the light intensity, ensuring that the shading effect in low light conditions is significantly highlighted, and at the same time avoiding the imbalance caused by direct linear accumulation in high light intensity; the change rate of light intensity It captures the dynamic fluctuation amplitude of the light intensity, reflecting the dynamic characteristics of the real-time changes in the photovoltaic module caused by occlusion. The overall calculation result is logarithmically processed on the average value of the time period, which can smooth the situation with weak occlusion influence, and at the same time make the result rise rapidly when the occlusion is significant, emphasizing the severity of the occlusion. This multi-level calculation logic enables the occlusion intensity index to comprehensively reflect the dynamic characteristics, time cumulative effect and spatial range of the occlusion, with strong adaptability and accuracy, providing a scientific basis for subsequent analysis.

[0032] The occlusion intensity index of the nth power generation module directly reflects the comprehensive degree of the influence of light on this module under dynamic occlusion conditions, and has a positive correlation with the degree of decline in its power generation efficiency. When is large, it indicates that the occlusion area ratio of this module is relatively high, the light intensity is relatively low, or the light intensity change rate is relatively large, and these factors will all lead to a significant decline in the power generation efficiency of this module; on the contrary, when is small, it indicates that the occlusion influence on this module is relatively light, and the influence on the power generation efficiency is relatively small. Therefore, by evaluating the size, the dynamic influence of occlusion on the power generation efficiency of each power generation module can be accurately quantified, providing a core basis for subsequent efficiency evaluation and module classification. For example, in the evaluation model of the decline in power generation efficiency, the value can be used as a weight factor, and combined with other characteristic data (such as the power fluctuation coefficient) to calculate and generate a power generation evaluation coefficient, so as to further accurately evaluate the degree of efficiency decline caused by occlusion and provide scientific guidance for subsequent optimization measures.

[0033] Extract the power generation power fluctuation characteristic information in the preprocessed operation status information, specifically including the actual power output values of each power generation module at different times during a period of time when the photovoltaic panel is affected by dynamic occlusion, the change amplitude of the actual power output values, and the maximum power output values of each power generation module under standard test conditions, and use the functions and to represent the actual power output values and the change amplitude of the actual power output values of each power generation module at different times during a period of time when the photovoltaic panel is affected by dynamic occlusion according to the time series respectively. represents the actual power output value of the nth power generation module at time during a period of time when the photovoltaic panel is affected by dynamic occlusion. represents the change amplitude of the actual power output value of the nth power generation module at The maximum power output value of each power generation component under standard test conditions is calibrated as ; To obtain the three types of data: "the actual power output value of each power generation component, the change range of the actual power output value, and the maximum power output value of each power generation component under standard test conditions" in real time, it can be achieved by combining a power sensor and a data processing system. First, install high-precision power sensors at the output end of each power generation component of the photovoltaic device. These sensors can monitor the actual power output value of the components in real time and record the data in the form of a time series, forming a dynamic data stream reflecting the power change of the components. Second, the change range of the actual power output value is obtained by performing differential analysis on the data collected by the power sensors. Specifically, the software system will compare the actual power output values at different times, calculate the power difference between adjacent time points, and thus extract the change range. This process combines the dynamic time window setting to ensure that the calculation of the change range can capture the influence trend of occlusion on power output. Finally, the maximum power output value of each power generation component under standard test conditions can be directly obtained through a preset value. The data of standard test conditions are usually provided by the manufacturer of the photovoltaic module and stored in the operation database of the device. By associating the real-time collected actual power output value and change range with the standard maximum power output value, the software system can dynamically monitor and analyze the power fluctuation characteristics of each power generation component, providing high-quality data support for subsequent analysis and evaluation.

[0034] Calculate the power generation power fluctuation coefficient of each power generation component. The specific calculation formula is as follows: In the formula, is the power generation power fluctuation coefficient of the

[0035] Calculate the power generation power fluctuation coefficient of each power generation component is to comprehensively quantify the instability of power output under dynamic occlusion conditions and its impact on power generation performance. The setting of each operation step in the formula aims to highlight the contribution of different characteristics to power fluctuation. First, use the exponential operation to describe the degree of deficiency of the actual power output value relative to the maximum power. This part amplifies the influence of low power output through non-linear attenuation, making the time period with significantly insufficient power contribute more to the overall coefficient; Second, use the logarithmic operation Enhance the sensitivity to the amplitude of power changes, smooth the impact of small fluctuations, and at the same time emphasize the contribution of large power fluctuations to the overall coefficient. These two parts express the combined effect of power shortage and fluctuations through summation, ensuring a comprehensive reflection of the strength of the occlusion effect. In addition, the power fluctuations over the entire time period are accumulated through integral operations to capture the time effect of dynamic changes, and the impact is normalized through averaging, making the results more generalizable and comparable. Finally, the square root operation balances the dimensional differences between different characteristics, ensuring that the results are more interpretable. This calculation logic can accurately reflect the complex impact of dynamic occlusion on the power fluctuations of power generation components, providing a scientific basis for efficiency evaluation.

[0036] The power fluctuation coefficient of the nth power generation component is closely related to evaluating the degree of decrease in power generation efficiency of this component due to dynamic occlusion. The larger it is, the more unstable the power output of this component is under dynamic occlusion conditions, manifested as a higher proportion of time with power shortage or a larger amplitude of power fluctuations. These factors directly reflect the negative impact of occlusion on power generation efficiency. When the power fluctuation coefficient is high, it indicates that the occlusion phenomenon not only reduces the average power output of this component but also significantly increases the instability of power generation, resulting in a more serious decrease in efficiency; conversely, when is small, it means that the power output of this component is relatively stable, and the impact of occlusion on power generation efficiency is small. Therefore, the magnitude of the power fluctuation coefficient of power generation can be used as an important indicator to measure the degree of influence of dynamic occlusion on power generation components, providing a key basis for subsequent evaluation of efficiency decline, and jointly used with other evaluation parameters to generate comprehensive evaluation results to support the optimization and adjustment strategies of power generation components.

[0037] In this embodiment, for the occlusion intensity index and the power fluctuation coefficient of each generated power generation component, an evaluation model for the decline in power generation efficiency is constructed, and the power generation evaluation coefficient of each power generation component is generated through weighted summation, according to the formula: where and are the non-zero weight coefficients of the occlusion intensity index and the power fluctuation coefficient of each power generation component respectively, and ; Building an evaluation model for the decline in power generation efficiency and generating the power generation evaluation coefficient for each power generation component through weighted summation is achieved by the weighted calculation that combines the occlusion intensity index and the power generation power fluctuation coefficient. First, extract the corresponding occlusion intensity index and power generation power fluctuation coefficient from each power generation component. These two parameters respectively quantify the impact of dynamic occlusion on the light conditions and the stability of power generation performance. Subsequently, according to the actual application scenarios and technical requirements, assign corresponding weight coefficients to these two parameters and . The setting of the weight coefficient is determined through experimental data or model training, and its value is usually related to the relative contribution of the occlusion intensity index to the decline in power generation efficiency, while is related to the degree of impact of power fluctuation on power generation performance. This weight allocation can be dynamically adjusted according to different environmental conditions (such as the volatility of light intensity, the frequency of occlusion) to ensure the adaptability and accuracy of the model. In the specific calculation, the software system multiplies the occlusion intensity index of each component by its corresponding weight coefficient , multiplies the power generation power fluctuation coefficient by the weight , and then adds the weighted values of the two to generate the power generation evaluation coefficient of this component. This process is achieved through real-time data input and algorithm processing, constructing a quantitative evaluation model for the comprehensive impact of dynamic occlusion and power fluctuation, providing a scientific basis for subsequent efficiency decline analysis and component classification.

[0038] Compare the generated power generation evaluation coefficients of each power generation component with the pre-set threshold range of the power generation evaluation coefficient , evaluate the degree of decline in power generation efficiency of each power generation component in the photovoltaic panel due to dynamic occlusion according to the comparison result, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components. The specific comparison analysis and classification are as follows: If , the degree of decline in power generation efficiency of this power generation component in the photovoltaic panel due to dynamic occlusion is low, and this power generation component is classified as a low-impact component; This situation indicates that the degree of decline in power generation efficiency of this component due to dynamic occlusion is relatively low. In other words, the occlusion area of this component during the operation of the photovoltaic panel is small, the light intensity remains relatively stable, and the amplitude of power generation power fluctuation is also within an acceptable range. This means that the power generation performance of this component is basically not significantly affected by dynamic occlusion, and its output power can stably approach the maximum power output under standard test conditions. The impact is that this component does not require additional optimization measures, can maintain the existing operating state to save system resources, and allocate the priority of more adjustments and optimizations to other more severely affected components, so as to ensure the maximization of the overall operating efficiency of the photovoltaic equipment.

[0039] If , the degree of power generation efficiency decline of the power generation component in the photovoltaic panel due to dynamic shading is medium, and the power generation component is classified as a medium-impact component; This situation indicates that the degree of power generation efficiency decline of the component due to dynamic shading is medium. At this time, the shading area ratio, light intensity change, and power fluctuation characteristics of the component are all within a certain range, which has a certain impact on the power generation performance, but has not reached a serious level. This means that the output power of the component is significantly interfered by dynamic shading, but still remains within an adjustable and optimizable range. The impact is that the component may require appropriate optimization measures, such as adjusting the distribution of the shaded area, or making minor optimizations to the operating parameters of the component, to reduce the impact of dynamic shading while avoiding unnecessary resource consumption caused by excessive intervention. By making appropriate adjustments to the medium-impact components, the overall power generation efficiency of the photovoltaic device can be further improved.

[0040] If , the degree of power generation efficiency decline of the power generation component in the photovoltaic panel due to dynamic shading is high, and the power generation component is classified as a high-impact component.

[0041] This situation indicates that the degree of power generation efficiency decline of the component due to dynamic shading is serious. At this time, the component may be in a large shaded area for a long time, the light intensity drops significantly, and the power output fluctuates significantly and unstably, far lower than the maximum power under standard test conditions. This means that the component has a greater negative impact on the overall operation of the photovoltaic device. If no optimization measures are taken, it may lead to a further decline in power generation efficiency and affect the overall balanced operation of the device. The impact is that the component needs to take strong-intervention optimization measures first, such as quickly adjusting the shaded area distribution, reallocating the operating parameters, and even physically intervening in the shading source when necessary. This prioritized optimization can not only restore the power generation performance of the high-impact component, but also reduce its negative linkage impact on the entire photovoltaic system, improving the overall power generation efficiency and stability of the system.

[0042] The pre-set threshold interval of the power generation evaluation coefficient can be determined by combining historical data analysis and experimental calibration. Specifically, it includes: collecting long-term data of the photovoltaic device in different environments (such as shading intensity index, power generation power fluctuation coefficient, and actual power generation efficiency), using clustering analysis and statistical modeling to identify the characteristic patterns of the impact of dynamic shading on power generation efficiency, establishing a benchmark model, classifying it into three categories: low impact, medium impact, and high impact, and extracting the corresponding typical value ranges. Through experimental calibration by simulating different shading conditions, dynamically adjusting the upper and lower limits of the threshold, and using a multi-objective optimization algorithm to balance the classification effect. This process can be automatically completed by a software system, providing a scientific basis for efficiency evaluation and classification.

[0043] According to the division results of each power generation component in the photovoltaic panel, a power generation efficiency optimization mechanism is constructed, and different optimization measures are taken for low-impact components, medium-impact components, and high-impact components respectively; In this embodiment, according to the division results of each power generation component in the photovoltaic panel, a power generation efficiency optimization mechanism is constructed as follows: according to the division results of low-impact components, medium-impact components, and high-impact components, different optimization adjustment parameters are set respectively to form a power generation efficiency optimization mechanism; this optimization mechanism is based on the dynamic feedback of the power generation evaluation coefficient of each power generation component, the shading intensity index, and the power generation power fluctuation coefficient, and through the preset optimization rules, automatically determines the adjustment method and adjustment range of the operating parameters of the components; To achieve "constructing a power generation efficiency optimization mechanism according to the division results of each power generation component in the photovoltaic panel", it can be achieved by combining a dynamic parameter adjustment model with data feedback analysis. Specifically, first, the division results of low-impact components, medium-impact components, and high-impact components need to be input into the optimization mechanism, which consists of a rule base based on the power generation evaluation coefficient and a dynamic adjustment model. The rule base presets the operation adjustment strategies for different types of components, including specific measures such as maintaining the status quo, optimizing parameters, and key compensation. The optimization mechanism first uses the power generation evaluation coefficient, the shading intensity index updated in real time, and the power generation power fluctuation coefficient data to dynamically analyze the operation status of the components, and calculates the adjustment priority of each component through a multi-objective optimization algorithm (such as a genetic algorithm or a fuzzy logic model). Subsequently, according to the optimization rules in the rule base, optimization adjustment parameters are assigned to each component, such as current-voltage characteristic values, shading compensation strategies, and operation load distribution. The setting of these parameters comprehensively considers the current state of the component, historical operation data, and dynamic feedback information through an optimization algorithm to ensure that the adjustment measures are scientific and adaptable. The reason for implementing it in this way is that photovoltaic equipment is greatly affected by environmental factors during actual operation, and the efficiency reduction caused by dynamic shading needs to be optimized by precisely adjusting the operating parameters of different components to optimize the overall power generation performance. The optimization mechanism uses real-time feedback data, which can not only quickly identify and classify components affected to different degrees, but also formulate targeted differential adjustment strategies to avoid resource waste or unnecessary adjustments, thereby improving the overall operating efficiency and stability of the equipment. In addition, this software-based dynamic optimization method can adapt to different operating environments, has strong flexibility and scalability, and provides the core technical support for the intelligent operation and maintenance of photovoltaic equipment.

[0044] Different optimization measures are taken for low-impact components, medium-impact components, and high-impact components respectively, specifically as follows: The optimization measure for low-impact components is: use the operation maintenance parameters in the optimization mechanism to maintain the current operation status without parameter adjustment; The optimization measures for low - impact components can be achieved through the operation maintenance mechanism in the software system. Specifically, according to the comparison result of the power generation evaluation coefficient of the components, the system sets the power generation units evaluated as low - impact components to the "maintenance mode". In the maintenance mode, the system ensures that the current operating state of the components can be continuously maintained within a stable range by real - time monitoring the power generation parameters of the components. For example, the key parameters such as current, voltage, and power output are within the normal value range. In this mode, the optimization mechanism will suspend the adjustment instructions for the components and only retain the basic operation monitoring function to reduce unnecessary calculations and resource consumption. The significance of this method is that for components whose power generation performance is not significantly affected by dynamic shading, excessive intervention may cause resource waste and even disrupt the overall operation balance. Therefore, by maintaining the current operating state, more computing and optimization resources can be used for medium - impact and high - impact components, thereby improving the optimization efficiency of the entire photovoltaic system.

[0045] The optimization measures for medium - impact components are as follows: Using the operation adjustment parameters in the optimization mechanism, clearly adjust the operating parameters of the power generation components, including resetting the current - voltage characteristic values and implementing the shading compensation strategy to reduce the impact of dynamic shading on power generation performance; The optimization measures for medium - impact components are achieved through the operation adjustment mechanism, which dynamically generates adjustment parameters based on the power generation evaluation coefficient, shading intensity index, and power generation power fluctuation coefficient of the components. The specific implementation methods include two parts: One is to reset the current - voltage characteristic values. The system analyzes the real - time operating point of the components, combines the shading intensity data, calculates the new maximum power point, and adjusts the operating parameters of the inverter to make the components operate at the new optimal power point. The other is to implement the shading compensation strategy. For example, through the dynamic distributed maximum power point tracking technology (MPPT), optimize the output efficiency of the power generation components under partial shading conditions, and at the same time adjust the local power distribution in combination with the dynamic data of the shaded area. The significance of this optimization method is that although medium - impact components are greatly affected by shading, by moderately adjusting the operating parameters, the power generation performance of the components can be significantly improved, avoiding a larger - scale efficiency loss, thereby maximizing the power generation capacity of the components while ensuring the operation stability.

[0046] The optimization measures for high - impact components are as follows: Using the operation optimization parameters in the optimization mechanism, focus on adjusting the operating mode of the power generation components, including dynamically changing the distribution of the shaded area, re - distributing the operating load of the components, and implementing full - coverage compensation measures for the shaded area to ensure the restoration of power generation performance.

[0047] The optimization measures for high-impact components are achieved by running an optimization mechanism, and a multi-level adjustment method is adopted for key optimization. The specific implementation methods include: First, dynamically analyze the distribution characteristics of the occluded areas in combination with computer vision data, and adjust the arrangement of the occluded areas through software instructions, such as controlling the actions of adjustable occlusion devices or notifying physical operation and maintenance personnel to remove the occlusion sources; Second, redistribute the operating loads of the components. The system distributes the loads of the components severely affected by occlusion to other components to balance the overall output power; Finally, implement full-coverage compensation measures for the occluded areas, such as enabling backup power generation components or adjusting the power output of the energy storage system to make up for the power gap caused by occlusion. The significance of this optimization measure lies in that if high-impact components are not optimized in a timely manner, it will have a significant negative impact on the operating efficiency and stability of the entire photovoltaic system. Therefore, through multi-level optimization means, the power generation performance can be restored to the greatest extent, while reducing the associated impact on other components and devices, ensuring the high efficiency and reliability of the overall system operation.

[0048] During the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the optimization adjustment feedback information of each power generation component is obtained in real time, and analyzed after acquisition to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectations, and optimize the power generation efficiency optimization mechanism according to the evaluation results; In this embodiment, during the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the optimization adjustment feedback information of each power generation component is obtained in real time, and analyzed after acquisition to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectations, and optimize the power generation efficiency optimization mechanism according to the evaluation results, which specifically includes the following steps: During the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the optimization adjustment feedback information of each power generation component is obtained in real time and preprocessed after acquisition; During the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, the real-time acquisition of the optimization adjustment feedback information can be achieved through the combination of sensor data acquisition and optimization instruction response tracking. Specifically, each power generation component is equipped with a power output sensor, a current-voltage characteristic monitoring module, and an occlusion change monitoring module to record the actual power output, current-voltage characteristic changes, and occlusion state changes of the component after optimization adjustment in real time. These data are transmitted to the central control system through a wireless sensor network or a data bus. At the same time, the adjustment instructions in the optimization mechanism are also recorded in the software system and associated with the collected real-time data for analysis as part of the feedback information. In addition, through the time synchronization module, the system can accurately correspond the feedback data after optimization adjustment with the time point when the optimization instruction is executed to capture the dynamic characteristics of the adjustment response, so as to generate a complete data stream of the optimization adjustment feedback information.

[0049] Extract the optimized output characteristic information and optimized response characteristic information from the optimized adjustment feedback information of each preprocessed power generation component, and perform analysis after extraction to generate the optimized output consistency index and optimized response sensitivity coefficient of each power generation component respectively; The extraction of the optimized output characteristic information and optimized response characteristic information from the preprocessed optimized adjustment feedback information can be achieved through data classification, feature extraction, and dynamic analysis. The specific method is as follows: Classify the feedback information into power-related data (such as actual power output and target power) and optimized adjustment-related data (such as adjustment amplitude and response time), and extract key characteristics respectively, such as output power difference, response time, and efficiency change rate. Combining time series analysis, model the dynamic change trend of the data, and extract the optimized output characteristic information and optimized response characteristic information. Finally, integrate the data through a feature aggregation algorithm (such as weighted average) to generate complete optimized characteristic information to support subsequent calculations.

[0050] Construct an optimized effect evaluation model for the generated optimized output consistency index and optimized response sensitivity coefficient of each power generation component, generate the optimized evaluation coefficient of each power generation component through weighted summation, and perform analysis after generation to evaluate whether the optimized effect of the power generation efficiency optimization mechanism on each power generation component meets the expectations, and optimize the power generation efficiency optimization mechanism according to the evaluation results.

[0051] In this embodiment, the acquisition logic of the optimized output consistency index and optimized response sensitivity coefficient of each power generation component is as follows: Extract the optimized output characteristic information from the optimized adjustment feedback information of each preprocessed power generation component, specifically including the actual output power of each power generation component at different times during a period in the optimization process, the change amplitude of the actual output power, and the target power value set by the power generation efficiency optimization mechanism for each power generation component, and calibrate them respectively as , and , represents the actual output power of the th power generation component at the th moment during a period in the optimization process, represents the change amplitude of the actual output power of the th power generation component at the th moment during a period in the optimization process, represents the target power value set by the power generation efficiency optimization mechanism for the th power generation component, , , and are all positive integers; During the optimization process, the actual output power of each power generation component, the change range of the actual output power, and the target power value set by the power generation efficiency optimization mechanism for each power generation component can be obtained in real time, which can be achieved through the integration of sensor data acquisition and optimization system data. Specifically, first, through high-precision power sensors installed at the output end of the power generation components, the actual output power data of each component is collected in real time. The power sensors can record the instantaneous output power values of the components at fixed time intervals and transmit the data to the central control system. Secondly, the system calculates the difference of the time series data of the actual output power to generate the change range of the actual output power. This process is automatically processed by software, which can capture the dynamic characteristics of power fluctuations and update the change range data in real time. In addition, the target power value in the power generation efficiency optimization mechanism is calculated by the optimization model based on the operating status of the components, environmental conditions, and historical operating data. The target power value is stored in the optimization system and associated with the actual power data when the optimization instruction is issued, and the setting of the target value is dynamically updated. The acquisition and calculation of all these data are seamlessly integrated through the software system. The system can automatically match and synchronize the data obtained in real time by the sensors with the target power values output by the optimization model, thus forming a complete optimization adjustment feedback information and providing accurate basic data support for subsequent analysis and optimization. This method not only ensures the real-time and accuracy of data acquisition but also can effectively cope with the complex changes in the operating status of components in a dynamic environment.

[0052] Calculate the optimization output consistency index of each power generation component. The specific calculation formula is as follows: In the formula, is the optimization output consistency index of the th power generation component; Calculating the optimization output consistency index of each power generation component is to comprehensively evaluate the consistency between the actual output and the target power and the stability of the output power of the power generation components during the optimization adjustment process. Each operation step in the formula aims to quantify the influence of different factors on the optimization effect. First, is used to measure the relative deviation between the actual output power and the target power. By squaring the operation, the influence of larger deviations is amplified, so as to more prominently show the moments when the target achievement is not ideal. Secondly, It reflects the variation range of the actual output power in the time series, directly quantifies the volatility of the component output. The larger the fluctuation range, the worse the stability of the output after optimization. Summing up the two parts can consider both the accuracy and stability of the output power. Then, through the averaging process of the time period, the overall effect of the optimization adjustment feedback is normalized so that the optimization results of different components are comparable. Finally, by taking the logarithm of the accumulated result, the influence of small deviations and small fluctuations is smoothed, while higher weights are given to larger deviations and instabilities, making the significant problems of the optimization effect more prominent. This calculation logic comprehensively captures the consistency and stability of the optimized output of the components, providing a scientific quantitative basis for the subsequent optimization evaluation.

[0053] The optimized output consistency index of the nth power generation component directly reflects the degree of achievement of the optimization effect of the power generation efficiency optimization mechanism on this component, and is closely related to evaluating whether the optimization effect meets the expectations. When is small, it indicates that the deviation between the actual output power and the target power of this component is small, and at the same time the fluctuation range of the output power is low, indicating that the optimized operating state is relatively stable and the target achievement degree is high. At this time, the optimization effect basically meets the expectations. On the contrary, if is large, it indicates that there is a significant deviation between the actual output power and the target power of the component, or the output power fluctuates significantly, indicating that the optimization mechanism fails to effectively improve the component performance, resulting in the optimization effect being lower than expected. Therefore, by comparing the size with the pre-set optimization evaluation criteria, it is possible to accurately evaluate whether the optimization effect meets the expectations and provide a clear direction for further optimization.

[0054] Extract the optimization response characteristic information from the optimization adjustment feedback information of each pre-processed power generation component, specifically including the percentage change in the ratio of the actual input energy to the output energy of each power generation component at different times during a period in the optimization process, the change rate of the power generation efficiency of each power generation component, and the time interval from receiving the optimization instruction to achieving the adjustment effect of each power generation component, and are respectively calibrated as , and , represents the percentage change in the ratio of the actual input energy to the output energy of the nth power generation component at the moment during a period in the optimization process, represents the change rate of the power generation efficiency of the nth power generation component at the moment during a period in the optimization process, represents the time interval from receiving the optimization instruction to achieving the adjustment effect of the nth power generation component during the optimization process; During the optimization process, the percentage change in the ratio of the actual input energy to the output energy of each power generation component, the change rate of the power generation efficiency, and the time interval from receiving the optimization instruction to achieving the adjustment effect can be obtained in real time by combining a sensor network, a data acquisition module, and an optimization instruction tracking mechanism. Specifically, the percentage change in the ratio of the actual input energy to the output energy can be obtained collaboratively by the current-voltage sensor and the power sensor installed on the power generation component. The current-voltage sensor measures the input electrical energy (such as the product of the voltage and current received by the component), and the power sensor records the output power. The ratio is calculated by comparing the time series of the two, and its change rate is dynamically analyzed by software; the real-time acquisition of the change rate of the power generation efficiency is based on the historical power output data and the power improvement after the optimization adjustment. The software system calculates the efficiency difference at the same moment before and after the optimization and normalizes it into a change rate to reflect the improvement degree of the power generation performance; as for the time interval from receiving the optimization instruction to achieving the adjustment effect, it can be accurately tracked through the instruction log and sensor feedback in the optimization mechanism. The software system records the sending time of each optimization instruction and the feedback time when the operating state of the component is stable after the optimization, and the time difference is the response interval. All these data acquisitions are integrated in real time through the data processing module in the central control system, and the dynamic monitoring algorithm is used to ensure the efficient acquisition and analysis of the data, providing comprehensive and accurate basic information support for the optimization evaluation.

[0055] Calculate the optimization response sensitivity coefficient of each power generation component. The specific calculation formula is as follows: In the formula, is the th optimization response sensitivity coefficient of the power generation component.

[0056] Calculate the optimization response sensitivity coefficient of each power generation component is to quantify the significance and timeliness of the response effect of the component during the optimization adjustment. Each operation step in the formula aims to comprehensively evaluate the multi-faceted impact of the optimization adjustment on the component performance. First, reflects the ratio of the change rate of the power generation efficiency to the response delay time, which is used to measure the optimization efficiency of the component. The shorter the response time and the more significant the efficiency improvement, the larger this ratio is, indicating a more ideal optimization effect; second, By taking the logarithm of the percentage change in the input-output energy ratio, the impact of larger changes is amplified, while the contribution of small changes is smoothed, capturing the non-linear effect of the optimization adjustment on energy utilization. Multiplying these two parts together, combined with the dynamic characteristics of the optimization adjustment, comprehensively reflects the quality and speed of the optimization response. Finally, by taking the average of the data at all times within the time period, the dynamic changes of the optimization response are unified into comparable quantitative indicators. This calculation logic comprehensively combines optimization efficiency, response timeliness, and energy utilization characteristics, providing a scientific and comprehensive basis for evaluating the optimization effect.

[0057] The optimization response sensitivity coefficient of the th power generation component directly reflects whether the optimization effect of the power generation efficiency optimization mechanism on this component meets the expectations. If the value is large, it indicates that this component shows a high power generation efficiency change rate after optimization adjustment, and the response time of the optimization instruction is short. At the same time, the improvement of the input-output energy ratio is significant, comprehensively indicating that the optimization adjustment has a significant effect on improving the component performance, and the optimization goal is basically achieved; conversely, if the value is small, it indicates that the power generation efficiency of this component has limited improvement after optimization adjustment, the response time is long, or the improvement of energy utilization is not obvious, showing that the optimization effect is lower than expected. Therefore, the size of

[0058] is an important quantitative indicator for evaluating the effect of the optimization mechanism, which can clearly reveal whether the optimization effectively achieves the expected goal, providing a basis for the optimization strategy of the subsequent adjustment mechanism.

[0058] In this embodiment, for the optimization output consistency index and the optimization response sensitivity coefficient of each generated power generation component, an optimization effect evaluation model is constructed, and the optimization evaluation coefficient of each power generation component is generated through weighted summation, according to the formula: where and are the non-zero weight coefficients of the optimization output consistency index and the optimization response sensitivity coefficient of each power generation component respectively, and ; The construction of the optimization effect evaluation model can be achieved through the weighted summation of the optimization output consistency index and the optimization response sensitivity coefficient . The specific method is: using the characteristic data extracted from the optimization adjustment feedback information, calculate the and of each power generation component respectively, and then according to the target requirements of the optimization mechanism, set the weight coefficients and . The setting of the weight coefficient is based on the focus of the optimization goal: if more emphasis is placed on the output consistency and goal achievement after optimization, then a higher weight is given; conversely, if more emphasis is placed on the response effect and adjustment efficiency of the optimization adjustment, then the weight of is increased. The weight coefficient also needs to satisfy to ensure that the results of the evaluation model have physical significance within a certain range. Through the calculation formula , the generated optimization evaluation coefficient

[0059] can comprehensively reflect the output consistency of the component and also reflect its response efficiency, providing a scientific basis for the quantitative evaluation of the optimization effect. Compare the generated optimization evaluation coefficients of each power generation component with the pre-set optimization evaluation coefficient thresholds of each power generation component, and evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectations according to the comparison results, and optimize the power generation efficiency optimization mechanism according to the evaluation results. The specific comparison and analysis are as follows: If , the optimization effect of the power generation efficiency optimization mechanism on this power generation component meets the expectations, and there is no need to optimize the power generation efficiency optimization mechanism; This situation indicates that the optimization effect of the power generation efficiency optimization mechanism on this component has reached the expected goal. This means that after the optimization adjustment of this component, its output consistency and response sensitivity both meet the performance requirements of the optimization mechanism, that is, the actual output power of the component is close to the target power, the power fluctuation is small, and at the same time, it responds quickly and efficiently to the optimization instructions. The impact is that this component is already in a relatively optimal state and does not require further optimization adjustment, thus saving the computing resources and time of the optimization mechanism and ensuring the high efficiency and stability of the overall operation of the photovoltaic equipment.

[0060] If , the optimization effect of the power generation efficiency optimization mechanism on this power generation component does not meet the expectations, and it is necessary to optimize the power generation efficiency optimization mechanism. Specifically, it includes: readjusting the setting of operating parameters in the optimization strategy, such as current-voltage characteristic values or local shading compensation parameters; improving the feedback information processing mechanism to enhance the real-time and accuracy of the optimization adjustment; dynamically updating the optimization effect evaluation model to adapt to the current conditions based on new operating data; optimizing the execution process to ensure that the power generation efficiency optimization mechanism can improve the power generation performance of each power generation component by reducing the response delay and improving the execution efficiency of the optimization instructions.

[0061] This situation indicates that the power generation efficiency optimization mechanism fails to effectively improve the performance of the component, and the optimization effect does not meet the expectation. This shows that there is a large deviation between the actual output power and the target power of the component, obvious power fluctuations, or a relatively slow response to the optimization instructions, resulting in insufficient improvement in its power generation performance. The impact of this situation is that the component may be in a sub-optimal operating state for a long time, which not only affects its own power generation efficiency but also may reduce the overall operating efficiency of the photovoltaic equipment. Therefore, it is necessary to make targeted adjustments and improvements to the optimization mechanism to ensure that the component can return to the optimal operating state while maintaining the continuous improvement of the overall system performance.

[0062] When the optimization effect of the power generation efficiency optimization mechanism on a certain power generation component does not meet the expectation, it is necessary to optimize the mechanism through software, which specifically includes the following aspects. First, the operating parameters are reset through the optimization strategy adjustment module. For example, the adjustment of the current-voltage characteristic values can be achieved by real-time monitoring of the maximum power point (MPP) position of the component and dynamically recalculating the optimal operating point in combination with the occlusion compensation data to ensure that the component operates in an efficient state under the current environment. Second, the feedback information processing mechanism is improved. The accuracy of the feedback data can be enhanced by introducing data filtering algorithms (such as Kalman filtering), and the real-time performance of the optimization adjustment can be optimized through timestamp calibration to ensure a more accurate dynamic association between the feedback data and the optimization instructions. Third, through the dynamic update module of the optimization effect evaluation model, the model parameters are adjusted online in combination with the latest operating data. For example, the threshold range of the optimization evaluation coefficient is recalibrated or the weight parameters are adjusted to enable the model to adapt to the changes in the component operating environment. Finally, an instruction queue optimization and priority management mechanism is introduced in the optimization execution process to reduce the execution delay. For example, the instruction execution efficiency is improved through parallel processing, and the optimization tasks of high-impact components are preferentially processed. These improvement measures enable the optimization mechanism to more flexibly adapt to the complex and changeable operating environment through software automation processing and dynamic adjustment, not only improving the optimization efficiency but also ensuring the stability and reliability of the overall performance of the photovoltaic equipment.

[0063] The threshold values of the optimization evaluation coefficients preset for each power generation component can be determined by software based on a comprehensive analysis of historical operating data, environmental conditions, and performance goals. The specific implementation methods include: collecting historical optimization data of the photovoltaic equipment in different operating environments (such as time series information of the optimization output consistency index and the optimization response sensitivity coefficient), and grouping the optimization effects of different components through cluster analysis (such as K-means clustering) to identify the characteristics of low-impact, medium-impact, and high-impact components. Combining environmental variables (such as light intensity, temperature, occlusion mode) and target performance, a multivariate regression model is used to fit the optimization effects of each group to generate a reference range for the optimization evaluation coefficient. Finally, the threshold values are dynamically adjusted through the empirical weight method to not only meet the performance goals but also adapt to different operating conditions, achieving a scientific and accurate setting of the evaluation coefficients.

[0064] Comprehensively monitor and analyze the impact of dynamic shading on photovoltaic panels, the implementation effect of optimization measures, and the overall operation data of photovoltaic equipment, continuously improve the power generation efficiency optimization mechanism, and enhance the operation efficiency and dynamic adaptability of photovoltaic equipment.

[0065] To comprehensively monitor and analyze the impact of dynamic shading on photovoltaic panels, the implementation effect of optimization measures, and the overall operation data of photovoltaic equipment, and continuously improve the power generation efficiency optimization mechanism, it can be achieved by combining multi-source data acquisition, dynamic modeling, and feedback optimization systems. Specifically, first, the key operation data of photovoltaic equipment are collected in real time through a sensor network, including the dynamic shading characteristics of photovoltaic panels (such as the size and change speed of the shaded area), the output power and power fluctuations of each power generation component, environmental parameters (such as light intensity and temperature), etc., to construct a multi-dimensional data input system. Secondly, the collected data are analyzed using the dynamic modeling module in the software. For example, through time series analysis and machine learning algorithms, the influence law of dynamic shading on power generation efficiency is modeled, and it is correlated with the implementation effect of optimization measures to evaluate the applicability and improvement space of the current optimization mechanism. Then, based on these analysis results, the system automatically generates improvement suggestions, such as adjusting the parameters of the optimization strategy, optimizing the response time series, or recalibrating the model weights, etc., to dynamically update the power generation efficiency optimization mechanism. Finally, combined with the global monitoring system, the analysis results of the overall operation status and improvement measures are real-time fed back to the operation and maintenance team through the data visualization function to achieve human-machine collaborative decision-making. This method can not only continuously improve the operation efficiency of photovoltaic equipment but also enhance the system's dynamic adaptability to complex environmental changes, ensuring the long-term efficient operation and stability of photovoltaic equipment.

[0066] As Figure 2 shown in the computer vision-based automated operation and maintenance management system for photovoltaic equipment, it includes a dynamic shading detection module, an operation status evaluation module, a power generation efficiency optimization module, an optimization effect feedback module, and a comprehensive monitoring and improvement module; The dynamic shading detection module, during the operation of photovoltaic equipment, uses computer vision technology to detect in real time whether there is a phenomenon of dynamic shading on the surface of the photovoltaic panel, which is the core power generation unit. When it detects the phenomenon of dynamic shading on the surface of the photovoltaic panel, it determines each power generation component used for power generation in the photovoltaic panel; The operation status evaluation module, in real time, obtains the operation status information of each power generation component in the photovoltaic panel during the process of being affected by dynamic shading, and analyzes it after obtaining it, evaluates the degree of power generation efficiency decline of each power generation component in the photovoltaic panel caused by dynamic shading, and divides each power generation component in the photovoltaic panel into low-impact components, medium-impact components, and high-impact components; The power generation efficiency optimization module constructs a power generation efficiency optimization mechanism based on the division results of each power generation component in the photovoltaic panel, and performs different optimization measures on the low-impact components, medium-impact components, and high-impact components respectively; The optimization effect feedback module, during the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, obtains the optimization adjustment feedback information of each power generation component in real time, analyzes it after obtaining, evaluates whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectation, and optimizes the power generation efficiency optimization mechanism according to the evaluation result; The comprehensive monitoring and improvement module comprehensively monitors and analyzes the influence of dynamic shading of the photovoltaic panel, the implementation effect of the optimization measures, and the overall operation data of the photovoltaic equipment, continuously improves the power generation efficiency optimization mechanism, and improves the operation efficiency and dynamic adaptability of the photovoltaic equipment.

[0067] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0068] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0069] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0070] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0071] In several embodiments provided by this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the above-described embodiments are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0072] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0073] In addition, the functional units in each embodiment of this application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0074] As described above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A photovoltaic equipment automated operation and maintenance management method based on computer vision, characterized in that: The specific steps include: During the operation of the photovoltaic equipment, computer vision technology is used to detect in real time whether there is dynamic occlusion on the surface of the photovoltaic panel, which is the core power generation unit. When dynamic occlusion is detected on the surface of the photovoltaic panel, each power generation component used for power generation in the photovoltaic panel is determined; Acquire the operating status information of each power generation component in the photovoltaic panel in real time when the photovoltaic panel is affected by dynamic shading, and analyze it after acquisition to evaluate the degree of reduction in power generation efficiency of each power generation component in the photovoltaic panel due to dynamic shading, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components; According to the classification results of each power generation component in the photovoltaic panel, a power generation efficiency optimization mechanism is constructed, and different optimization measures are taken for low-impact components, medium-impact components and high-impact components respectively; In the process of optimizing each power generation component in the photovoltaic panel by the power generation efficiency optimization mechanism, the optimization adjustment feedback information of each power generation component is obtained in real time, and analyzed after acquisition to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets expectations, and optimize the power generation efficiency optimization mechanism according to the evaluation results; Comprehensively monitor and analyze the impact of dynamic shading of photovoltaic panels, the implementation effect of optimization measures and the overall operation data of photovoltaic equipment, continuously improve the power generation efficiency optimization mechanism, and enhance the operating efficiency and dynamic adaptability of photovoltaic equipment.

2. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 1, characterized in that: The operation status information of each power generation component in the photovoltaic panel is obtained in real time when the photovoltaic panel is affected by dynamic shading, and analyzed after acquisition to evaluate the degree of reduction in power generation efficiency of each power generation component in the photovoltaic panel due to dynamic shading, and divide each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components, which specifically includes the following steps: Real-time acquisition of the operating status information of each power generation component in the photovoltaic panel when the photovoltaic panel is affected by dynamic shading, and pre-processing after acquisition; Extracting the light shielding characteristic information and the power generation fluctuation characteristic information from the preprocessed operation status information, and analyzing them after extraction, respectively generating the shielding intensity index and the power generation fluctuation coefficient of each power generation component; A power generation efficiency reduction assessment model is constructed for the shading intensity index and power generation power fluctuation coefficient of each generated power generation component. The power generation assessment coefficient of each power generation component is generated by weighted summation. After generation, the model is analyzed to evaluate the degree of power generation efficiency reduction of each power generation component in the photovoltaic panel due to dynamic shading, and the power generation components in the photovoltaic panel are divided into low-impact components, medium-impact components and high-impact components.

3. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 2, characterized in that: The logic for obtaining the shielding intensity index and power generation fluctuation coefficient of each power generation component is as follows: Extract the light shielding characteristic information from the preprocessed operating status information, including the proportion of the shielded area of ​​each power generation component surface to the total surface at different times during a period of time when the photovoltaic panel is affected by dynamic shielding, the light intensity received by each power generation component, and the rate of change of the light intensity received by each power generation component, and use the function to calculate the light shielding characteristic information according to the time series. , and To express, For time point, Indicates that during a period of time when the photovoltaic panel is affected by dynamic shading Moment The proportion of the blocked area of ​​the power generation component surface to the total surface, Indicates that during a period of time when the photovoltaic panel is affected by dynamic shading Moment The light intensity received by each power generation component is Indicates that during a period of time when the photovoltaic panel is affected by dynamic shading Moment The rate of change of the light intensity received by each power generation component is defined as the time period , , is a positive integer; The light intensity received by each power generation component at different times during a period of time when the photovoltaic panel is affected by dynamic shading is compared, and the maximum value is calibrated as ; Calculate the shielding intensity index of each power generation component. The specific calculation formula is as follows: In the formula, For the The shading intensity index of each power generation component; Extract the power generation fluctuation characteristic information from the preprocessed operating status information, specifically including the actual power output value of each power generation component at different times during a period of time when the photovoltaic panel is affected by dynamic shading, the change range of the actual power output value, and the maximum power output value of each power generation component under standard test conditions, and use the function to calculate the actual power output value of each power generation component at different times during a period of time when the photovoltaic panel is affected by dynamic shading. and To express, Indicates that during a period of time when the photovoltaic panel is affected by dynamic shading Moment The actual power output value of each power generation component, Indicates that during a period of time when the photovoltaic panel is affected by dynamic shading Moment The change in the actual power output value of the first power generation component will The maximum power output value of each power generation component under standard test conditions is calibrated as ; Calculate the power fluctuation coefficient of each power generation component. The specific calculation formula is as follows: In the formula, For the The power generation fluctuation coefficient of each power generation component.

4. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 3 is characterized in that: The shading intensity index of each generated power generation component and power generation fluctuation coefficient Construct a power generation efficiency decline assessment model and generate the power generation assessment coefficients of each power generation component through weighted summation , according to the formula: ,in and are the shading intensity index of each power generation component and power generation fluctuation coefficient The non-zero weight coefficient of ; The power generation evaluation coefficients of each power generation component will be generated The pre-set threshold value of the power generation evaluation coefficient The comparison is carried out, and the degree of reduction in power generation efficiency of each power generation component in the photovoltaic panel due to dynamic shading is evaluated based on the comparison results, and each power generation component in the photovoltaic panel is divided into low-impact components, medium-impact components and high-impact components. The specific comparison analysis and division are as follows: like , the power generation efficiency of the power generation component in the photovoltaic panel is reduced to a low degree due to dynamic shading, and the power generation component is classified as a low-impact component; like , the power generation efficiency of the power generation component in the photovoltaic panel is reduced to a medium degree due to dynamic shading, and the power generation component is classified as a medium-impact component; like The degree of reduction in power generation efficiency of this power generation component in the photovoltaic panel due to dynamic shading is high, and the power generation component is classified as a high-impact component.

5. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 4, characterized in that: According to the results of the division of each power generation component in the photovoltaic panel, a power generation efficiency optimization mechanism is constructed, specifically: according to the division results of low-impact components, medium-impact components and high-impact components, different optimization adjustment parameters are set respectively to form a power generation efficiency optimization mechanism; this optimization mechanism is based on the power generation evaluation coefficient of each power generation component and the dynamic feedback of the shading intensity index and the power generation power fluctuation coefficient, and automatically determines the component's operating parameter adjustment method and adjustment range through pre-set optimization rules; Different optimization measures are taken for low-impact components, medium-impact components, and high-impact components, specifically: The optimization measures for low-impact components are: using the operation-maintaining parameters in the optimization mechanism to maintain the current operation status without adjusting the parameters; The optimization measures for the affected components are: using the operation adjustment parameters in the optimization mechanism to clearly adjust the operation parameters of the power generation components, including resetting the current and voltage characteristic values ​​and implementing the shading compensation strategy to reduce the impact of dynamic shading on power generation performance; The optimization measures for high-impact components are: using the operating optimization parameters in the optimization mechanism, focusing on adjusting the operating mode of the power generation components, including dynamically changing the distribution of the shading area, redistributing the component operating load, and implementing full coverage compensation measures for the shading area to ensure the restoration of power generation performance.

6. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 5, characterized in that: In the process of optimizing each power generation component in the photovoltaic panel by the power generation efficiency optimization mechanism, the optimization adjustment feedback information of each power generation component is obtained in real time, and analyzed after acquisition to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets expectations, and optimize the power generation efficiency optimization mechanism according to the evaluation results, which specifically includes the following steps: In the process of optimizing each power generation component in the photovoltaic panel by the power generation efficiency optimization mechanism, the optimization adjustment feedback information of each power generation component is obtained in real time and preprocessed after being obtained; Extracting the optimized output characteristic information and the optimized response characteristic information from the preprocessed optimized adjustment feedback information of each power generation component, and analyzing them after extraction to generate the optimized output consistency index and the optimized response sensitivity coefficient of each power generation component respectively; An optimization effect evaluation model is constructed for the generated optimized output consistency index and optimized response sensitivity coefficient of each power generation component. The optimization evaluation coefficient of each power generation component is generated by weighted summation. After generation, an analysis is performed to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets expectations, and the power generation efficiency optimization mechanism is optimized according to the evaluation results.

7. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 6, characterized in that: The acquisition logic of the optimized output consistency index and optimized response sensitivity coefficient of each power generation component is as follows: The optimized output characteristic information in the preprocessed optimized adjustment feedback information of each power generation component is extracted, including the actual output power of each power generation component at different times during the optimization process, the change range of the actual output power, and the target power value set for each power generation component by the power generation efficiency optimization mechanism, and calibrated as , and , Indicates that during the optimization process, Moment The actual output power of each power generation component, Indicates that during the optimization process, Moment The actual output power variation of each power generation component is Indicates that the power generation efficiency optimization mechanism is The target power value set for each power generation component, , , and All are positive integers; Calculate the optimized output consistency index of each power generation component. The specific calculation formula is as follows: In the formula, For the The optimized output consistency index of each power generation component; The optimization response characteristic information in the optimization adjustment feedback information of each power generation component after preprocessing is extracted, including the percentage change of the ratio of the actual input energy to the output energy of each power generation component at different times during the optimization process, the power generation efficiency change rate of each power generation component, and the time interval from receiving the optimization instruction to achieving the adjustment effect of each power generation component, and calibrated as , and , Indicates that during the optimization process, Moment The percentage change of the ratio of actual input energy to output energy of each power generation component, Indicates that during the optimization process, Moment The rate of change of power generation efficiency of each power generation component, Indicates that during the optimization process The time interval from when a power generation component receives an optimization instruction to when the adjustment effect is achieved; Calculate the optimized response sensitivity coefficient of each power generation component. The specific calculation formula is as follows: In the formula, For the The optimized response sensitivity coefficient of each power generation component.

8. The photovoltaic equipment automated operation and maintenance management method based on computer vision according to claim 7, characterized in that: Optimized output consistency index for each generated power generation component and the optimized response sensitivity coefficient Construct an optimization effect evaluation model and generate the optimization evaluation coefficients of each power generation component through weighted summation , according to the formula: ,in and The optimized output consistency index of each power generation component is and the optimized response sensitivity coefficient The non-zero weight coefficient of ; The optimization evaluation coefficients of each power generation component generated The optimized evaluation coefficient thresholds of each power generation component are set in advance Compare and evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets expectations based on the comparison results, and optimize the power generation efficiency optimization mechanism based on the evaluation results. The specific comparison and analysis is as follows: like , the optimization effect of the power generation efficiency optimization mechanism on the power generation component reaches the expected value, and there is no need to optimize the power generation efficiency optimization mechanism; like The optimization effect of the power generation efficiency optimization mechanism on the power generation component did not meet the expectations, and the power generation efficiency optimization mechanism needs to be optimized, including: readjusting the operating parameter settings in the optimization strategy; improving the feedback information processing mechanism to improve the real-time and accuracy of the optimization adjustment; dynamically updating the optimization effect evaluation model to adapt it to current conditions based on new operating data; optimizing the execution process to ensure that the power generation efficiency optimization mechanism can improve the power generation performance of each power generation component by reducing response delays and improving the execution efficiency of optimization instructions.

9. A photovoltaic equipment automated operation and maintenance management system based on computer vision, used to implement the photovoltaic equipment automated operation and maintenance management method based on computer vision as described in any one of claims 1 to 8, characterized in that: It includes dynamic shading detection module, operation status evaluation module, power generation efficiency optimization module, optimization effect feedback module and comprehensive monitoring improvement module; The dynamic occlusion detection module uses computer vision technology to detect in real time whether there is dynamic occlusion on the surface of the photovoltaic panel, which is the core power generation unit, during the operation of the photovoltaic equipment. When dynamic occlusion is detected on the surface of the photovoltaic panel, the module determines the various power generation components in the photovoltaic panel used for power generation. The operation status evaluation module obtains the operation status information of each power generation component in the photovoltaic panel in real time when the photovoltaic panel is affected by dynamic shading, and analyzes it after acquisition to evaluate the degree of reduction in power generation efficiency of each power generation component in the photovoltaic panel due to dynamic shading, and divides each power generation component in the photovoltaic panel into low-impact components, medium-impact components and high-impact components; The power generation efficiency optimization module builds a power generation efficiency optimization mechanism based on the division results of each power generation component in the photovoltaic panel, and performs different optimization measures for low-impact components, medium-impact components and high-impact components respectively; The optimization effect feedback module obtains the optimization adjustment feedback information of each power generation component in real time during the process of the power generation efficiency optimization mechanism optimizing each power generation component in the photovoltaic panel, and analyzes it after obtaining it to evaluate whether the optimization effect of the power generation efficiency optimization mechanism on each power generation component meets the expectations, and optimizes the power generation efficiency optimization mechanism according to the evaluation results; The comprehensive monitoring and improvement module comprehensively monitors and analyzes the impact of dynamic shading of photovoltaic panels, the implementation effect of optimization measures and the overall operation data of photovoltaic equipment, continuously improves the power generation efficiency optimization mechanism, and improves the operating efficiency and dynamic adaptability of photovoltaic equipment.

Images