Intelligent testing method, device and equipment of photovoltaic inverter and storage medium

Abstract

The invention relates to the technical field of intelligent testing, in particular to an intelligent testing method, device and equipment of a photovoltaic inverter and a storage medium. The method comprises the following steps: obtaining photovoltaic inverter structure data; performing shielding simulation device deployment on the photovoltaic inverter structure data to generate photovoltaic module shielding simulation device deployment data; carrying out key structure data acquisition on the structure data of the photovoltaic inverter through the deployment data of the photovoltaic module shielding simulation device, and obtaining the operation data of the standard photovoltaic inverter; and performing shielding test scene simulation on the deployment data of the photovoltaic module shielding simulation device to obtain photovoltaic inverter joint test power data. According to the invention, by introducing shielding simulation, dynamic current-voltage analysis, anti-shielding capability prediction and evaluation and data visualization, a performance detection process of the photovoltaic inverter in a shielding state is provided, and the intelligent level of the test and the reliability of the test result are improved at the same time.

Description

Technical Field

[0001] The present invention relates to the field of intelligent testing technology, and in particular to an intelligent testing method, device, equipment and storage medium for a photovoltaic inverter. Background Art

[0002] Early photovoltaic inverters mainly relied on traditional analog circuit design, with good performance stability, but limited efficiency and monitoring functions. With the increase in the scale of photovoltaic systems, the demand for intelligent inverters has become increasingly prominent. In the mid-2000s, the introduction of digital control technology enabled photovoltaic inverters to achieve more accurate power conversion and intelligent management. At the same time, the grid-connected function of the inverter has also been significantly improved. With the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, photovoltaic inverters not only have efficient power conversion capabilities, but also can monitor the operating status of the inverter in real time through embedded control systems, predict faults, and perform self-diagnosis. Intelligent testing methods have emerged, which can improve the stability and reliability of the system through remote monitoring and automated testing, and significantly reduce the cost of manual testing. However, the current traditional photovoltaic inverter testing methods often ignore the impact of shielding factors on inverter performance, especially in actual use environments, where shielding of photovoltaic modules is a common phenomenon. If the photovoltaic modules are partially or completely shielded and cannot obtain sufficient light, the input voltage and current of the inverter will drop significantly, affecting the power generation efficiency and even causing the inverter to fail to start or operate normally. At the same time, existing technologies often obtain performance data of photovoltaic inverters through static tests, but ignore the adaptability of the inverter under different light intensities and shielding conditions, which leads to low intelligence level of anti-shielding tests and low reliability of test results. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent testing method, device, equipment and storage medium for a photovoltaic inverter to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent testing method for a photovoltaic inverter is provided, the method comprising the following steps: Step S1: Acquire photovoltaic inverter structure data; deploy a shielding simulation device on the photovoltaic inverter structure data to generate photovoltaic component shielding simulation device deployment data; collect key structure data on the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; Step S2: simulating the shading test scenario for the deployment data of the photovoltaic component shading simulation device to obtain the photovoltaic inverter joint test power data; performing a current-voltage change trend analysis on the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to generate the current-voltage change trend data; performing a maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data to generate the inverter maximum power point tracking impact data; Step S3: using a light intensity sensor to collect inverter light intensity data for inverter shading test scene data, and obtaining inverter light intensity collection data; performing model training on inverter maximum power point tracking impact data, and generating an inverter anti-shading capability prediction model; using the inverter anti-shading capability prediction model to predict the anti-shading capability of photovoltaic inverter joint test power data, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on photovoltaic inverter anti-shading capability prediction data through inverter light intensity collection data, and generating photovoltaic inverter actual anti-shading capability data; Step S4: Visualize the actual anti-shading capability data of the photovoltaic inverter to generate a photovoltaic inverter anti-shading performance report.

[0005] By acquiring detailed structural data of the photovoltaic inverter and deploying a shielding simulation device, the present invention can comprehensively collect key operating data of the inverter in a simulated shielding environment to ensure the authenticity and comprehensiveness of the test data, which provides standardized benchmark data for subsequent testing and analysis, thereby providing a reliable basis for performance evaluation and optimization. By simulating the shielding scene of the photovoltaic component, generating joint test power data and performing current-voltage change trend analysis, the electrical characteristics of the inverter under different shielding conditions can be dynamically captured, which provides data support for in-depth understanding of the performance changes of the inverter under actual working conditions. At the same time, combined with the maximum power point tracking (MPPT) impact analysis, the impact of shielding on the inverter efficiency can be accurately evaluated, thereby helping to optimize the inverter design and control strategy. The light intensity data collection during the shielding test of the inverter using the light intensity sensor can obtain the real response data of the inverter under different light intensity conditions. Combined with the trained anti-shielding ability prediction model, the anti-shielding performance of the inverter under different shielding conditions can be accurately predicted, which not only provides a scientific basis for inverter performance prediction, but also helps to personalize the inverter in practical applications and improve its reliability in complex environments. By visualizing the actual anti-shading capability data of the inverter, complex test results can be converted into an intuitive and easy-to-understand report format, allowing users or engineers to quickly identify problems and optimization directions. Data visualization not only enhances the readability of the test results, but also provides detailed operational suggestions for maintenance personnel in practical applications, which helps to improve the operation and maintenance efficiency and reliability of the inverter. Therefore, the present invention provides a performance detection process for photovoltaic inverters under shading conditions by introducing shading simulation, dynamic current-voltage analysis, anti-shading capability prediction and evaluation, and data visualization, while improving the intelligence level of the test and the reliability of the test results.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire photovoltaic inverter structure data; Step S12: screening the photovoltaic components of the inverter for the photovoltaic inverter structure data to obtain photovoltaic component structure screening data; deploying a shielding simulation device for the photovoltaic inverter according to the photovoltaic component structure screening data to generate photovoltaic component shielding simulation device deployment data; Step S13: screening the key operation structure of the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain the key operation structure data of the inverter; deploying operation sensors for the photovoltaic inverter according to the key operation structure data of the inverter, and collecting data from the deployed operation sensors to obtain initial photovoltaic inverter operation data; Step S14: performing data preprocessing on the initial photovoltaic inverter operation data to generate standard photovoltaic inverter operation data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

[0007] The present invention can simulate and identify the obstruction factors that affect the power generation efficiency of photovoltaic modules by deploying an obstruction simulation device in the photovoltaic inverter, which helps to discover potential problems in advance in the design stage, thereby improving the overall energy efficiency of the system. By screening the key operating structures of the inverter, it is ensured that only structures that have a significant impact on the system performance are monitored, which makes the deployed operating sensors more focused on core components and improves the accuracy and real-time performance of data collection. Data cleaning, denoising, missing value filling and standardization can eliminate interference factors in the data and ensure that the data used in subsequent analysis is more accurate and reliable, which is of great significance for subsequent fault diagnosis, performance prediction and other applications. Through this refined data processing and sensor deployment, the operating status of the photovoltaic inverter can be monitored in real time, and problems in operation can be discovered and solved in a timely manner, thereby improving the stability of the system and extending the service life of the equipment.

[0008] Preferably, step S2 comprises the following steps: Step S21: simulating a shielding test scenario for the photovoltaic component shielding simulation device deployment data to generate inverter shielding test scenario data; using a preset load change threshold range to perform a joint power output on the photovoltaic inverter according to the inverter shielding test scenario data to obtain photovoltaic inverter joint test power data; Step S22: Calculating the power loss percentage of the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to obtain power loss variation amplitude data; Step S23: performing current-voltage change trend analysis on the standard photovoltaic inverter operation data through the power loss change amplitude data to generate current-voltage change trend data; Step S24: performing maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data and the power loss change amplitude data, and generating inverter maximum power point tracking impact data.

[0009] The present invention simulates the shading test scenario of the photovoltaic module shading simulation device deployment data, and can evaluate the impact of different shading conditions on the photovoltaic inverter in advance, which helps to design a more effective shading protection scheme, thereby ensuring the stability of the system in a complex environment. The photovoltaic inverter is tested for joint power output according to the inverter shading test scenario data, which can accurately calculate the power change under different load conditions, provide effective data on the efficiency reduction of the photovoltaic system in actual operation, and predict potential performance losses in advance. By calculating the power loss percentage of the photovoltaic inverter joint test power data, the efficiency loss of the inverter under different working conditions can be quantitatively evaluated. This analysis helps to identify efficiency bottlenecks, optimize system configuration, and thus improve energy conversion efficiency. By analyzing the current and voltage change trends, the electrical characteristics of the inverter under different operating conditions can be monitored more carefully, and abnormal fluctuations or performance degradation can be identified, which is of great significance for early fault diagnosis and system adjustment. Based on the analysis of the impact of current-voltage change trend data and power loss change amplitude data on maximum power point tracking, the maximum power point tracking strategy of the inverter under different conditions can be optimized, which helps to ensure that the photovoltaic system can always maximize energy output under various load conditions and improve overall performance and benefits.

[0010] Preferably, step S21 includes the following steps: Step S211: performing shading test scene setting on the deployment data of the photovoltaic component shading simulation device to obtain shading test scene setting data, wherein the shading test scene setting includes a completely unshaded scene setting, a single-point shading scene setting, a linear shading scene setting, and a dynamic shading scene setting; Step S212: using the shading test scene setting data to simulate the shading process of the photovoltaic inverter to obtain shading process simulation data; recording the output power change of the photovoltaic inverter according to the shading process simulation data to obtain first output power change data; Step S213: Perform a dynamic change power test on the first output power change data based on a preset load change threshold range to generate second output power change data; perform non-overlapping data screening on the first output power change data and the second output power change data to obtain photovoltaic inverter joint test power data.

[0011] The present invention can simulate the shading conditions in various actual environments by setting different shading test scenes (such as completely unshaded, single-point shading, linear shading and dynamic shading), which provides a multi-angle evaluation for the optimization design of the photovoltaic system and ensures that the system can operate stably in various environments. By simulating the shading process, the change in the output power of the photovoltaic inverter when the shading occurs can be clearly understood, which helps to accurately evaluate the impact of different shading conditions on the performance of the inverter, thereby providing data basis for subsequent optimization. The output power change data is dynamically tested using a preset load change threshold range, which further reveals the responsiveness of the photovoltaic inverter under different load conditions, which can effectively evaluate the energy efficiency of the inverter in actual operation, especially the stability in the face of load fluctuations. By non-overlapping screening of different output power change data, irrelevant or redundant data can be eliminated to ensure that only valid data is used for further analysis. This process improves the accuracy and reliability of the data, so that the test results more truly reflect the actual performance of the photovoltaic inverter. Finally, the combined test power data obtained can be used to evaluate the comprehensive performance of the photovoltaic inverter under a variety of different shading and load conditions. This not only helps to optimize the system design, but also can identify performance bottlenecks in advance and ensure the optimal output power and efficiency in actual applications.

[0012] Preferably, step S24 includes the following steps: Step S241: Performing photovoltaic inverter relationship modeling on the current-voltage change trend data and the power loss change amplitude data, thereby obtaining a relationship modeling curve; performing preliminary positioning of the inverter maximum power point based on the relationship modeling curve, thereby obtaining preliminary maximum power point data; Step S242: performing maximum power point tracking response analysis according to the preliminary maximum power point data, thereby obtaining tracking response performance data; performing curve conversion on the tracking response performance data, and generating a maximum power point tracking response performance curve; Step S243: Calculate the mean curvature of the maximum power point tracking response performance curve to obtain maximum power point tracking stability data; perform power fluctuation amplitude analysis on the relationship modeling curve based on the tracking stability data to obtain inverter maximum power point tracking impact data.

[0013] The present invention can accurately depict the working characteristics of the photovoltaic inverter by modeling the current-voltage change trend data and the power loss change amplitude data. This relationship modeling provides a preliminary positioning basis for the maximum power point of the inverter and provides a reliable starting point for subsequent optimization. Response analysis based on the preliminary maximum power point data can reveal the maximum power point tracking capability of the inverter under different environments and load conditions, which helps to evaluate the real-time adjustment capability of the inverter in practical applications, ensure that the inverter can always track the optimal power point of the system, and improve energy efficiency. By converting the tracking response performance data into a curve, the dynamic changes in the maximum power point tracking process can be more intuitively displayed. This visual method helps technicians better understand the behavior of the inverter in a complex environment, thereby optimizing the maximum power point tracking algorithm and system tuning. By calculating the mean curvature of the maximum power point tracking response performance curve, the stability of the inverter in maintaining the maximum power point tracking in long-term operation can be evaluated, which is crucial to ensuring the stable operation of the system and avoiding the influence of power fluctuations on photovoltaic power generation efficiency. Power fluctuation amplitude analysis based on tracking stability data helps to identify system instability factors and perform targeted optimization. Finally, the inverter maximum power point tracking impact data can be generated to provide data support for further improving the maximum power point tracking accuracy of the system.

[0014] Preferably, step S3 comprises the following steps: Step S31: using a light intensity sensor to collect inverter light intensity data for inverter shielding test scene data to obtain inverter light intensity collection data; extracting inverter anti-shielding influence features for inverter maximum power point tracking influence data to obtain inverter anti-shielding feature data; Step S32: dividing the anti-shading feature data of the inverter into a data set to generate a model training set and a model test set; training the model training set using a convolutional neural network algorithm to generate an anti-shading capability prediction pre-model; optimizing and iterating the anti-shading capability prediction pre-model using the model test set, thereby generating an inverter anti-shading capability prediction model; Step S33: importing the photovoltaic inverter joint test power data into the inverter anti-shading capability prediction model to perform anti-shading capability prediction, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on the photovoltaic inverter joint test power data according to the inverter light intensity collection data, and generating photovoltaic inverter dynamic shading adaptability data; Step S34: adjusting actual prediction parameters of the photovoltaic inverter anti-shading capability prediction data using the photovoltaic inverter dynamic shading adaptability data, thereby obtaining the photovoltaic inverter actual anti-shading capability data.

[0015] The present invention collects the inverter shielding test scene data through a light intensity sensor, and can monitor the changes in light intensity under different shielding conditions in real time, which provides basic data for the subsequent anti-shielding ability evaluation and helps to more accurately reflect the light changes in the actual working environment. By extracting the anti-shielding influence characteristics of the inverter, the working characteristics of the inverter under different shielding conditions can be identified, which helps to understand how the inverter copes with the challenge of shielding. This process can provide data support for optimizing the design and control strategy of the inverter, especially in complex environments. By dividing the anti-shielding feature data into training sets and test sets, and combining the convolutional neural network (CNN) algorithm for model training, intelligent prediction of the inverter's anti-shielding ability can be achieved. The powerful characteristics of the CNN model make the prediction results more accurate and can handle complex input data patterns. By optimizing and iterating the model test set, the accuracy of the anti-shielding ability prediction model can be continuously improved to ensure that it has better adaptability in the actual environment, so that the performance of the photovoltaic inverter under various shielding conditions can be more accurately estimated and regulated. Dynamic shading adaptability assessment based on the light intensity data collected from the inverter can monitor the inverter's adaptability to shading in real time, which not only provides real-time feedback on the inverter's performance, but also guides system adjustments to cope with power losses caused by different shading. Based on the dynamic shading adaptability data of the photovoltaic inverter, actual prediction parameter adjustments are made based on the shading resistance prediction data to further optimize the inverter's performance under dynamic shading conditions, which ensures that the inverter can always operate efficiently in complex environments and avoid performance fluctuations caused by shading.

[0016] Preferably, performing dynamic shading adaptability evaluation on photovoltaic inverter joint test power data according to inverter light intensity collection data includes: Perform illumination change rate analysis on the light intensity acquisition data of the inverter to generate light intensity change amplitude data; perform inverter response monitoring on the photovoltaic inverter joint test power data based on the light intensity change amplitude data to generate inverter response monitoring data; According to the preliminary maximum power point data, the response time of the inverter response monitoring data is evaluated to generate dynamic shading response time evaluation data; the dynamic shading response time evaluation data is used to divide the inverter response monitoring data into light intensity change response power segments to generate dynamic shading response power segments; Perform power fluctuation recovery timing analysis on the dynamic shading response power segment to generate dynamic shading power recovery timing data; perform output power stability evaluation on the dynamic shading response power segment through the dynamic shading power recovery timing data to generate output power stability evaluation data; The dynamic shading response time evaluation data and the output power stability evaluation data are used to evaluate the dynamic shading adaptability of the photovoltaic inverter joint test power data, thereby generating the dynamic shading adaptability data of the photovoltaic inverter.

[0017] The present invention can accurately capture the rapid changes of light in the shading environment by analyzing the light change rate of the inverter light intensity collection data, which provides detailed light fluctuation data for subsequent analysis and helps evaluate the inverter's response ability to different light conditions. The inverter response monitoring based on the light intensity change amplitude data can track the performance of the inverter under dynamic light changes in real time. The inverter response monitoring data can reflect the stability and adaptability of the inverter in a rapidly changing environment, and provide a reliable basis for adjusting the inverter's operating strategy. By evaluating the response time of the inverter response monitoring data, the reaction speed of the inverter when the light changes rapidly can be understood, which is crucial for optimizing the inverter's regulation mechanism and improving its response efficiency, especially in scenarios where shading conditions change frequently. By using the dynamic shading response time evaluation data to segment the power segment, the output power segment of the inverter under different light intensities can be clarified, which helps to further analyze the output characteristics of the inverter under different light change rates, and find out the performance bottleneck and adjustment direction. Performing power fluctuation recovery timing analysis on the dynamic shading response power segment can reveal the power recovery process of the inverter after changes in light. This analysis provides intuitive data support for the power stability of the inverter under different shading scenarios, helping to improve the recovery capability and stability of the inverter. By performing stability evaluation on the power recovery timing data, the output power stability of the inverter under different shading conditions can be quantified, which is crucial to ensure the stable operation of the photovoltaic system in a dynamic environment, especially to ensure power generation efficiency and system reliability. By combining the response time evaluation data and the output power stability evaluation data to conduct a comprehensive evaluation of the photovoltaic inverter joint test power data, the adaptability of the inverter under dynamic shading conditions can be fully understood, which enables the inverter to make more precise adjustments according to different shading modes and light changes, thereby improving its overall performance.

[0018] In this specification, an intelligent testing device for a photovoltaic inverter is provided, which is used to perform the intelligent testing method for the photovoltaic inverter. The intelligent testing device for the photovoltaic inverter includes: The device deployment module is used to obtain the photovoltaic inverter structure data; perform shielding simulation device deployment on the photovoltaic inverter structure data to generate photovoltaic module shielding simulation device deployment data; perform key structure data collection on the photovoltaic inverter structure data through the photovoltaic module shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; The shading simulation module is used to simulate the shading test scenario for the deployment data of the PV module shading simulation device to obtain the PV inverter joint test power data; perform current-voltage change trend analysis on the standard PV inverter operation data based on the PV inverter joint test power data to generate current-voltage change trend data; perform maximum power point tracking impact analysis on the PV inverter joint test power data based on the current-voltage change trend data to generate inverter maximum power point tracking impact data; The anti-shading capability evaluation module is used to collect the inverter light intensity data of the inverter shading test scene data using the light intensity sensor to obtain the inverter light intensity collection data; to perform model training on the inverter maximum power point tracking impact data to generate the inverter anti-shading capability prediction model; to use the inverter anti-shading capability prediction model to predict the anti-shading capability of the photovoltaic inverter joint test power data to generate the photovoltaic inverter anti-shading capability prediction data; to perform dynamic shading adaptability evaluation on the photovoltaic inverter anti-shading capability prediction data through the inverter light intensity collection data to generate the actual anti-shading capability data of the photovoltaic inverter; The visualization module is used to visualize the actual anti-shading capability data of the photovoltaic inverter, thereby generating a photovoltaic inverter anti-shading performance report.

[0019] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the intelligent testing method for the photovoltaic inverter is implemented.

[0020] A storage medium stores a computer program, which implements the above-mentioned intelligent testing method for the photovoltaic inverter when executed by a processor.

[0021] The beneficial effect of the present invention is that by acquiring the structural data of the photovoltaic inverter, the inverter is simulated by simulating the shielding device. This step provides standard data for subsequent tests to ensure that the test and analysis under different shielding conditions are based on real and effective inverter structural data. By simulating the deployment data of the shielding device, the power data of the photovoltaic inverter under different shielding conditions can be generated, and the electrical characteristics of the inverter under these conditions can be analyzed in combination with the current-voltage change trend data, and the impact of the maximum power point tracking can be further evaluated. This process provides the necessary basic data for evaluating the maximum power point tracking performance of the inverter. The light intensity data of the inverter under different shielding test scenarios is collected by the light intensity sensor, and the anti-shielding ability of the inverter is evaluated by training the prediction model. The module uses real-time data to provide the system with a prediction of the ability of the inverter to adapt to different degrees of shielding, and can perform adaptability evaluation according to the actual dynamic light intensity changes. Finally, the actual anti-shielding ability data is displayed by data visualization means to generate a detailed anti-shielding performance report. The report can not only provide clear analysis results for the inverter performance, but also provide strong data support for future optimization design and improvement. Therefore, the present invention provides a performance detection process for photovoltaic inverters under shading conditions by introducing shading simulation, dynamic current-voltage analysis, anti-shading capability prediction and evaluation, and data visualization, while improving the intelligence level of the test and the reliability of the test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the steps of an intelligent testing method for a photovoltaic inverter; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0025] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0026] To achieve this, please refer to Figures 1 to 3 , an intelligent testing method for a photovoltaic inverter, the method comprising the following steps: Step S1: Acquire photovoltaic inverter structure data; deploy a shielding simulation device on the photovoltaic inverter structure data to generate photovoltaic component shielding simulation device deployment data; collect key structure data on the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; Step S2: simulating the shading test scenario for the deployment data of the photovoltaic component shading simulation device to obtain the photovoltaic inverter joint test power data; performing a current-voltage change trend analysis on the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to generate the current-voltage change trend data; performing a maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data to generate the inverter maximum power point tracking impact data; Step S3: using a light intensity sensor to collect inverter light intensity data for inverter shading test scene data, and obtaining inverter light intensity collection data; performing model training on inverter maximum power point tracking impact data, and generating an inverter anti-shading capability prediction model; using the inverter anti-shading capability prediction model to predict the anti-shading capability of photovoltaic inverter joint test power data, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on photovoltaic inverter anti-shading capability prediction data through inverter light intensity collection data, and generating photovoltaic inverter actual anti-shading capability data; Step S4: Visualize the actual anti-shading capability data of the photovoltaic inverter to generate a photovoltaic inverter anti-shading performance report.

[0027] By acquiring detailed structural data of the photovoltaic inverter and deploying a shielding simulation device, the present invention can comprehensively collect key operating data of the inverter in a simulated shielding environment to ensure the authenticity and comprehensiveness of the test data, which provides standardized benchmark data for subsequent testing and analysis, thereby providing a reliable basis for performance evaluation and optimization. By simulating the shielding scene of the photovoltaic component, generating joint test power data and performing current-voltage change trend analysis, the electrical characteristics of the inverter under different shielding conditions can be dynamically captured, which provides data support for in-depth understanding of the performance changes of the inverter under actual working conditions. At the same time, combined with the maximum power point tracking (MPPT) impact analysis, the impact of shielding on the inverter efficiency can be accurately evaluated, thereby helping to optimize the inverter design and control strategy. The light intensity data collection during the shielding test of the inverter using the light intensity sensor can obtain the real response data of the inverter under different light intensity conditions. Combined with the trained anti-shielding ability prediction model, the anti-shielding performance of the inverter under different shielding conditions can be accurately predicted, which not only provides a scientific basis for inverter performance prediction, but also helps to personalize the inverter in practical applications and improve its reliability in complex environments. By visualizing the actual anti-shading capability data of the inverter, complex test results can be converted into an intuitive and easy-to-understand report format, allowing users or engineers to quickly identify problems and optimization directions. Data visualization not only enhances the readability of the test results, but also provides detailed operational suggestions for maintenance personnel in practical applications, which helps to improve the operation and maintenance efficiency and reliability of the inverter. Therefore, the present invention provides a performance detection process for photovoltaic inverters under shading conditions by introducing shading simulation, dynamic current-voltage analysis, anti-shading capability prediction and evaluation, and data visualization, while improving the intelligence level of the test and the reliability of the test results.

[0028] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of an intelligent testing method for a photovoltaic inverter of the present invention. In this example, the intelligent testing method for a photovoltaic inverter includes the following steps: Step S1: Acquire photovoltaic inverter structure data; deploy a shielding simulation device on the photovoltaic inverter structure data to generate photovoltaic component shielding simulation device deployment data; collect key structure data on the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; In an embodiment of the present invention, structural data is imported by using three-dimensional scanning (such as laser scanning) technology or computer-aided design (CAD) model. The existing inverter is disassembled and the size, position and relationship of each component are recorded to generate a structural data set. The data is stored in a standardized format, such as STEP, IGES or other engineering graphic data formats. According to factors such as the installation position of the inverter and the angle of the photovoltaic module, a shielding simulation device (such as a shielding model, a light source simulator, etc.) is designed. Computer simulation software (such as MATLAB, ANSYS, etc.) is used to simulate the effects of different ambient lighting and object shielding on the inverter and its electrical components. A virtual shielding test is performed on the inverter and its key components to generate simulation data under different lighting and shielding conditions, and shielding simulation deployment data is output, including information such as the placement position, type, size, etc. of the shielding object, and associated with the structural data of the inverter. Sensors (such as temperature sensors, light sensors, voltage / current sensors, etc.) are used to collect data at key parts of the inverter. The working status of the photovoltaic inverter is monitored in real time, including power output, temperature changes, current fluctuations, etc., especially performance changes caused by shielding. Compare the collected raw data with the simulation results to identify which components are most sensitive to different shading conditions. Finally, obtain the standard photovoltaic inverter operation data, including but not limited to: maximum power point tracking (MPPT) efficiency, heat loss, output voltage fluctuation, etc. under different shading simulations. Convert all data into a unified standard format, and perform data cleaning and denoising to eliminate unnecessary errors. Use statistical analysis methods (such as regression analysis, correlation analysis, etc.) to identify the factors most relevant to inverter performance. Based on these analysis results, generate a performance estimation model for photovoltaic inverters under various environmental factors to provide a basis for subsequent optimization.

[0029] Step S2: simulating the shading test scenario for the deployment data of the photovoltaic component shading simulation device to obtain the photovoltaic inverter joint test power data; performing a current-voltage change trend analysis on the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to generate the current-voltage change trend data; performing a maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data to generate the inverter maximum power point tracking impact data; In an embodiment of the present invention, different shielding scenarios are designed by generating the deployment data of the shielding simulation device. These scenarios specifically include changes in illumination angle, adjustment of the position of shielding objects (such as buildings, trees, etc.), and simulations under different seasons and weather conditions. In different simulation scenarios, the photovoltaic modules are shielded by virtual or actual test equipment (such as solar simulators, shielding object control devices). The power output data of the inverter in each scenario is recorded, especially the joint test power data. The power data of the photovoltaic inverter is collected using a real-time monitoring system, especially the instantaneous power and average power output under different shielding conditions, and the joint test power data is output. These data should include power output changes under different shielding conditions and light intensities. The obtained joint test power data is compared and analyzed with the standard photovoltaic inverter operation data (such as open circuit voltage, short circuit current, maximum power point voltage, etc.). Under different shielding test scenarios, the changes in the current-voltage (IV) curve are analyzed. Generally, the IV characteristics of photovoltaic modules change with changes in light intensity and shielding, especially the position of the maximum power point (MPP). Through data visualization and curve fitting, the current-voltage change trend, especially the change of maximum power point voltage and current, is obtained. The relationship between current and voltage is found by regression analysis method, and converted into trend data to generate current-voltage change trend data, which includes the relationship between current and voltage changes under different shading scenarios, especially the fluctuation of MPP. Based on the combined test power data and standard operation data, the power loss amplitude under different shading conditions is calculated. By comparing the power output of the inverter before and after shading, the power loss ratio of shading can be obtained. According to the obtained current-voltage change trend, the maximum power point tracking under different shading conditions is analyzed. In particular, the impact of the maximum power point (MPP) change on power output is analyzed, including the fluctuation of MPP voltage and current. An impact analysis model is constructed to analyze the maximum power point tracking accuracy of photovoltaic inverters under different shading scenarios by integrating current-voltage change trend data and power loss amplitude data. Use algorithms (such as optimization analysis of the maximum power point tracking algorithm) to evaluate the decline in inverter MPPT performance under different shading conditions, and output the inverter maximum power point tracking impact data, which includes the change in MPP, the tracking error of the MPPT algorithm, and the power loss caused by shading. Compare the MPPT impact data of different test scenarios to find the main influencing factors of obstructions on maximum power point tracking. Optimize the MPPT algorithm of the photovoltaic inverter based on the data, improve the maximum power point tracking accuracy under shading conditions, and output inverter performance optimization suggestions for different shading types and intensities, such as adaptive MPPT algorithm, dynamic adjustment control strategy, etc.

[0030] Step S3: using a light intensity sensor to collect inverter light intensity data for inverter shading test scene data, and obtaining inverter light intensity collection data; performing model training on inverter maximum power point tracking impact data, and generating an inverter anti-shading capability prediction model; using the inverter anti-shading capability prediction model to predict the anti-shading capability of photovoltaic inverter joint test power data, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on photovoltaic inverter anti-shading capability prediction data through inverter light intensity collection data, and generating photovoltaic inverter actual anti-shading capability data; In an embodiment of the present invention, by installing multiple light intensity sensors in the working area of ​​the inverter, especially on the light-receiving surface of the photovoltaic module, these sensors should be able to collect light intensity data at different positions in real time, especially under shading conditions. According to the shading test scene data in step S2, create test scenes under different shading environments. The sensor should record light intensity changes in these scenes, especially the fluctuations of light intensity before and after the inverter panel. The data of the light intensity sensor is collected by a real-time monitoring system and stored in a standard data format (such as CSV, JSON, etc.). These data should include the light intensity readings at each sensor position, as well as the operating status of the inverter during the test, and output the inverter light intensity collection data, which reflects the light intensity changes of the inverter under different shading environments. Integrate the inverter maximum power point tracking impact data (such as MPP change amplitude, power loss, etc.) with the inverter light intensity collection data. Feature selection and processing of the data, including normalization or standardization of factors such as light intensity changes, power loss, and MPP fluctuations. To ensure the effectiveness of the model, remove noise data and perform data cleaning. Use machine learning methods (such as support vector machine SVM, decision tree, random forest or neural network) for training, and generate the inverter anti-shading ability prediction model based on the integrated data set. The training process can use methods such as cross-validation to avoid overfitting and optimize the accuracy of the model. Use evaluation indicators such as accuracy, recall, and mean square error (MSE) to evaluate the trained prediction model. Adjust the model parameters according to the evaluation results to ensure the stability and accuracy of the model's prediction ability in practical applications, and output the inverter anti-shading ability prediction model, which can predict the inverter's anti-shading ability based on different shading test conditions and light intensity data. The collected photovoltaic inverter joint test power data (such as power output, MPP change) is used as input, combined with the collected light intensity data, and passed to the trained anti-shading ability prediction model. Based on the input data, the model predicts the performance of the inverter under different shading conditions, especially the anti-shading ability in maximum power point tracking (MPPT). The prediction results include power loss and MPP variation under different shading intensities, and generate PV inverter anti-shading capability prediction data, which includes the performance evaluation results of the inverter under various shading conditions, such as the relationship between shading intensity and power output, and the dynamic adaptability of the inverter. The collected real-time light intensity data is combined with the anti-shading capability prediction data to conduct dynamic adaptability evaluation. This process should take into account real-time environmental changes, such as the movement of obstructions and fluctuations in light intensity. Based on dynamic light intensity data, analyze how the inverter adjusts its maximum power point tracking strategy to cope with changes caused by shading. Feedback control mechanisms can be used to monitor the real-time response of the inverter and compare the differences between the predicted data and the actual data. By comparing the power output under the predicted data and the actual light intensity changes, the adaptability and stability of the inverter are evaluated.Analyze whether the inverter can adjust its working state in a timely and accurate manner to adapt to changes in shading, and output the actual anti-shading capability data of the PV inverter. The data should include the anti-shading capability evaluation results of the inverter when operating in the actual environment, such as actual power output, maximum power point tracking accuracy, adaptive response time, etc. Compare the predicted anti-shading capability data of the PV inverter with the actual anti-shading capability data to find out the gap between the two. Based on the evaluation results, put forward optimization suggestions, such as improving the MPPT algorithm, enhancing the dynamic adaptability of the inverter, or improving the shading perception and response mechanism. Based on the new data collected in actual operation, continuously optimize the prediction model and the anti-shading design of the inverter to ensure its stability and efficiency in different environments.

[0031] Step S4: Visualize the actual anti-shading capability data of the photovoltaic inverter to generate a photovoltaic inverter anti-shading performance report.

[0032] In an embodiment of the present invention, by checking and cleaning the actual anti-shading capability data of the photovoltaic inverter, invalid, missing or abnormal data is removed. Ensure that the data contains performance indicators of the inverter under different shading conditions, such as power output, MPP change, adaptive response, etc. Standardize the data to ensure that the data in different time periods and different shading scenarios are comparable. According to actual needs, unit unification, normalization and other processing are required. Integrate data from different sources (such as light intensity collection data, maximum power point tracking data, anti-shading capability prediction data, etc.) for further analysis and visualization. Select tools suitable for data visualization, such as Matplotlib, Plotly, Tableau, Power BI, etc. Select static or dynamic visualization methods according to the complexity and display requirements of the data. Use line graphs, scatter plots and other methods to display the power output and MPP changes of the inverter under different shading conditions. For example, show the relationship between shading intensity and power output, or show the MPP tracking accuracy under different light intensities. Use heat maps to display the performance changes of the inverter under different shading intensities, especially indicators such as power loss and MPP fluctuations. Use 3D graphs or multi-dimensional data views (such as radar graphs) to show the changes in the inverter's anti-shading ability under different factors (light, shading position, time, etc.). If the data is time-dependent, a time series graph can be used to show the changes in the inverter's anti-shading ability under long-term operation, such as power fluctuations at different time periods every day. Based on the comparison of actual data and predicted data, design a visual chart to show the inverter's adaptive response and reflect its anti-shading ability in the actual environment. Based on the previously collated data, use the selected visualization tool to draw charts and generate graphics that show the performance of the PV inverter, including: displaying the power output change chart under different shading scenarios to intuitively show the impact of shading on the inverter performance. Draw the maximum power point change curve to reveal how the inverter adjusts to maximize the output power under shading. Show the inverter's adaptability to real-time shading changes, including data such as the change in power output before and after shading, response time, etc. Adjust the chart's color, annotation, scale, etc. as needed to make the data visualization clearer and easier to understand. Integrate the visualization charts into a complete anti-shading performance report and provide support for subsequent decision-making.

[0033] Preferably, step S1 comprises the following steps: Step S11: Acquire photovoltaic inverter structure data; Step S12: screening the photovoltaic components of the inverter for the photovoltaic inverter structure data to obtain photovoltaic component structure screening data; deploying a shielding simulation device for the photovoltaic inverter according to the photovoltaic component structure screening data to generate photovoltaic component shielding simulation device deployment data; Step S13: screening the key operation structure of the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain the key operation structure data of the inverter; deploying operation sensors for the photovoltaic inverter according to the key operation structure data of the inverter, and collecting data from the deployed operation sensors to obtain initial photovoltaic inverter operation data; Step S14: performing data preprocessing on the initial photovoltaic inverter operation data to generate standard photovoltaic inverter operation data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

[0034] In an embodiment of the present invention, the structural data of the photovoltaic inverter is collected through existing photovoltaic inverter design documents or field surveys, and these data include information such as the size, components, and installation location of the inverter. The structural data is accurately obtained through laser scanning or 3D modeling technology. The detailed physical structural data of the photovoltaic inverter is obtained from the inverter design system, including the circuit design, wiring diagram, connection method, and installation space layout of the inverter. It can be accurately obtained through 3D modeling technology and reverse engineering methods, combined with data provided by the original equipment manufacturer (OEM). According to the design requirements of the inverter, the working environment and parameters of the photovoltaic module are analyzed, including the power generation efficiency, angle, position, etc. of the module. The best module is selected through the photovoltaic module screening algorithm. Based on the structural screening data, the shading (such as buildings, trees, etc.) encountered by the photovoltaic module under different time and weather conditions is simulated, and the corresponding shading simulation device is deployed. These devices are calculated and deployed using light simulation software (such as PVsyst or SAM) to ensure that the power generation efficiency of the photovoltaic module is maximized. According to the shading simulation results of the photovoltaic modules, analyze which structural components (such as the internal circuit of the inverter, connectors, cooling system, etc.) are affected, so as to screen out the key operating components of the inverter. Deploy sensors on the selected key components to collect operating parameters such as temperature, humidity, current, and voltage. The deployment of sensors should take into account the particularity of the inverter working environment, such as high temperature and strong electromagnetic field. The sensors collect operating data in real time and transmit the data to the data acquisition system to form a preliminary photovoltaic inverter operation data set. Remove invalid data (such as duplicate values, error values, etc.) to ensure the integrity of the data set. Use filtering technology (such as low-pass filter, Gaussian filter, etc.) to remove noise from sensor data. Use interpolation or statistical methods to fill in missing data to ensure data consistency. Standardize different types of data (voltage, current, temperature, etc.) to make them have the same dimension, which is convenient for subsequent analysis and model training.

[0035] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: simulating a shielding test scenario for the photovoltaic component shielding simulation device deployment data to generate inverter shielding test scenario data; using a preset load change threshold range to perform a joint power output on the photovoltaic inverter according to the inverter shielding test scenario data to obtain photovoltaic inverter joint test power data; Step S22: Calculating the power loss percentage of the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to obtain power loss variation amplitude data; Step S23: performing current-voltage change trend analysis on the standard photovoltaic inverter operation data through the power loss change amplitude data to generate current-voltage change trend data; Step S24: performing maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data and the power loss change amplitude data, and generating inverter maximum power point tracking impact data.

[0036] In an embodiment of the present invention, different shielding test scenarios (such as partial shielding, full shielding, dynamic shielding, etc.) are constructed by using the data of the deployed photovoltaic component shielding simulation device. Lighting simulation software or a custom calculation model can be used to simulate the light intensity and angle changes under different shielding degrees. During the simulation process, weather factors (such as clouds, temperature changes, etc.) and the position, size and dynamic changes of shielding objects (such as buildings, trees, etc.) are considered. According to the preset load change threshold range (such as power demand under different load conditions), the power output of the inverter under various load conditions is calculated by simulating the joint working state of the photovoltaic inverter and photovoltaic components in the scene. The power output model (such as the maximum power point tracking model, the inverter efficiency model) is combined with the test scene data to obtain the photovoltaic inverter joint test power data. Compare the power output of the photovoltaic inverter under standard operating conditions (such as the power output when there is no shielding and the load is rated) with the joint test power output (power output under shielding or other change conditions), and calculate the power loss percentage. Calculation formula: Power loss percentage = (standard power − test power) ÷ standard power × 100%; Track the change in power loss percentage under different test scenarios to generate power loss change amplitude data, which can be used to analyze the performance fluctuations of photovoltaic inverters under different environmental changes (such as shading, load changes, etc.). According to the power loss change amplitude data generated in step S22, the current and voltage change trends of the photovoltaic inverter are further analyzed. The change trends of current and voltage are directly related to power output, so this analysis can reveal the working status of the inverter under different conditions. Use a real-time data acquisition system or simulation tool to draw a current-voltage (IV) curve to analyze the changes in the working voltage and current of the photovoltaic inverter under different power losses. Based on the current-voltage data, generate trend data charts (such as IV curves, power curves, etc.), which can help evaluate the performance of the inverter and identify the changes in the maximum power point and the reasons for the decline in efficiency. Use the current-voltage (IV) change trend and power loss data of the inverter to analyze the position changes of the maximum power point (MPP). MPP is the optimal operating point in a photovoltaic system, where the product of current and voltage is the largest. It is usually tracked in real time using a maximum power point tracking (MPPT) algorithm. Using a maximum power point tracking algorithm (such as Perturb and Observe, Incremental Conductance, etc.), combined with current and voltage data under different shading conditions and load changes, the position change of the maximum power point is analyzed. By comparing the changes in the maximum power point under different test scenarios, the inverter maximum power point tracking impact data is generated. This data helps evaluate whether the inverter can accurately track the maximum power point, and the impact of environmental factors (such as shading and load changes) on the accuracy of maximum power point tracking.Sensitivity analysis techniques can be used to further identify which factors (such as shading level, weather conditions, etc.) have the greatest impact on maximum power point tracking.

[0037] Preferably, step S21 includes the following steps: Step S211: performing shading test scene setting on the deployment data of the photovoltaic component shading simulation device to obtain shading test scene setting data, wherein the shading test scene setting includes a completely unshaded scene setting, a single-point shading scene setting, a linear shading scene setting, and a dynamic shading scene setting; Step S212: using the shading test scene setting data to simulate the shading process of the photovoltaic inverter to obtain shading process simulation data; recording the output power change of the photovoltaic inverter according to the shading process simulation data to obtain first output power change data; Step S213: Perform a dynamic change power test on the first output power change data based on a preset load change threshold range to generate second output power change data; perform non-overlapping data screening on the first output power change data and the second output power change data to obtain photovoltaic inverter joint test power data.

[0038] In an embodiment of the present invention, an environment without any shielding is simulated to ensure that the photovoltaic module receives sunlight completely. A completely unobstructed scene is set by simulation software (such as PVsyst, SAM, etc.) or an actually deployed photovoltaic module shielding simulation device, and the output power of the photovoltaic inverter at this time is measured and recorded as a reference. A shielding is set at a certain position in a photovoltaic module, such as a small object (such as a branch, a building, etc.) shielding a certain point of the photovoltaic panel. This scene is created using physical shielding simulation or computer simulation, and the effect of the shielding on the output power of the photovoltaic module is recorded. A linear shielding source (such as a long strip object, such as a protruding part of a roof or the shadow of a tall tree) is simulated to shield a certain area of ​​the photovoltaic panel. This setting can help analyze the linear effect of the shielding source on the power output and record the relationship between the output power and the change of the shielding range. A dynamic shielding source is set, such as simulating the effect of the sun's trajectory or cloud changes on the photovoltaic module. In a dynamic scene, the shielding changes over time, and simulating this scene can more realistically reflect the working performance of the photovoltaic inverter in the actual environment. Based on the different shielding test scenarios defined in step S211, simulation software or a custom mathematical model is used to simulate the operation process of the inverter under different shielding scenarios. The simulation process should cover the gradual change of the output power of the photovoltaic module in the process of shielding from completely unshielded to fully shielded. In each simulation step, the output power of the photovoltaic inverter is calculated and recorded to form a set of simulation data. The output power of the photovoltaic inverter in each scenario is recorded in real time to obtain the first output power change data, and the output power change should change with the change of the shielding degree. The recorded data includes parameters such as output power value, shielding rate, time, etc., which are convenient for subsequent analysis. According to the preset load change threshold range, the first output power change data is dynamically tested for power change. By adjusting the load of the photovoltaic inverter (for example, simulating different grid loads or simulating load fluctuations), the change of the output power of the photovoltaic inverter under different load conditions is recorded. When using the load change test, the power output of the inverter will fluctuate according to the change of the load, and the second output power change data is obtained, which helps to understand the performance of the inverter under load changes. The first output power change data and the second output power change data are screened for non-overlapping data to ensure the independence and validity of the data sets. During the screening process, the repeated parts in the two sets of data (i.e. the same time period or the same power change mode) can be removed to ensure that the final data is not repeated. The screened data set should include the combined power output performance of the inverter under different shading and load changes, providing a comprehensive performance analysis.The first output power change data and the second output power change data that have been filtered out for non-overlapping data are merged to form the final photovoltaic inverter joint test power data. These data include the power output of the inverter under different environmental conditions (such as shading and load changes), which is convenient for subsequent power loss analysis, maximum power point tracking (MPPT) optimization, etc.

[0039] Preferably, step S24 includes the following steps: Step S241: Performing photovoltaic inverter relationship modeling on the current-voltage change trend data and the power loss change amplitude data, thereby obtaining a relationship modeling curve; performing preliminary positioning of the inverter maximum power point based on the relationship modeling curve, thereby obtaining preliminary maximum power point data; Step S242: performing maximum power point tracking response analysis according to the preliminary maximum power point data, thereby obtaining tracking response performance data; performing curve conversion on the tracking response performance data, and generating a maximum power point tracking response performance curve; Step S243: Calculate the mean curvature of the maximum power point tracking response performance curve to obtain maximum power point tracking stability data; perform power fluctuation amplitude analysis on the relationship modeling curve based on the tracking stability data to obtain inverter maximum power point tracking impact data.

[0040] In an embodiment of the present invention, by using current-voltage (IV) change trend data and power loss change amplitude data, a relationship model between the output power of a photovoltaic inverter and the current and voltage is established through mathematical modeling techniques (such as regression analysis, machine learning methods, etc.). The relationship modeling curve should depict the change law of the inverter output power according to the actual current and voltage change trends and the amplitude fluctuations of the power loss. Polynomial regression or other fitting methods can be used to generate this curve. Based on the relationship modeling curve, the position of the maximum power point (MPP) is preliminarily determined. The MPP is usually located at the optimal point of the current-voltage curve, which corresponds to the maximum power output of the photovoltaic system. Through the analysis of the relationship modeling curve, the position of the MPP can be preliminarily determined, and preliminary maximum power point data can be extracted from it. The preliminary maximum power point data usually includes the voltage and current values ​​of the MPP, which provide a preliminary reference for subsequent maximum power point tracking. Based on the preliminary maximum power point data, a maximum power point tracking response analysis is performed. The goal of this analysis is to evaluate how the inverter responds to changes in the maximum power point under actual conditions. The tracking process of the maximum power point can be analyzed by simulating the impact of load changes, environmental changes (such as sunlight intensity, temperature, etc.) and shading conditions on the performance of the inverter. According to the actual tracking situation, record the response time, stability and other parameters of the inverter during maximum power point tracking to generate tracking response performance data. Convert the tracking response performance data into curve form (for example, tracking response time-stability curve, power output-response time curve, etc.), which can help evaluate the performance of the inverter when tracking the maximum power point and reflect its tracking ability under different environmental conditions. The maximum power point tracking response performance curve generated in step S242 is subjected to the mean value of the curve curvature calculation. Curvature is a mathematical concept that describes the degree of change of the curve, which can be used to measure the response stability of the inverter during the maximum power point tracking process. The mean value of the curve curvature can be calculated by a numerical method, such as a second-order difference calculation based on discrete points, to obtain the overall stability characteristics of the tracking response curve. Based on the mean value of the curve curvature, the stability data of the maximum power point tracking is obtained. If the mean value of the curvature is small, it means that the tracking process is stable and the inverter can quickly and accurately locate the maximum power point; if the mean value of the curvature is large, it means that the inverter has large oscillations or instability during the tracking process. According to the tracking stability data, the power fluctuation amplitude of the inverter when tracking the maximum power point is further analyzed. The fluctuation range of power output, frequency and amplitude of fluctuations in different time periods or under different load conditions can be calculated. Power fluctuation amplitude analysis helps to reveal whether the inverter can continue to work stably at the maximum power point in actual work, or whether frequent power fluctuations occur under certain environmental conditions. Based on the analysis results of power fluctuation amplitude, the maximum power point tracking impact data of the inverter is obtained, which can help further optimize the maximum power point tracking algorithm of the inverter and improve its stability and efficiency under different environmental conditions.

[0041] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: using a light intensity sensor to collect inverter light intensity data for inverter shielding test scene data to obtain inverter light intensity collection data; extracting inverter anti-shielding influence features for inverter maximum power point tracking influence data to obtain inverter anti-shielding feature data; Step S32: dividing the anti-shading feature data of the inverter into a data set to generate a model training set and a model test set; training the model training set using a convolutional neural network algorithm to generate an anti-shading capability prediction pre-model; optimizing and iterating the anti-shading capability prediction pre-model using the model test set, thereby generating an inverter anti-shading capability prediction model; Step S33: importing the photovoltaic inverter joint test power data into the inverter anti-shading capability prediction model to perform anti-shading capability prediction, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on the photovoltaic inverter joint test power data according to the inverter light intensity collection data, and generating photovoltaic inverter dynamic shading adaptability data; Step S34: adjusting actual prediction parameters of the photovoltaic inverter anti-shading capability prediction data using the photovoltaic inverter dynamic shading adaptability data, thereby obtaining the photovoltaic inverter actual anti-shading capability data.

[0042] In an embodiment of the present invention, light intensity sensors are deployed on different photovoltaic modules of the inverter to collect light intensity data of the environment where the inverter is located in real time. The sensor should have high precision and a wide measurement range, and be able to measure light intensity changes in different time periods (such as daytime, cloudy days, etc.). Based on the previously defined shading test scenarios (such as complete unshading, single-point shading, linear shading, dynamic shading, etc.), light intensity data is collected under different shading conditions. The data should include light intensity changes under different shading conditions, such as shadow intensity, shading area, etc. The light intensity data of the inverter is recorded in real time to form a time series data set. The recorded content includes information such as time, light intensity, and light intensity fluctuation range. The data is preprocessed, such as noise removal and missing value filling, to ensure the integrity and accuracy of the data. Based on the light intensity collection data and the maximum power point tracking impact data, the anti-shading impact characteristics of the inverter are extracted. The main features include the power change rate, response speed, stability, etc. of the inverter under different shading scenarios. Statistical analysis methods (such as mean, variance, fluctuation amplitude, etc.) are used to calculate the output power change of the inverter under different light intensity conditions, as well as the impact on the maximum power point tracking during the shading process. By analyzing these feature data, the anti-shading feature data of the inverter is obtained, which helps to evaluate its anti-shading ability. The extracted anti-shading feature data of the inverter is divided to generate a training set and a test set. Usually, the training set accounts for 70%-80% of the data, and the test set accounts for 20%-30%. Ensure that the coverage of the training set and the test set is wide, covering the anti-shading feature data under different shading scenarios and different environmental conditions to ensure the generalization ability of the model training. Use the convolutional neural network (CNN) algorithm to train the model on the training set. CNN performs well in feature extraction and pattern recognition, and is suitable for processing complex time series data and nonlinear relationships. Set up a suitable network architecture, including convolutional layers, pooling layers, fully connected layers, etc., to extract anti-shading features and predict the anti-shading ability of the inverter. During the training process, the back propagation algorithm is used to optimize the model parameters and minimize the prediction error. Use cross-validation and early stopping strategies to avoid overfitting and ensure the generalization ability of the model. Use the model test set to evaluate the performance of the trained model and calculate the model's accuracy, precision, recall and other indicators. Optimize the model according to the test results, such as adjusting the network structure, learning rate and other parameters. According to the test results and optimization strategy, iteratively update the model to gradually improve the accuracy of the anti-shading ability prediction. During the optimization process, regularization methods (such as Dropout, L2 regularization, etc.) can be introduced to further improve the performance of the model. Import the joint test power data of the photovoltaic inverter into the trained inverter anti-shading ability prediction model to predict the anti-shading ability. The input data should include light intensity, shading type, inverter power output, etc. The model will predict the anti-shading ability of the inverter under different shading conditions based on these data.Through the model output, the inverter's anti-shading ability prediction data in different shading scenarios is obtained. The prediction results specifically include the percentage of power loss, the accuracy of maximum power point tracking, the response time, etc. According to the light intensity acquisition data of the inverter, the adaptability of the inverter under dynamic shading (such as cloud changes, building movement, etc.) is evaluated. The power output fluctuation and maximum power point tracking error of the inverter under dynamic shading are analyzed to generate dynamic shading adaptability data. The evaluation data will reflect the performance of the inverter in the face of dynamic shading in the actual environment, covering key indicators such as response speed and power fluctuation. The actual parameters of the anti-shading ability prediction model are adjusted using the dynamic shading adaptability data of the photovoltaic inverter. If the inverter shows a large fluctuation in shading adaptability in actual applications, the prediction effect can be optimized by adjusting the parameters of the model (such as adding more data features, improving the accuracy of the model, etc.). According to the adjusted model, the actual anti-shading ability data of the inverter is obtained. This data can reflect the real performance of the inverter under actual dynamic shading conditions and provide a basis for inverter performance optimization.

[0043] Preferably, performing dynamic shading adaptability evaluation on photovoltaic inverter joint test power data according to inverter light intensity collection data includes: Perform illumination change rate analysis on the light intensity acquisition data of the inverter to generate light intensity change amplitude data; perform inverter response monitoring on the photovoltaic inverter joint test power data based on the light intensity change amplitude data to generate inverter response monitoring data; According to the preliminary maximum power point data, the response time of the inverter response monitoring data is evaluated to generate dynamic shading response time evaluation data; the dynamic shading response time evaluation data is used to divide the inverter response monitoring data into light intensity change response power segments to generate dynamic shading response power segments; Perform power fluctuation recovery timing analysis on the dynamic shading response power segment to generate dynamic shading power recovery timing data; perform output power stability evaluation on the dynamic shading response power segment through the dynamic shading power recovery timing data to generate output power stability evaluation data; The dynamic shading response time evaluation data and the output power stability evaluation data are used to evaluate the dynamic shading adaptability of the photovoltaic inverter joint test power data, thereby generating the dynamic shading adaptability data of the photovoltaic inverter.

[0044] In the embodiment of the present invention, the light intensity data in the environment where the inverter is located is collected. The light intensity data should be obtained from the light intensity sensor, covering the dynamic changes in different time periods. The original light intensity data is denoised and smoothed to ensure the accuracy of the data. The rate of change of the light intensity data within a certain time interval is calculated to obtain the light intensity change amplitude data. The light intensity change rate reflects the degree of fluctuation of the lighting environment, and is usually calculated by the difference or derivative method. The light intensity change amplitude data is statistically analyzed to obtain the maximum value, minimum value, average value, standard deviation and other characteristic data of the change, and the light intensity change amplitude data is generated. These data will reflect the drastic fluctuation of the light intensity in different time periods, such as cloud cover, morning and evening light changes, etc. The light intensity change amplitude data is used to monitor the output power of the photovoltaic inverter. For each change in light intensity, the response time of the inverter, the output power change and other data are recorded to generate the inverter response monitoring data. The monitoring data includes the output power, response time, power fluctuation and the like of the inverter under different light intensity changes. These data will help analyze the dynamic response characteristics of the inverter under different shielding conditions, especially the influence of light intensity fluctuation on power output. Based on the preliminary maximum power point data of the inverter (i.e., the maximum output power that the inverter can achieve under different lighting conditions), evaluate the response speed of the inverter to changes in light intensity. Evaluate the response time of the inverter after the light intensity changes. At this time, the time series analysis method can be used to calculate the time required for the inverter to reach the new maximum power point from the start of the light intensity change. The evaluation results will include the mean and standard deviation of the response time, reflecting the speed at which the inverter adapts to changes in shading, and generate dynamic shading response time evaluation data. These evaluation data will help determine the responsiveness of the inverter when facing dynamic shading (such as shadow changes, cloud shading). Based on the dynamic shading response time evaluation data, the response monitoring data of the inverter is segmented, and the power segments are divided according to the amplitude of the light intensity change and the response time. Each segment represents the power output characteristics of the inverter under specific light change conditions. The segmented segments include: high light intensity segment: light intensity does not change much, and the output power is stable; medium light intensity segment: light intensity fluctuates greatly, and the power output fluctuates; low light intensity segment: insufficient light, output power decreases, and dynamic shading response power segments are generated. The segmented power segments can be used as input data for subsequent analysis to help identify the power response characteristics under different light intensity conditions. Perform time series analysis on the power fluctuations in the dynamic shading response power segment to identify the recovery process of power fluctuations. Time series models (such as autoregressive models, long short-term memory networks, etc.) can be used to analyze the trend of power recovery. Evaluate the speed and stability of power recovery under the influence of dynamic shading, and generate dynamic shading power recovery time series data. These data will reflect the power fluctuation recovery process of the inverter after dynamic shading, and evaluate the timeliness and stability of the recovery. Based on the dynamic shading power recovery time series data, evaluate the ability of the inverter's output power to remain stable during dynamic shading.Power stability analysis can be performed using indicators such as fluctuation amplitude, frequency, and root mean square error to generate output power stability evaluation data, which will help determine the long-term stability of the inverter under different shading environments, especially its performance in fast shading and recovery scenarios. Combined with the dynamic shading response time evaluation data and the output power stability evaluation data, the dynamic shading adaptability of the inverter is comprehensively evaluated. Evaluation indicators include: response time, power stability, power recovery speed, etc. Based on the above evaluation, the final PV inverter dynamic shading adaptability data is generated. This data will describe the adaptability of the inverter under different dynamic shading conditions, including its anti-shading capability, response time, and power stability.

[0045] In this specification, an intelligent testing device for a photovoltaic inverter is provided, which is used to perform the intelligent testing method for the photovoltaic inverter. The intelligent testing device for the photovoltaic inverter includes: The device deployment module is used to obtain the photovoltaic inverter structure data; perform shielding simulation device deployment on the photovoltaic inverter structure data to generate photovoltaic module shielding simulation device deployment data; perform key structure data collection on the photovoltaic inverter structure data through the photovoltaic module shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; The shading simulation module is used to simulate the shading test scenario for the deployment data of the PV module shading simulation device to obtain the PV inverter joint test power data; perform current-voltage change trend analysis on the standard PV inverter operation data based on the PV inverter joint test power data to generate current-voltage change trend data; perform maximum power point tracking impact analysis on the PV inverter joint test power data based on the current-voltage change trend data to generate inverter maximum power point tracking impact data; The anti-shading capability evaluation module is used to collect the inverter light intensity data of the inverter shading test scene data using the light intensity sensor to obtain the inverter light intensity collection data; to perform model training on the inverter maximum power point tracking impact data to generate the inverter anti-shading capability prediction model; to use the inverter anti-shading capability prediction model to predict the anti-shading capability of the photovoltaic inverter joint test power data to generate the photovoltaic inverter anti-shading capability prediction data; to perform dynamic shading adaptability evaluation on the photovoltaic inverter anti-shading capability prediction data through the inverter light intensity collection data to generate the actual anti-shading capability data of the photovoltaic inverter; The visualization module is used to visualize the actual anti-shading capability data of the photovoltaic inverter, thereby generating a photovoltaic inverter anti-shading performance report.

[0046] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the intelligent testing method for the photovoltaic inverter is implemented.

[0047] A storage medium stores a computer program, which implements the above-mentioned intelligent testing method for the photovoltaic inverter when executed by a processor.

[0048] The beneficial effect of the present invention is that by acquiring the structural data of the photovoltaic inverter, the inverter is simulated by simulating the shielding device. This step provides standard data for subsequent tests to ensure that the test and analysis under different shielding conditions are based on real and effective inverter structural data. By simulating the deployment data of the shielding device, the power data of the photovoltaic inverter under different shielding conditions can be generated, and the electrical characteristics of the inverter under these conditions can be analyzed in combination with the current-voltage change trend data, and the impact of the maximum power point tracking can be further evaluated. This process provides the necessary basic data for evaluating the maximum power point tracking performance of the inverter. The light intensity data of the inverter under different shielding test scenarios is collected by the light intensity sensor, and the anti-shielding ability of the inverter is evaluated by training the prediction model. The module uses real-time data to provide the system with a prediction of the ability of the inverter to adapt to different degrees of shielding, and can perform adaptability evaluation according to the actual dynamic light intensity changes. Finally, the actual anti-shielding ability data is displayed by data visualization means to generate a detailed anti-shielding performance report. The report can not only provide clear analysis results for the inverter performance, but also provide strong data support for future optimization design and improvement. Therefore, the present invention provides a performance detection process for photovoltaic inverters under shading conditions by introducing shading simulation, dynamic current-voltage analysis, anti-shading capability prediction and evaluation, and data visualization, while improving the intelligence level of the test and the reliability of the test results.

[0049] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0050] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent testing method for photovoltaic inverters, characterized in that: The following steps are involved: Step S1: Acquire photovoltaic inverter structure data; deploy a shielding simulation device on the photovoltaic inverter structure data to generate photovoltaic component shielding simulation device deployment data; collect key structure data on the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; Step S2: simulating the shading test scenario for the deployment data of the photovoltaic component shading simulation device to obtain the photovoltaic inverter joint test power data; performing a current-voltage change trend analysis on the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to generate the current-voltage change trend data; performing a maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data to generate the inverter maximum power point tracking impact data; Step S3: using a light intensity sensor to collect inverter light intensity data for the inverter shading test scene data to obtain inverter light intensity collection data; performing model training on the inverter maximum power point tracking impact data to generate an inverter anti-shading ability prediction model; The inverter anti-shading capability prediction model is used to predict the anti-shading capability of the photovoltaic inverter joint test power data, and the photovoltaic inverter anti-shading capability prediction data is generated; the photovoltaic inverter anti-shading capability prediction data is dynamically evaluated for its adaptability to shading by using the inverter light intensity collection data, and the actual anti-shading capability data of the photovoltaic inverter is generated; Step S4: Visualize the actual anti-shading capability data of the photovoltaic inverter to generate a photovoltaic inverter anti-shading performance report.

2. The intelligent testing method for photovoltaic inverter according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire photovoltaic inverter structure data; Step S12: screening the photovoltaic components of the inverter for the photovoltaic inverter structure data to obtain photovoltaic component structure screening data; deploying a shielding simulation device for the photovoltaic inverter according to the photovoltaic component structure screening data to generate photovoltaic component shielding simulation device deployment data; Step S13: screening the key operation structure of the photovoltaic inverter structure data through the photovoltaic component shielding simulation device deployment data to obtain the key operation structure data of the inverter; deploying operation sensors for the photovoltaic inverter according to the key operation structure data of the inverter, and collecting data from the deployed operation sensors to obtain initial photovoltaic inverter operation data; Step S14: performing data preprocessing on the initial photovoltaic inverter operation data to generate standard photovoltaic inverter operation data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

3. The intelligent testing method for photovoltaic inverter according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: simulating a shielding test scenario for the photovoltaic component shielding simulation device deployment data to generate inverter shielding test scenario data; using a preset load change threshold range to perform a joint power output on the photovoltaic inverter according to the inverter shielding test scenario data to obtain photovoltaic inverter joint test power data; Step S22: Calculating the power loss percentage of the standard photovoltaic inverter operation data according to the photovoltaic inverter joint test power data to obtain power loss variation amplitude data; Step S23: performing current-voltage change trend analysis on the standard photovoltaic inverter operation data through the power loss change amplitude data to generate current-voltage change trend data; Step S24: performing maximum power point tracking impact analysis on the photovoltaic inverter joint test power data based on the current-voltage change trend data and the power loss change amplitude data, and generating inverter maximum power point tracking impact data.

4. The intelligent testing method for photovoltaic inverter according to claim 3, characterized in that: Step S21 includes the following steps: Step S211: performing shading test scene setting on the deployment data of the photovoltaic component shading simulation device to obtain shading test scene setting data, wherein the shading test scene setting includes a completely unshaded scene setting, a single-point shading scene setting, a linear shading scene setting, and a dynamic shading scene setting; Step S212: using the shading test scene setting data to simulate the shading process of the photovoltaic inverter to obtain shading process simulation data; recording the output power change of the photovoltaic inverter according to the shading process simulation data to obtain first output power change data; Step S213: Perform a dynamic change power test on the first output power change data based on a preset load change threshold range to generate second output power change data; perform non-overlapping data screening on the first output power change data and the second output power change data to obtain photovoltaic inverter joint test power data.

5. The intelligent testing method for photovoltaic inverter according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: Performing photovoltaic inverter relationship modeling on the current-voltage change trend data and the power loss change amplitude data, thereby obtaining a relationship modeling curve; performing preliminary positioning of the inverter maximum power point based on the relationship modeling curve, thereby obtaining preliminary maximum power point data; Step S242: performing maximum power point tracking response analysis according to the preliminary maximum power point data, thereby obtaining tracking response performance data; performing curve conversion on the tracking response performance data, and generating a maximum power point tracking response performance curve; Step S243: Calculate the mean curvature of the maximum power point tracking response performance curve to obtain maximum power point tracking stability data; perform power fluctuation amplitude analysis on the relationship modeling curve based on the tracking stability data to obtain inverter maximum power point tracking impact data.

6. The intelligent testing method for photovoltaic inverter according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: using a light intensity sensor to collect inverter light intensity data for inverter shielding test scene data to obtain inverter light intensity collection data; extracting inverter anti-shielding influence features for inverter maximum power point tracking influence data to obtain inverter anti-shielding feature data; Step S32: dividing the anti-shading feature data of the inverter into a data set to generate a model training set and a model test set; training the model training set using a convolutional neural network algorithm to generate an anti-shading capability prediction pre-model; optimizing and iterating the anti-shading capability prediction pre-model using the model test set, thereby generating an inverter anti-shading capability prediction model; Step S33: importing the photovoltaic inverter joint test power data into the inverter anti-shading capability prediction model to perform anti-shading capability prediction, and generating photovoltaic inverter anti-shading capability prediction data; performing dynamic shading adaptability evaluation on the photovoltaic inverter joint test power data according to the inverter light intensity collection data, and generating photovoltaic inverter dynamic shading adaptability data; Step S34: adjusting actual prediction parameters of the photovoltaic inverter anti-shading capability prediction data using the photovoltaic inverter dynamic shading adaptability data, thereby obtaining the photovoltaic inverter actual anti-shading capability data.

7. The intelligent testing method for photovoltaic inverter according to claim 6, characterized in that: The dynamic shading adaptability evaluation of the photovoltaic inverter joint test power data based on the inverter light intensity collection data includes: Perform illumination change rate analysis on the light intensity acquisition data of the inverter to generate light intensity change amplitude data; perform inverter response monitoring on the photovoltaic inverter joint test power data based on the light intensity change amplitude data to generate inverter response monitoring data; According to the preliminary maximum power point data, the response time of the inverter response monitoring data is evaluated to generate dynamic shading response time evaluation data; the inverter response monitoring data is segmented into light intensity change response power segments using the dynamic shading response time evaluation data to generate dynamic shading response power segments; Perform power fluctuation recovery timing analysis on the dynamic shading response power segment to generate dynamic shading power recovery timing data; perform output power stability evaluation on the dynamic shading response power segment through the dynamic shading power recovery timing data to generate output power stability evaluation data; The dynamic shading response time evaluation data and the output power stability evaluation data are used to evaluate the dynamic shading adaptability of the photovoltaic inverter joint test power data, thereby generating the dynamic shading adaptability data of the photovoltaic inverter.

8. An intelligent testing device for photovoltaic inverters, characterized in that: For executing the intelligent testing method of the photovoltaic inverter according to claim 1, the intelligent testing device of the photovoltaic inverter comprises: The device deployment module is used to obtain the photovoltaic inverter structure data; perform shielding simulation device deployment on the photovoltaic inverter structure data to generate photovoltaic module shielding simulation device deployment data; perform key structure data collection on the photovoltaic inverter structure data through the photovoltaic module shielding simulation device deployment data to obtain standard photovoltaic inverter operation data; The shading simulation module is used to simulate the shading test scenario for the deployment data of the PV module shading simulation device to obtain the PV inverter joint test power data; perform current-voltage change trend analysis on the standard PV inverter operation data based on the PV inverter joint test power data to generate current-voltage change trend data; perform maximum power point tracking impact analysis on the PV inverter joint test power data based on the current-voltage change trend data to generate inverter maximum power point tracking impact data; The anti-shading capability evaluation module is used to collect the inverter light intensity data of the inverter shading test scene data using the light intensity sensor to obtain the inverter light intensity collection data; to perform model training on the inverter maximum power point tracking impact data to generate the inverter anti-shading capability prediction model; to use the inverter anti-shading capability prediction model to predict the anti-shading capability of the photovoltaic inverter joint test power data to generate the photovoltaic inverter anti-shading capability prediction data; to perform dynamic shading adaptability evaluation on the photovoltaic inverter anti-shading capability prediction data through the inverter light intensity collection data to generate the actual anti-shading capability data of the photovoltaic inverter; The visualization module is used to visualize the actual anti-shading capability data of the photovoltaic inverter, thereby generating a photovoltaic inverter anti-shading performance report.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images