Photovoltaic power generation fault detection method and system

Abstract

The invention discloses a photovoltaic power generation fault detection method and system, and the method comprises the steps: obtaining the historical operation data of a photovoltaic power generation system, carrying out the analysis of the historical operation data, and determining the operation characteristic parameters which affect the performance of the photovoltaic power generation system; constructing a performance prediction model of the photovoltaic power generation system based on the operation characteristic parameters and a neural network model, and obtaining performance prediction data according to the prediction of the performance prediction model; acquiring real-time performance data, and comparing and analyzing the real-time performance data with the performance prediction data to determine data difference characteristics; evaluating and calculating the performance change condition of the photovoltaic power generation system based on the data difference characteristics to obtain a performance change evaluation value; and judging whether the photovoltaic power generation system fails or not according to the performance change evaluation value. According to the invention, the real-time performance data and the performance prediction data are compared and analyzed, so that the change deviation of the operation state of the system can be found in time, and whether the photovoltaic power generation system breaks down can be accurately judged by analyzing the change deviation of the performance of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a photovoltaic power generation fault detection method and system. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power generation, as one of the important representatives of clean energy, has been widely used around the world. However, photovoltaic power generation systems will inevitably face various faults and problems in long-term operation, which may lead to reduced power generation efficiency, reduced system safety and increased operating costs. Therefore, developing an efficient and reliable photovoltaic power generation fault detection method is crucial to ensure the normal operation and continuous power generation of photovoltaic power generation systems.

[0003] However, traditional photovoltaic power generation fault detection methods mainly rely on manual inspections and regular maintenance, which have problems such as low detection efficiency, high cost, and inability to monitor in real time. With the development of artificial intelligence and machine learning technology, data-driven photovoltaic power generation fault detection methods have gradually become a research hotspot. By using historical operation data, real-time monitoring data, and advanced data analysis technology, photovoltaic power generation system faults can be diagnosed and monitored in real time and accurately. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a photovoltaic power generation fault detection method and system, comprising:

[0005] Obtain historical operating data of the photovoltaic power generation system, analyze the historical operating data, and determine the operating characteristic parameters in the historical operating data that affect the performance of the photovoltaic power generation system;

[0006] A performance prediction model of the photovoltaic power generation system is constructed based on the operating characteristic parameters and the neural network model, and prediction is performed according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system;

[0007] Obtain the real-time performance data of the photovoltaic power generation system, and compare and analyze the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine the data difference characteristics;

[0008] Evaluate and calculate the performance change of the photovoltaic power generation system based on the data difference characteristics, and obtain the performance change evaluation value of the photovoltaic power generation system;

[0009] Whether a photovoltaic power generation system fails is determined based on the performance change evaluation value of the photovoltaic power generation system.

[0010] Furthermore, the acquisition of historical operation data of the photovoltaic power generation system and analysis of the historical operation data to determine the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system include:

[0011] Acquire historical operation data and historical performance data of the photovoltaic power generation system, and divide the historical operation data into a plurality of operation parameter data groups according to parameter types, and divide the historical performance data into a plurality of performance parameter data groups;

[0012] Analyze the correlation between each operating parameter data group and the performance parameter data group, and use the operating parameter data group with the highest correlation with the performance parameter data group as a candidate operating parameter data group corresponding to the performance parameter data group;

[0013] For each candidate operating parameter data, screening the performance parameter data of the photovoltaic power generation system when other operating parameter data are the same, and determining the change amount of the performance parameter data;

[0014] The operating parameters corresponding to the candidate operating parameter data group whose variation is greater than the preset value are selected and determined as the operating characteristic parameters that affect the performance of the photovoltaic power generation system in the historical operating data.

[0015] Furthermore, the performance prediction model of the photovoltaic power generation system is constructed based on the operating characteristic parameters and the neural network model, and prediction is performed according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system, including:

[0016] Build a data set based on the operating characteristic parameters and the corresponding historical performance data, and input the data set into a preset neural network model to build an initial performance prediction model;

[0017] Divide the data set into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial performance prediction model;

[0018] The initial performance prediction model is trained and tested until the initial performance prediction model meets a preset convergence condition, thereby obtaining a performance prediction model of the photovoltaic power generation system;

[0019] The real-time operation data of the photovoltaic power generation system is obtained, and the real-time operation data is input into the performance prediction model. The performance prediction model performs prediction to obtain the performance prediction data of the photovoltaic power generation system.

[0020] Furthermore, the real-time performance data of the photovoltaic power generation system is obtained, and the real-time performance data of the photovoltaic power generation system is compared and analyzed with the performance prediction data to determine the data difference characteristics, including:

[0021] Acquire real-time performance data and performance prediction data of the photovoltaic power generation system, and divide the real-time performance data into a plurality of real-time performance parameter data groups, and divide the performance prediction data into a plurality of performance parameter prediction data groups;

[0022] According to the parameter type, the real-time performance parameter data group is matched with the performance parameter prediction data group one by one to obtain several groups of corresponding performance parameter groups;

[0023] Calculate the average values ​​of the real-time performance parameter data group and the performance parameter prediction data group in each performance parameter group respectively, and perform a difference calculation between the average value of the real-time performance parameter data group and the average value of the performance parameter prediction data group to obtain the average value difference of each performance parameter group;

[0024] Performing a difference calculation between the real-time performance parameter data set and the performance parameter prediction data set in each performance parameter group to obtain performance parameter difference data;

[0025] The performance parameter difference data is plotted into a time series curve graph to obtain a performance parameter difference curve graph, and a first curve segment greater than or equal to zero and a second curve segment less than zero are determined from the performance parameter difference curve graph;

[0026] The number, time length and average value of the first curve segments and the second curve segments are determined, and the average value difference of each performance parameter group and the number, time length and average value of the first curve segments and the second curve segments are used as data difference features.

[0027] Furthermore, the performance change of the photovoltaic power generation system is evaluated and calculated based on the data difference characteristics to obtain the performance change evaluation value of the photovoltaic power generation system, including:

[0028] Obtain the average value difference of each performance parameter group, and evaluate the average value difference to obtain the change evaluation value of each performance parameter group;

[0029] Obtaining the number, time length and average value of the first curve segments and the second curve segments, and calculating the evaluation coefficient corresponding to each performance parameter group based on the number, time length and average value of the first curve segments and the second curve segments;

[0030] The performance change evaluation value of the photovoltaic power generation system is determined based on the change evaluation value and evaluation coefficient of each performance parameter group. The calculation formula of the performance change evaluation value of the photovoltaic power generation system is:

[0031]

[0032] Wherein, S is the performance change evaluation value of the photovoltaic power generation system, Di is the evaluation coefficient of the i-th performance parameter group, Pi is the change evaluation value of the i-th performance parameter group, and n is the number of performance parameter groups.

[0033] Furthermore, the calculation formula of the evaluation coefficient of the performance parameter group is:

[0034]

[0035] Among them, Di is the evaluation coefficient of the i-th performance parameter group, α is the weight coefficient of the first curve segment, Kx is the average value of the x-th first curve segment, Ex is the time length of the x-th first curve segment, c is the number of first curve segments, β is the weight coefficient of the second curve segment, Jy is the average value of the y-th second curve segment, Fy is the time length of the y-th second curve segment, and d is the number of second curve segments.

[0036] Further, judging whether a photovoltaic power generation system fails according to the performance change evaluation value of the photovoltaic power generation system includes:

[0037] Presetting a preset performance change evaluation value of the photovoltaic power generation system, and comparing the performance change evaluation value of the photovoltaic power generation system with the preset performance change evaluation value;

[0038] If the performance change evaluation value of the photovoltaic power generation system is greater than or equal to the preset performance change evaluation value, it is determined that a failure has occurred in the photovoltaic power generation system;

[0039] If the performance change evaluation value of the photovoltaic power generation system is less than the preset performance change evaluation value, it is determined that no failure has occurred in the photovoltaic power generation system.

[0040] The present invention also provides a photovoltaic power generation fault detection system, comprising:

[0041] A determination module is used to obtain historical operation data of the photovoltaic power generation system, analyze the historical operation data, and determine the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system;

[0042] A prediction module is used to build a performance prediction model of the photovoltaic power generation system based on the operating characteristic parameters and the neural network model, and to perform predictions according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system;

[0043] An analysis module is used to obtain the real-time performance data of the photovoltaic power generation system, and compare and analyze the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine the data difference characteristics;

[0044] A calculation module is used to evaluate and calculate the performance change of the photovoltaic power generation system based on the data difference characteristics to obtain the performance change evaluation value of the photovoltaic power generation system;

[0045] The judgment module is used to judge whether a failure occurs in the photovoltaic power generation system according to the performance change evaluation value of the photovoltaic power generation system.

[0046] Compared with the prior art, the photovoltaic power generation fault detection method and system according to the embodiment of the present invention have the following beneficial effects:

[0047] The present invention can determine the key influencing factors and operating characteristic parameters of the photovoltaic power generation system performance by analyzing the historical operating data, and help understand the laws and characteristics of the system operation;

[0048] The present invention uses a neural network model to predict the performance of a photovoltaic power generation system. By learning the pattern of historical data, it predicts future performance and provides a method for predicting performance for system operation.

[0049] The present invention compares and analyzes real-time performance data with performance prediction data, which can find deviations and abnormalities in actual work and help to find system problems in a timely manner;

[0050] The present invention can evaluate and calculate the changes in system performance by comparing and analyzing the data difference characteristics, and help understand the changes in the system operation status;

[0051] The present invention can accurately determine whether a photovoltaic power generation system has a fault or an abnormality based on the performance change evaluation value in combination with a preset threshold value or rule, thereby helping to promptly discover and solve the problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 1 is a schematic diagram of the structure of the photovoltaic power generation fault detection method according to an embodiment of the present invention;

[0053] Figure 2 It is a schematic diagram of the composition of a photovoltaic power generation fault detection system in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0055] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0056] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying a relative degree of importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0057] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technical personnel in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] like Figure 1 As shown, in an embodiment of the present application, a photovoltaic power generation fault detection method is provided, including: S100: acquiring historical operation data of a photovoltaic power generation system, analyzing the historical operation data, and determining operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system; S200: constructing a performance prediction model of the photovoltaic power generation system based on the operation characteristic parameters and a neural network model, and performing prediction according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system; S300: acquiring real-time performance data of the photovoltaic power generation system, and comparing and analyzing the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine data difference characteristics; S400: evaluating and calculating the performance change of the photovoltaic power generation system based on the data difference characteristics to obtain a performance change evaluation value of the photovoltaic power generation system; S500: judging whether a photovoltaic power generation system has a fault according to the performance change evaluation value of the photovoltaic power generation system.

[0059] Furthermore, the present invention can determine the key influencing factors and operating characteristic parameters of the photovoltaic power generation system performance through analysis of historical operating data, and help understand the laws and characteristics of the system operation; the present invention can use a neural network model to predict the performance of the photovoltaic power generation system, and predict future performance by learning the pattern of historical data, thereby providing a method for predicting performance for system operation; the present invention compares and analyzes real-time performance data with performance prediction data to discover deviations and abnormalities in actual work, which helps to discover system problems in a timely manner; the present invention can evaluate and calculate changes in system performance through data difference characteristics obtained through comparative analysis, and help understand changes in the system operating status; the present invention can accurately determine whether a photovoltaic power generation system has a fault or abnormality based on the performance change evaluation value combined with pre-set thresholds or rules, and help to discover and solve problems in a timely manner.

[0060] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, wherein historical operation data of a photovoltaic power generation system is obtained, and the historical operation data is analyzed to determine the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system, including: obtaining the historical operation data and historical performance data of the photovoltaic power generation system, and dividing the historical operation data into a plurality of operation parameter data groups according to parameter type, and dividing the historical performance data into a plurality of performance parameter data groups; analyzing the correlation between each operation parameter data group and the performance parameter data group, and taking the operation parameter data group with the highest correlation with the performance parameter data group as a candidate operation parameter data group corresponding to the performance parameter data group; for each candidate operation parameter data, screening the performance parameter data of the photovoltaic power generation system when other operation parameter data are the same, and determining the change amount of the performance parameter data; selecting the operation parameter corresponding to the candidate operation parameter data group whose change amount is greater than a preset value, and determining it as the operation characteristic parameter in the historical operation data that affects the performance of the photovoltaic power generation system.

[0061] Specifically, historical operation data and historical performance data are obtained from the photovoltaic power generation system, and the historical operation data are divided into several operation parameter data groups according to parameter type, and the historical performance data are divided into several performance parameter data groups; the correlation between each operation parameter data group and the performance parameter data group is analyzed, and a statistical correlation analysis method (correlation coefficient analysis) is used to measure the degree of linear correlation between them; the operation parameter data group with the highest correlation with the performance parameter data group is used as the candidate operation parameter data group corresponding to the performance parameter data group; for each candidate operation parameter data group, the performance parameter data of the photovoltaic power generation system when other operation parameter data are the same is screened, and the change amount of the performance parameter data is determined; the operation parameters corresponding to the candidate operation parameter data group whose change amount is greater than the preset value are selected, and determined as the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system.

[0062] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, wherein a performance prediction model of a photovoltaic power generation system is constructed based on operating characteristic parameters and a neural network model, and prediction is performed according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system, including: constructing a data set based on operating characteristic parameters and corresponding historical performance data, and inputting the data set into a preset neural network model to construct an initial performance prediction model; dividing the data set into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial performance prediction model; training and testing the initial performance prediction model until the initial performance prediction model meets a preset convergence condition to obtain a performance prediction model of the photovoltaic power generation system; acquiring real-time operating data of the photovoltaic power generation system, and inputting the real-time operating data into the performance prediction model, and performing prediction by the performance prediction model to obtain performance prediction data of the photovoltaic power generation system.

[0063] Specifically, a data set is constructed based on the operating characteristic parameters and the corresponding historical performance data. This data set will include the historical operating characteristic parameters and the corresponding performance data, which are used to train and verify the performance prediction model; the data set is input into the preset neural network model to construct the initial performance prediction model; the data set is divided into a training set and a test set according to a certain ratio to train and verify the model, and the training set and the test set are input into the initial performance prediction model to train and test the model. During the training process, the model predicts future performance by learning the pattern of historical data, and the testing process is used to verify the generalization ability and accuracy of the model; the initial performance prediction model is trained and tested until the model meets the preset convergence conditions, and a performance prediction model of the photovoltaic power generation system is obtained. This model will be able to predict the performance of the photovoltaic power generation system in the future based on the historical operating data; the real-time operating data of the photovoltaic power generation system is obtained, and the real-time operating data is input into the performance prediction model, and the model is predicted to obtain the performance prediction data of the photovoltaic power generation system. This step can more accurately predict the performance of the photovoltaic power generation system by constructing a neural network model, which helps to improve the reliability of the system, reduce operating costs and optimize system operation management.

[0064] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, which obtains real-time performance data of a photovoltaic power generation system, and compares and analyzes the real-time performance data of the photovoltaic power generation system with performance prediction data to determine data difference characteristics, including: obtaining real-time performance data and performance prediction data of the photovoltaic power generation system, and dividing the real-time performance data into several real-time performance parameter data groups, and dividing the performance prediction data into several performance parameter prediction data groups; matching the real-time performance parameter data groups with the performance parameter prediction data groups one by one according to parameter types to obtain several groups of corresponding performance parameter groups; and calculating the average values ​​of the real-time performance parameter data groups and the performance parameter prediction data groups in each group of performance parameter groups respectively. , and perform a difference calculation between the average value of the real-time performance parameter data group and the average value of the performance parameter prediction data group to obtain the average value difference of each performance parameter group; perform a difference calculation between the real-time performance parameter data group and the performance parameter prediction data group in each performance parameter group to obtain performance parameter difference data; plot the performance parameter difference data into a time series curve chart to obtain a performance parameter difference curve chart, and determine a first curve segment greater than or equal to zero and a second curve segment less than zero from the performance parameter difference curve chart; determine the number, time length and average value of the first curve segment and the second curve segment, and use the average value difference of each performance parameter group and the number, time length and average value of the first curve segment and the second curve segment as data difference features.

[0065] Specifically, the real-time performance data and the performance prediction data are divided into several data groups according to the parameter type to ensure that the real-time performance data and the prediction data correspond on the same time scale; the real-time performance parameter data group is matched with the performance parameter prediction data group one by one according to the parameter type to obtain several groups of corresponding performance parameter groups; the average values ​​of the real-time performance parameter data group and the performance parameter prediction data group in each performance parameter group are calculated respectively, and the average value of the real-time performance parameter data group is subtracted from the average value of the performance parameter prediction data group to obtain the average value difference of each performance parameter group; the real-time performance parameter data group in each performance parameter group is subtracted from the performance parameter prediction data group to obtain performance parameter difference data; the performance parameter difference data is plotted into a time series curve graph to obtain a performance parameter difference curve graph, and a first curve segment greater than or equal to zero and a second curve segment less than zero are determined therefrom; the number, time length and average value of the first curve segment and the second curve segment are determined, and the average value difference of each performance parameter group and the number, time length and average value of the first curve segment and the second curve segment are used as data difference features. By comparing the real-time performance data with the performance prediction data, this step can understand in real time whether the performance of the photovoltaic power generation system meets expectations, discover abnormal situations in time, and based on the analysis of the performance parameter difference curve, determine the number, time length and average value of the first curve segment and the second curve segment, thereby realizing the detection and early warning of system performance abnormalities, and providing an important reference for system maintenance and troubleshooting. In general, this step can provide strong technical support for the real-time performance analysis of photovoltaic power generation systems, discover potential problems in time, and extract data difference features, providing an important reference for system operation management and maintenance.

[0066] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, wherein the performance change of the photovoltaic power generation system is evaluated and calculated based on the data difference characteristics to obtain the performance change evaluation value of the photovoltaic power generation system, including: obtaining the average value difference of each group of performance parameter groups, and evaluating and valuing the average value difference to obtain the change evaluation value of each group of performance parameter groups; obtaining the number, time length and average value of the first curve segment and the second curve segment, and calculating the evaluation coefficient corresponding to each group of performance parameter groups based on the number, time length and average value of the first curve segment and the second curve segment; determining the performance change evaluation value of the photovoltaic power generation system based on the change evaluation value and evaluation coefficient of each group of performance parameter groups, and the calculation formula of the performance change evaluation value of the photovoltaic power generation system is:

[0067]

[0068] Wherein, S is the performance change evaluation value of the photovoltaic power generation system, Di is the evaluation coefficient of the i-th performance parameter group, Pi is the change evaluation value of the i-th performance parameter group, and n is the number of performance parameter groups.

[0069] Specifically, the difference in the mean values ​​of each group of performance parameter groups is evaluated and the change evaluation value of each group of performance parameter groups is obtained, and the change evaluation value can determine the actual change range of the performance parameter; the number, time length and average value of the first curve segment and the second curve segment are obtained, and the evaluation coefficient corresponding to each group of performance parameter groups is calculated based on these data. The evaluation coefficient can be calculated based on the characteristics of the first curve segment and the second curve segment, such as the number, time length and average value. These coefficients can reflect the degree and duration of performance changes in different stages of the system; based on the change evaluation value and evaluation coefficient of each group of performance parameter groups, the performance change evaluation value of the photovoltaic power generation system can be determined. This evaluation value will comprehensively consider the evaluation value of the mean value difference and the evaluation coefficient of the curve segment characteristics, so as to provide a comprehensive performance change evaluation. This step can quantify the performance changes of the photovoltaic power generation system by evaluating the mean value difference and curve segment characteristics, so that the system manager can more clearly understand the changes in system performance, and comprehensively consider the evaluation coefficients of the mean value difference and curve segment characteristics to obtain a comprehensive performance change evaluation value, which helps the system manager to more comprehensively evaluate the changes in system performance, provide important references for the system manager's decision-making, and help them adjust the operation strategy, perform maintenance and troubleshooting in a timely manner, thereby improving the reliability and efficiency of the system. In general, this step can provide a quantitative evaluation of the performance changes of the photovoltaic power generation system, help system managers better understand the changes in system performance, and provide important support for operation management and maintenance decisions.

[0070] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, and the calculation formula of the evaluation coefficient of the performance parameter group is:

[0071]

[0072] Among them, Di is the evaluation coefficient of the i-th performance parameter group, α is the weight coefficient of the first curve segment, Kx is the average value of the x-th first curve segment, Ex is the time length of the x-th first curve segment, c is the number of first curve segments, β is the weight coefficient of the second curve segment, Jy is the average value of the y-th second curve segment, Fy is the time length of the y-th second curve segment, and d is the number of second curve segments.

[0073] In an embodiment of the present application, a photovoltaic power generation fault detection method is provided, wherein judging whether a photovoltaic power generation system has a fault based on a performance change evaluation value of the photovoltaic power generation system comprises: presetting a preset performance change evaluation value of the photovoltaic power generation system, and comparing the performance change evaluation value of the photovoltaic power generation system with the preset performance change evaluation value; if the performance change evaluation value of the photovoltaic power generation system is greater than or equal to the preset performance change evaluation value, judging that a fault has occurred in the photovoltaic power generation system; and if the performance change evaluation value of the photovoltaic power generation system is less than the preset performance change evaluation value, judging that no fault has occurred in the photovoltaic power generation system.

[0074] Specifically, a preset performance change evaluation value is set according to the characteristics and operation of the system, and this value is used as a standard for performance change; the actual performance change evaluation value of the photovoltaic power generation system is compared with the preset performance change evaluation value. If the actual performance change evaluation value is greater than or equal to the preset performance change evaluation value, it is judged that the photovoltaic power generation system has a fault; if the actual performance change evaluation value is less than the preset performance change evaluation value, it is judged that the photovoltaic power generation system has not a fault. This step can realize automatic fault diagnosis and early warning of the photovoltaic power generation system by comparing the actual performance change evaluation value with the preset performance change evaluation value. The system manager can use this mechanism to timely know the operating status of the system and avoid potential faults from causing greater impact on the system; using the preset performance change evaluation value for comparison can reduce the reliance on human subjective judgment and improve the objectivity and consistency of system fault judgment; the automated fault judgment and early warning mechanism can improve the efficiency of fault handling, help system managers respond more quickly, and reduce the impact of faults on system operation. In general, this step can realize automatic fault diagnosis and early warning of the photovoltaic power generation system by comparing the actual performance change evaluation value with the preset performance change evaluation value, and improve the efficiency and accuracy of system management.

[0075] like Figure 2 As shown, in an embodiment of the present application, a photovoltaic power generation fault detection system is provided, including: a determination module, which is used to obtain historical operation data of a photovoltaic power generation system, and analyze the historical operation data to determine the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system; a prediction module, which is used to construct a performance prediction model of the photovoltaic power generation system based on the operation characteristic parameters and a neural network model, and perform predictions according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system; an analysis module, which is used to obtain real-time performance data of the photovoltaic power generation system, and compare and analyze the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine data difference characteristics; a calculation module, which is used to evaluate and calculate the performance change of the photovoltaic power generation system based on the data difference characteristics to obtain a performance change evaluation value of the photovoltaic power generation system; and a judgment module, which is used to judge whether a fault occurs in the photovoltaic power generation system according to the performance change evaluation value of the photovoltaic power generation system.

[0076] In summary, the embodiments of the present invention provide a photovoltaic power generation fault detection method and system, which include: obtaining historical operation data of the photovoltaic power generation system, analyzing it, and determining the operation characteristic parameters that affect the performance of the photovoltaic power generation system; constructing a performance prediction model of the photovoltaic power generation system based on the operation characteristic parameters and the neural network model, and obtaining performance prediction data based on its prediction; obtaining real-time performance data, and comparing and analyzing it with the performance prediction data to determine data difference characteristics; evaluating and calculating the performance change of the photovoltaic power generation system based on the data difference characteristics to obtain a performance change evaluation value; judging whether the photovoltaic power generation system has a fault according to the performance change evaluation value. The present invention can timely discover the change deviation of the system operation state by comparing and analyzing the real-time performance data with the performance prediction data, and can accurately judge whether the photovoltaic power generation system has a fault by analyzing the change deviation of the system performance.

[0077] Finally, it should be noted that: Obviously, a person skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0078] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0079] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0080] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is easy for a person skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, a person skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A photovoltaic power generation fault detection method, characterized in that: include: Obtain historical operating data of the photovoltaic power generation system, analyze the historical operating data, and determine the operating characteristic parameters in the historical operating data that affect the performance of the photovoltaic power generation system; A performance prediction model of the photovoltaic power generation system is constructed based on the operating characteristic parameters and the neural network model, and prediction is performed according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system; Obtain the real-time performance data of the photovoltaic power generation system, and compare and analyze the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine the data difference characteristics; Evaluate and calculate the performance change of the photovoltaic power generation system based on the data difference characteristics, and obtain the performance change evaluation value of the photovoltaic power generation system; Whether a photovoltaic power generation system fails is determined based on the performance change evaluation value of the photovoltaic power generation system.

2. A photovoltaic power generation fault detection method according to claim 1, characterized in that: The obtaining of historical operation data of the photovoltaic power generation system, analyzing the historical operation data, and determining the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system include: Acquire historical operation data and historical performance data of the photovoltaic power generation system, and divide the historical operation data into a plurality of operation parameter data groups according to parameter types, and divide the historical performance data into a plurality of performance parameter data groups; Analyze the correlation between each operating parameter data group and the performance parameter data group, and use the operating parameter data group with the highest correlation with the performance parameter data group as a candidate operating parameter data group corresponding to the performance parameter data group; For each candidate operating parameter data, screening the performance parameter data of the photovoltaic power generation system when other operating parameter data are the same, and determining the change amount of the performance parameter data; The operating parameters corresponding to the candidate operating parameter data group whose variation is greater than the preset value are selected and determined as the operating characteristic parameters that affect the performance of the photovoltaic power generation system in the historical operating data.

3. A photovoltaic power generation fault detection method according to claim 2, characterized in that: The performance prediction model of the photovoltaic power generation system is constructed based on the operating characteristic parameters and the neural network model, and prediction is performed according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system, including: Build a data set based on the operating characteristic parameters and the corresponding historical performance data, and input the data set into a preset neural network model to build an initial performance prediction model; Divide the data set into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial performance prediction model; The initial performance prediction model is trained and tested until the initial performance prediction model meets a preset convergence condition, thereby obtaining a performance prediction model of the photovoltaic power generation system; The real-time operation data of the photovoltaic power generation system is obtained, and the real-time operation data is input into the performance prediction model. The performance prediction model performs prediction to obtain the performance prediction data of the photovoltaic power generation system.

4. A photovoltaic power generation fault detection method according to claim 3, characterized in that: The real-time performance data of the photovoltaic power generation system is obtained, and the real-time performance data of the photovoltaic power generation system is compared and analyzed with the performance prediction data to determine the data difference characteristics, including: Acquire real-time performance data and performance prediction data of the photovoltaic power generation system, and divide the real-time performance data into a plurality of real-time performance parameter data groups, and divide the performance prediction data into a plurality of performance parameter prediction data groups; According to the parameter type, the real-time performance parameter data group is matched with the performance parameter prediction data group one by one to obtain several groups of corresponding performance parameter groups; Calculate the average values ​​of the real-time performance parameter data group and the performance parameter prediction data group in each performance parameter group respectively, and perform a difference calculation between the average value of the real-time performance parameter data group and the average value of the performance parameter prediction data group to obtain the average value difference of each performance parameter group; Performing a difference calculation between the real-time performance parameter data set and the performance parameter prediction data set in each performance parameter group to obtain performance parameter difference data; The performance parameter difference data is plotted into a time series curve graph to obtain a performance parameter difference curve graph, and a first curve segment greater than or equal to zero and a second curve segment less than zero are determined from the performance parameter difference curve graph; The number, time length and average value of the first curve segments and the second curve segments are determined, and the average value difference of each performance parameter group and the number, time length and average value of the first curve segments and the second curve segments are used as data difference features.

5. A photovoltaic power generation fault detection method according to claim 4, characterized in that: The performance change of the photovoltaic power generation system is evaluated and calculated based on the data difference characteristics to obtain the performance change evaluation value of the photovoltaic power generation system, including: Obtain the average value difference of each performance parameter group, and evaluate the average value difference to obtain the change evaluation value of each performance parameter group; Obtaining the number, time length and average value of the first curve segments and the second curve segments, and calculating the evaluation coefficient corresponding to each performance parameter group based on the number, time length and average value of the first curve segments and the second curve segments; The performance change evaluation value of the photovoltaic power generation system is determined based on the change evaluation value and evaluation coefficient of each performance parameter group. The calculation formula of the performance change evaluation value of the photovoltaic power generation system is: Wherein, S is the performance change evaluation value of the photovoltaic power generation system, Di is the evaluation coefficient of the i-th performance parameter group, Pi is the change evaluation value of the i-th performance parameter group, and n is the number of performance parameter groups.

6. A photovoltaic power generation fault detection method according to claim 5, characterized in that: The calculation formula of the evaluation coefficient of the performance parameter group is: Among them, Di is the evaluation coefficient of the i-th performance parameter group, α is the weight coefficient of the first curve segment, Kx is the average value of the x-th first curve segment, Ex is the time length of the x-th first curve segment, c is the number of first curve segments, β is the weight coefficient of the second curve segment, Jy is the average value of the y-th second curve segment, Fy is the time length of the y-th second curve segment, and d is the number of second curve segments.

7. A photovoltaic power generation fault detection method according to claim 5, characterized in that: The determining whether a photovoltaic power generation system fails according to the performance change evaluation value of the photovoltaic power generation system includes: Presetting a preset performance change evaluation value of the photovoltaic power generation system, and comparing the performance change evaluation value of the photovoltaic power generation system with the preset performance change evaluation value; If the performance change evaluation value of the photovoltaic power generation system is greater than or equal to the preset performance change evaluation value, it is determined that a failure has occurred in the photovoltaic power generation system; If the performance change evaluation value of the photovoltaic power generation system is less than the preset performance change evaluation value, it is determined that no failure has occurred in the photovoltaic power generation system.

8. A photovoltaic power generation fault detection system, characterized in that: include: A determination module is used to obtain historical operation data of the photovoltaic power generation system, analyze the historical operation data, and determine the operation characteristic parameters in the historical operation data that affect the performance of the photovoltaic power generation system; A prediction module is used to build a performance prediction model of the photovoltaic power generation system based on the operating characteristic parameters and the neural network model, and to perform predictions according to the performance prediction model to obtain performance prediction data of the photovoltaic power generation system; An analysis module is used to obtain the real-time performance data of the photovoltaic power generation system, and compare and analyze the real-time performance data of the photovoltaic power generation system with the performance prediction data to determine the data difference characteristics; A calculation module is used to evaluate and calculate the performance change of the photovoltaic power generation system based on the data difference characteristics to obtain the performance change evaluation value of the photovoltaic power generation system; The judgment module is used to judge whether a failure occurs in the photovoltaic power generation system according to the performance change evaluation value of the photovoltaic power generation system.

Images