Photovoltaic power station operation and maintenance fault monitoring and positioning method and platform

Abstract

The invention relates to a photovoltaic power station operation and maintenance fault monitoring and positioning method and platform, and relates to the field of photovoltaic technology, and the method comprises the steps: collecting a power generation parameter sequence for a photovoltaic module in a photovoltaic power station in operation and maintenance, carrying out the processing to obtain a total power generation parameter, and determining a target photovoltaic module to be subjected to shielding fault analysis through combining with a meteorological data sequence; extracting gale meteorological data and rainfall meteorological data, indexing to obtain a gale power generation parameter combination and a rainfall power generation parameter combination, carrying out shielding fault type analysis on the target photovoltaic module to obtain a first vegetation shielding probability and a first dust shielding probability, and obtaining a second vegetation shielding probability and a second dust shielding probability according to the rainfall power generation parameter combination; and analyzing to obtain a second vegetation shielding probability and a second dust shielding probability, generating a plurality of shielding probability distributions, and generating a fault monitoring and positioning result of the photovoltaic power station in combination with the position information of the plurality of target photovoltaic modules. The problem that the shielding fault monitoring and positioning effect of the photovoltaic module is poor in the operation and maintenance of the photovoltaic power station is solved.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic technology, and in particular to a photovoltaic power station operation and maintenance fault monitoring and positioning method and platform. Background Art

[0002] With the rapid development of photovoltaic power generation technology, the maintenance of photovoltaic power stations has become an important link in ensuring power generation efficiency. The shading failure of photovoltaic panels is a common problem that affects the efficiency of photovoltaic power generation. Obstructions such as dust, leaves, and growing materials will block light, reduce the power generation efficiency of photovoltaic cells, and even cause local overheating, affecting the life of the components. In the current prior art, the mainstream method for monitoring photovoltaic panel shading failures is real-time monitoring through cameras. However, the deployment and maintenance costs of camera monitoring systems are high, especially in large-scale photovoltaic power stations, where the installation, wiring and maintenance of cameras are huge. In addition, camera equipment is exposed to outdoor environments for a long time and is easily affected by factors such as weather, which increases the difficulty of maintenance and the risk of monitoring failure. In the prior art, the monitoring and positioning of photovoltaic component shading failures in the operation and maintenance of photovoltaic power stations have technical problems such as high costs and poor monitoring and positioning effects. Summary of the invention

[0003] The present invention aims to solve the technical problem that the occlusion fault monitoring and positioning effect of photovoltaic power station operation and maintenance fault monitoring and positioning in the prior art is poor.

[0004] In a first aspect, the present invention provides a photovoltaic power station operation and maintenance fault monitoring and positioning method, including: performing power generation parameter detection and statistics within a preset time range on multiple photovoltaic modules in the photovoltaic power station under operation and maintenance, obtaining multiple power generation parameter sequences, processing to obtain multiple total power generation parameters, combining with the meteorological data sequence within the preset time range, and determining multiple target photovoltaic modules to be subjected to shading fault analysis;

[0005] Extracting strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and indexing to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data;

[0006] According to the multiple strong wind power generation parameter combinations, the shielding fault type analysis of the multiple target photovoltaic components is performed to obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities; according to the multiple rainfall power generation parameter combinations, the shielding fault type analysis of the multiple target photovoltaic components is performed to obtain multiple second vegetation shielding probabilities and multiple second dust shielding probabilities;

[0007] Based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, multiple shading probability distributions are generated, and combined with the position information of the multiple target photovoltaic components, a fault monitoring and positioning result of the photovoltaic power station is generated.

[0008] In a second aspect, the present invention provides a photovoltaic power station operation and maintenance fault monitoring and positioning platform, the platform comprising:

[0009] Photovoltaic power generation collection module, used to detect and count the power generation parameters of multiple photovoltaic modules in the photovoltaic power station under operation and maintenance within a preset time range, obtain multiple power generation parameter sequences, process to obtain multiple total power generation parameters, and combine the meteorological data sequence within the preset time range to determine multiple target photovoltaic modules to be analyzed for shading faults;

[0010] A meteorological data extraction module, used to extract strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data by index;

[0011] A shielding fault analysis module, used to perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple strong wind power generation parameter combinations, obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities, and perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple rainfall power generation parameter combinations, and obtain multiple second vegetation shielding probabilities and multiple second dust shielding probabilities;

[0012] A fault location module is used to generate multiple shading probability distributions based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, and generate fault monitoring and location results of the photovoltaic power station in combination with the position information of the multiple target photovoltaic components.

[0013] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing the photovoltaic power station operation and maintenance fault monitoring and positioning method of the first aspect.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer software program stored therein, and when the computer software program is executed by a processor, the photovoltaic power station operation and maintenance fault monitoring and locating method of the first aspect is implemented.

[0015] The present invention uses one or more of the above-mentioned technical solutions to detect and count the power generation parameters of multiple photovoltaic modules in a photovoltaic power station within a preset time range, combine the meteorological data within the preset time, and extract data of specific meteorological conditions such as strong winds and rainfall to perform shielding fault analysis, and utilize the shielding change characteristics of different shielding objects under different weather conditions to achieve accurate identification of the shielding type of photovoltaic modules. Compared with the traditional camera monitoring method, this solution effectively avoids the high cost problem of the camera system. By analyzing the changes in the power generation parameters of photovoltaic modules under strong wind weather conditions and rainfall conditions, based on the characteristics of the changes in the shielding conditions of photovoltaic modules shielded by vegetation and dust under strong wind and rainfall weather conditions, it is possible to determine the faults caused by vegetation shielding or dust shielding. This method not only performs a dual analysis of the shielding faults through the power generation parameters under strong wind and rainfall conditions, but also generates multiple shielding probability distributions, combined with the location information of the photovoltaic modules, to achieve accurate positioning of different types of shielding faults in the photovoltaic power station. It can further improve the accuracy of fault diagnosis, provide maintenance personnel with a more intuitive positioning and repair solution, and reduce the workload of operation and maintenance personnel. At the same time, since the solution completely relies on existing meteorological data and power generation parameters without the need for additional equipment deployment, it greatly reduces the operation and maintenance costs of photovoltaic power stations. Overall, the solution not only improves the fault monitoring efficiency of photovoltaic power stations and has high practicality, but also provides a low-cost and efficient solution for the long-term operation of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a photovoltaic power station operation and maintenance fault monitoring and locating method provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of the structure of a photovoltaic power station operation and maintenance fault monitoring and positioning platform provided by an embodiment of the present invention;

[0018] Figure 3 A functional block diagram of an electronic device provided by an embodiment of the present invention;

[0019] Figure 4 A principle block diagram of the computer-readable storage medium provided by the present invention.

[0020] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0021] Photovoltaic power generation collection module 11, meteorological data extraction module 12, shading fault analysis module 13, fault location module 14, electronic device 100, memory 110, processor 120, computer program 111, computer readable storage medium 200. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0023] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0024] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0025] Example 1

[0026] like Figure 1 As shown, an embodiment of the present invention provides a photovoltaic power station operation and maintenance fault monitoring and positioning method, including the following steps.

[0027] S10: Detect and count power generation parameters of multiple photovoltaic modules in the photovoltaic power station under operation and maintenance within a preset time range, obtain multiple power generation parameter sequences, process to obtain multiple total power generation parameters, and determine multiple target photovoltaic modules for shading fault analysis in combination with meteorological data sequences within the preset time range;

[0028] In the embodiment of the present application, during the operation and maintenance of a photovoltaic power station, it is first necessary to detect and count the power generation parameters of multiple photovoltaic modules in the photovoltaic power station within a preset time range. The preset time range usually refers to a time period set according to the operation and maintenance plan of the photovoltaic power station, such as a week or a month, etc., for collecting the power generation performance of the photovoltaic modules. The photovoltaic power station includes multiple photovoltaic modules, each of which performs photovoltaic power generation, and each photovoltaic module includes, for example, a photovoltaic panel, an inverter, etc.

[0029] By continuously monitoring and counting the power generation parameters of multiple photovoltaic modules, multiple power generation parameter sequences of multiple photovoltaic modules within a preset time range can be obtained. For example, the power generation parameters include real-time output power, voltage, current and other data of photovoltaic power generation of the photovoltaic modules, which can reflect the power generation situation of the photovoltaic modules.

[0030] Furthermore, the total power generation parameters of the multiple photovoltaic modules within a preset time range are calculated based on the multiple power generation parameter sequences, and the meteorological data of the area where the photovoltaic power station is located within the preset time range is collected to obtain a meteorological data sequence. The meteorological data sequence and the multiple total power generation parameters are combined to analyze the photovoltaic modules that may have shading faults among the multiple photovoltaic modules, obtain multiple target photovoltaic modules, and further analyze the types of shading faults.

[0031] Step S10 in the method provided in the embodiment of the present application includes:

[0032] Perform power generation parameter detection and statistics on multiple photovoltaic modules in a photovoltaic power station under operation and maintenance within a preset time range to obtain multiple power generation parameter sequences;

[0033] Calculating and obtaining a plurality of total power generation parameters according to the plurality of power generation parameter sequences;

[0034] Collecting a meteorological data sequence within the preset time range, predicting power generation parameters of the plurality of photovoltaic modules, and obtaining a theoretical total power generation parameter;

[0035] The power generation parameter deviations between the plurality of total power generation parameters and the theoretical total power generation parameters are calculated, and photovoltaic components corresponding to the power generation parameter deviations greater than a power generation parameter deviation threshold are marked to obtain a plurality of target photovoltaic components.

[0036] In an embodiment of the present application, during the operation and maintenance of a photovoltaic power station, it is first necessary to detect and count the power generation parameters of multiple photovoltaic modules within a preset time range. The preset time range refers to a period of time set according to specific maintenance needs, which is used to observe the working status of photovoltaic modules in different time periods, such as a week or a month. By continuously monitoring the power generation data of each photovoltaic module, multiple power generation parameter sequences can be obtained. The power generation parameter sequence includes real-time voltage, current, power and other indicators at multiple times within the preset time range, forming a data sequence that can reflect the immediate working conditions of the photovoltaic modules. The collection of power generation parameters can be detected and counted through inverters and concentrators of photovoltaic power stations.

[0037] Furthermore, based on multiple power generation parameter sequences, multiple total power generation parameters are statistically calculated. Total power generation parameters refer to comprehensive indicators of the power generation performance of photovoltaic modules within a specified time period, such as cumulative power generation, average power output, etc. Total power generation parameters can effectively reflect the overall power generation performance of photovoltaic modules and serve as important basic data for subsequent analysis.

[0038] Meteorological data of the photovoltaic power station area is collected within the same preset time range to obtain a meteorological data sequence, which can be collected through a meteorological forecasting platform. The meteorological data in the meteorological data sequence has a corresponding meaning to the power generation parameters in multiple power generation parameter sequences, for example, belonging to multiple moments within the preset time range.

[0039] Meteorological data series covers environmental parameters including light intensity, wind speed, rainfall, temperature, humidity, etc. Meteorological data is crucial for photovoltaic power generation because the power generation capacity of photovoltaic modules is significantly affected by environmental factors. By predicting the power generation parameters of multiple photovoltaic modules based on the meteorological data series, the ideal power generation performance of each photovoltaic module under the environmental meteorological data can be predicted to obtain the theoretical total power generation parameters. The theoretical total power generation parameters are the total power generation parameters of each photovoltaic module under ideal conditions predicted based on meteorological data, representing the power generation level that the photovoltaic module should achieve under the current meteorological data series, such as the theoretical cumulative power generation and average power output within a preset time range.

[0040] Furthermore, the multiple total power generation parameters of the multiple photovoltaic modules actually calculated are compared with the theoretical total power generation parameters, and the power generation parameter deviation between the two is calculated to obtain multiple power generation parameter deviations between the multiple photovoltaic modules and the theoretical total power generation parameters. The power generation parameter deviation reflects the difference between the actual power generation of the photovoltaic module and the theoretical power generation. When the power generation parameter deviation of some photovoltaic modules exceeds the preset power generation parameter deviation threshold, it means that the photovoltaic modules may have a shielding fault, resulting in a reduction in power generation, causing their actual power generation performance to be significantly lower than expected. At this time, these photovoltaic modules are marked as target photovoltaic modules, and multiple target photovoltaic modules are obtained.

[0041] For example, the power generation parameter threshold can be a threshold range set according to the fluctuation range of the power generation of the photovoltaic module under normal conditions without shading faults, such as within the range of ±10% of the ideal total power generation parameter. If the power generation parameter deviation between the total power generation parameter and the theoretical total power generation parameter exceeds 10% of the theoretical total power generation parameter, the photovoltaic module corresponding to the total power generation parameter is marked as a target photovoltaic module. In this way, multiple photovoltaic modules are obtained.

[0042] This data-driven fault analysis method can quickly identify and locate photovoltaic modules with abnormal power generation efficiency without relying on external equipment, greatly improving the maintenance efficiency and fault handling capabilities of photovoltaic power stations.

[0043] The method provided in the embodiment of the present application of “collecting the meteorological data sequence within the preset time range to predict the power generation parameters of the plurality of photovoltaic modules” includes:

[0044] According to the historical power generation data of the photovoltaic power station, a set of sample meteorological data sequences is collected, and the theoretical total power generation parameters of a single photovoltaic module under different sample meteorological data sequences are marked to obtain a set of sample theoretical total power generation parameters;

[0045] Using the sample meteorological data sequence set and the sample theoretical total power generation parameter set to train a theoretical power generation predictor;

[0046] The theoretical power generation predictor is used to predict power generation parameters of the meteorological data sequence to obtain theoretical total power generation parameters.

[0047] In the embodiment of the present application, in order to improve the ability to predict the power generation performance of photovoltaic modules, it is first necessary to build an analysis model based on historical power generation data to predict the theoretical total power generation parameters.

[0048] The specific steps are as follows: First, in the historical power generation data of the photovoltaic power station, meteorological data within multiple preset time ranges are collected to obtain a set of sample meteorological data sequences. The sample meteorological data sequence refers to meteorological environment data in the past time, such as light intensity, wind speed, rainfall, temperature, humidity, etc. By collecting these meteorological data, a reference basis can be provided for subsequent power generation forecasts.

[0049] Furthermore, for each sample meteorological data sequence, based on the photovoltaic power generation calculation method in the prior art, the theoretical total power generation parameters of the photovoltaic module are calculated, or other factors affecting photovoltaic power generation such as shading failures are eliminated through experimental methods, and power generation tests are carried out under different sample meteorological data sequences to obtain the theoretical total power generation parameters. The theoretical total power generation parameters refer to the amount of power that the photovoltaic module should generate under ideal environmental conditions according to meteorological conditions, reflecting the standard power generation performance of the photovoltaic module under different meteorological data sequences. After all sample meteorological data and their corresponding theoretical power generation parameters are identified, a sample theoretical total power generation parameter set is formed. Each set of data in the sample theoretical total power generation parameter set contains the ideal power generation performance of a single photovoltaic module under the corresponding sample meteorological data sequence, which serves as the basic data for the power generation prediction model.

[0050] Furthermore, after obtaining the set of sample meteorological data sequences and the set of sample theoretical total power generation parameters, a theoretical power generation predictor is trained. The theoretical power generation predictor is a prediction model constructed by machine learning or statistical modeling methods, which aims to accurately predict the theoretical power generation of photovoltaic modules based on input meteorological conditions. Through training with a large amount of historical data, the predictor can learn the power generation laws of photovoltaic modules under different meteorological data sequences and improve the prediction accuracy of theoretical total power generation parameters.

[0051] Exemplarily, a set of sample meteorological data sequences and a set of sample theoretical total power generation parameters are used as training data sets, and the theoretical power generation predictor is trained using a machine learning algorithm, such as a feedforward neural network model, including an input layer, one or more hidden layers, and an output layer. The number of hidden layers and the number of neurons in each layer can be adjusted experimentally. More common are 2-3 hidden layers, each containing dozens to hundreds of neurons. The hidden layer uses a nonlinear activation function (such as the ReLU function) to enable the network to learn complex nonlinear mappings. During the training process, the theoretical power generation predictor can predict the corresponding total power generation parameters based on the input meteorological data sequence, and then calculate the error between the predicted value and the sample theoretical total power generation parameter. Then adjust the network parameters such as the weight of the hidden layer in the theoretical power generation predictor based on the error. Through an iterative optimization algorithm (such as the gradient descent method), the above steps are repeated for training, and the theoretical power generation predictor gradually approaches the optimal parameter setting, minimizes the prediction error, and converges, for example, the accuracy rate reaches 95%.

[0052] After the theoretical power generation predictor is trained, it can be used to predict power generation parameters for the meteorological data sequence within the current preset time range. Specifically, the current meteorological data sequence is input, and the predictor will output the corresponding theoretical total power generation parameters based on these data. This predicted value represents the ideal power generation of the photovoltaic module under the existing meteorological conditions, and serves as an important reference indicator for evaluating the actual operation of the photovoltaic module.

[0053] By introducing meteorological data analysis and theoretical power generation predictor training, photovoltaic power station operators can predict and evaluate the power generation performance of photovoltaic modules without relying on actual power generation data. This method can not only help timely detect photovoltaic modules with potential shading failures, but also provide reliable technical support for power station operation optimization and long-term maintenance.

[0054] S20: extracting strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and indexing to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data;

[0055] In the embodiments of the present application, different weather conditions will have an impact on different shielding faults of photovoltaic modules. For example, dust will be blown up in strong winds and more likely to fall on photovoltaic modules to block light and affect power generation. After strong winds, photovoltaic modules will be covered and blocked by more dust, resulting in a decrease in power generation parameters, such as a decrease in power generation. In the case where plants block photovoltaic modules, the area blocked by photovoltaic modules before and after the strong wind will not change significantly, and the change in power generation parameters will also be small. In addition, in rainy weather, the dust on the photovoltaic modules will be washed away. If the photovoltaic modules are blocked by dust, the power generation parameters of the photovoltaic modules will increase before and after the rain, such as the power generation will increase. In the case where plants block photovoltaic modules, the area blocked by photovoltaic modules before and after the rain will not change significantly, and the change in power generation parameters will also be small.

[0056] Therefore, in order to effectively identify and analyze the type of shading faults of photovoltaic modules, in-depth analysis is required in combination with specific meteorological conditions. Extract strong wind meteorological data and rainfall meteorological data from the meteorological data sequence. The so-called strong wind meteorological data refers to the wind speed meteorological data recorded in the meteorological sequence for the time period with high wind speed and no rainfall, such as wind speed meteorological data greater than level 5, as strong wind meteorological data. The rainfall meteorological data refers to the rainfall meteorological data for the time period with high precipitation in the meteorological sequence, such as the rainfall meteorological data for the time period with rainfall greater than 10 mm and no strong wind.

[0057] After extracting these specific meteorological data, the power generation parameter combinations of multiple target photovoltaic modules before and after the strong wind meteorological data and the rainfall meteorological data will be obtained based on the index of the strong wind meteorological data and the rainfall meteorological data. By comparing the power generation parameters of the photovoltaic modules in the time periods before and after the strong wind meteorological data and the rainfall meteorological data, it can be determined whether the power generation performance of the photovoltaic modules has been significantly changed. For example, if the power generation of some modules is significantly reduced after strong winds, it may mean that the wind has caused dust covering and blocking failures; if the power generation is significantly increased after rainy weather, it may be that the rain has washed away dust and other substances that affect photovoltaic power generation. If the power generation parameters before and after strong winds and rainy weather have not changed significantly, it may mean that the photovoltaic modules are blocked by vegetation.

[0058] By extracting high wind meteorological data and rainfall meteorological data, and indexing and extracting multiple high wind power generation parameter combinations and multiple rainfall power generation parameter combinations, the diagnostic accuracy of photovoltaic module shading faults can be improved, providing effective technical support for subsequent fault detection and maintenance.

[0059] Step S20 in the method provided in the embodiment of the present application includes:

[0060] Extracting gale meteorological data and rainfall meteorological data from the meteorological data sequence, wherein the gale meteorological data includes gale meteorological time and gale meteorological parameters, and the rainfall meteorological data includes rainfall meteorological time and rainfall meteorological parameters;

[0061] In the plurality of power generation parameter sequences, the power generation parameters before and after the strong wind weather time and before and after the rainfall weather time are respectively collected to obtain a plurality of strong wind power generation parameter combinations and a plurality of rainfall power generation parameter combinations of a plurality of photovoltaic modules.

[0062] In the embodiment of the present application, in order to analyze the power generation performance of photovoltaic modules under different meteorological conditions, firstly, strong wind meteorological data and rainfall meteorological data are extracted from the acquired meteorological data sequence. The so-called strong wind meteorological data includes the recorded strong wind meteorological time and the related strong wind meteorological parameters. The strong wind meteorological time refers to the time period when the wind speed reaches or exceeds the set threshold (for example, level 5), and the strong wind meteorological parameters are specific values ​​such as wind speed and wind direction, which can reflect the strong wind intensity within the time period. The rainfall meteorological data also includes the rainfall meteorological time and rainfall meteorological parameters when the rainfall is greater than the set threshold (for example, 10mm). The rainfall meteorological time refers to the time period when the rainfall occurs, and the rainfall meteorological parameters include rainfall intensity, rainfall amount, etc., which are used to quantify the specific situation of the rainfall.

[0063] Furthermore, from multiple power generation parameter sequences, power generation parameters before and after strong wind weather time and before and after rainfall weather time are collected respectively. By collecting power generation parameters of multiple photovoltaic modules before and after these time points, multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations can be formed. Strong wind power generation parameter combination refers to the power generation parameters of photovoltaic modules before and after strong wind weather time. Similarly, rainfall power generation parameter combination refers to the power generation parameters of photovoltaic modules before and after rainfall occurs.

[0064] For example, the time before and after the strong wind weather time and the time before and after the rainfall can be set based on those skilled in the art, specifically the time before and after the strong wind weather time and before and after the rainfall when the photovoltaic components are in normal light power generation. For example, from multiple power generation parameter sequences, the power generation parameters of one hour before and after the strong wind weather time and the power generation parameters of one hour before and after the rainfall weather time are collected respectively, and multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations are obtained.

[0065] S30: performing shielding fault type analysis of the multiple target photovoltaic components according to the multiple strong wind power generation parameter combinations, obtaining multiple first vegetation shielding probabilities and multiple first dust shielding probabilities; performing shielding fault type analysis of the multiple target photovoltaic components according to the multiple rainfall power generation parameter combinations, obtaining multiple second vegetation shielding probabilities and multiple second dust shielding probabilities;

[0066] In an embodiment of the present application, during the operation and maintenance of a photovoltaic power station, in order to accurately identify the type of shading fault of a photovoltaic module, a multi-dimensional analysis is performed based on the power generation performance under strong wind and rainfall meteorological conditions. First, through a combination of strong wind power generation parameters, a plurality of target photovoltaic modules are analyzed for the type of shading fault. A strong wind power generation parameter combination refers to a parameter set composed of the power generation data (such as power output, voltage, current, etc.) of the photovoltaic module before and after the strong wind meteorological event. By analyzing these data, the probability of a photovoltaic module being blocked by dust or vegetation can be obtained based on the impact of strong winds on the power generation parameters of the photovoltaic module.

[0067] During this analysis, the changes in power generation parameters such as power generation before and after the strong wind will be compared. If the power generation of some photovoltaic modules decreases after the strong wind, it may indicate that the photovoltaic modules are covered by dust after the strong wind, resulting in a decrease in power generation parameters. Based on this prediction, the first vegetation shading probability and the first dust shading probability are obtained, that is, the possibility of vegetation shading failure under strong wind conditions. At the same time, the possibility of dust shading will be evaluated based on the changes in power generation performance after the strong wind.

[0068] In addition, multiple combinations of rainfall power generation parameters are used for further analysis. The rainfall power generation parameter combination refers to the power generation data set of photovoltaic modules before and after the rainfall meteorological event. Rainfall conditions usually have a significant impact on dust shading because rainwater can clear the dust accumulation on the surface of the module. By comparing the changes in power generation before and after rainfall, shading failures caused by dust shading can be identified. If the power generation of some photovoltaic modules increases significantly after rainfall, it means that these modules may have generated poor power before due to dust coverage. If the power generation of some photovoltaic modules does not change significantly after rainfall, it means that these photovoltaic modules may have generated poor power before. It may be in a vegetation shading failure state, so the second vegetation shading probability and the second dust shading probability can be calculated, that is, the failure probability of dust shading under rainfall conditions.

[0069] In summary, through comprehensive analysis of the wind power generation parameter combination and the rainfall power generation parameter combination, the first vegetation shading probability, the first dust shading probability, the second vegetation shading probability and the second dust shading probability of multiple target photovoltaic modules can be calculated respectively. These probability data provide an important basis for the subsequent shading fault diagnosis. The fault is double-verified by meteorological conditions such as strong wind and rainfall, which improves the accuracy and reliability of fault diagnosis. By comparing the changes in the power generation parameter combination, the shading type can be better identified, and more accurate technical support can be provided for the maintenance of photovoltaic modules.

[0070] Step S30 in the method provided in the embodiment of the present application includes:

[0071] According to the historical fault monitoring data of multiple photovoltaic modules, a sample high wind power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample high wind power generation parameter combinations is obtained, and the calculations are marked as the sample first vegetation blocking probability set and the sample first dust blocking probability set;

[0072] The sample high wind power generation parameter combination set, the sample first vegetation shielding probability set and the sample first dust shielding probability set are used to train a high wind shielding predictor;

[0073] The high wind shielding predictor is used to analyze the shielding fault types of the multiple target photovoltaic components for the multiple high wind power generation parameter combinations, and obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities.

[0074] In the embodiment of the present application, in order to improve the ability to identify shading faults of photovoltaic components in windy weather, machine learning methods are used to analyze the types of shading faults.

[0075] First, based on the historical fault monitoring data of multiple photovoltaic modules, that is, the recorded data when the shielding fault occurred in the historical time, the sample wind power generation parameter combination set is collected by the method described above. Each sample power generation parameter combination set includes the power output, current and voltage and other power generation parameters of the photovoltaic module recorded before and after the historical windy weather data, reflecting the power generation performance of the module before and after the windy weather.

[0076] Furthermore, according to the proportion of photovoltaic components blocked by vegetation or dust under different sample wind power generation parameter combinations obtained through actual maintenance detection of photovoltaic components in historical fault monitoring data, the sample first vegetation blocking probability and sample first dust blocking probability are calculated and labeled. For example, under a certain sample wind power generation parameter combination, the number of detections of the sample wind power generation parameter combination is 15 times, and the actual maintenance detection shows that the number of photovoltaic components blocked by vegetation is 5 times, and the number of photovoltaic components blocked by dust is 10 times. Then the proportion of photovoltaic components blocked by vegetation is 1 / 3, the sample first vegetation blocking probability is 0.33, and the sample first dust blocking probability is 0.67. In this way, according to the historical fault monitoring data and the sample wind power generation parameter combination set, the sample first vegetation blocking probability set and the sample first dust blocking probability set are labeled.

[0077] Among them, due to errors in photovoltaic power generation parameter monitoring and errors in communication transmission of other machines and equipment, photovoltaic components may be blocked by vegetation or dust under a combination of strong wind power generation parameters. Therefore, the embodiment of the present application analyzes the probability of vegetation blocking and the probability of dust blocking to provide a reference for photovoltaic component blocking fault maintenance.

[0078] Based on machine learning, a high wind shielding predictor is trained using a sample high wind power generation parameter combination set, a sample first vegetation shielding probability set, and a sample first dust shielding probability set. The high wind shielding predictor is used to predict the probability of a photovoltaic module being shielded by vegetation or dust based on the input high wind power generation parameter combination.

[0079] Exemplarily, a high wind shading predictor is trained based on a feedforward neural network, which includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer should match the number of input features, that is, the dimension of the high wind power generation parameter combination. The hidden layer includes multiple hidden layers, each of which includes multiple neurons. The number of neurons in the output layer is two, corresponding to the first vegetation shading probability and the first dust shading probability, respectively. The feedforward neural network is trained using a training set, and the network weights are optimized using a backpropagation algorithm. The specific steps include: forward propagation, passing the input data through the network layer layer by layer, and calculating the output first vegetation shading probability and the first dust shading probability. Loss calculation, using a loss function (such as cross entropy loss) to evaluate the error between the predicted value and the true value, specifically calculating the error between the output first vegetation shading probability and the first dust shading probability and the sample first vegetation shading probability and the sample first dust shading probability. Back propagation, updating the network parameters according to the error to minimize the error. Optimization algorithms such as Adam or SGD are usually used to adjust and optimize network parameters. After multiple sets of data and multiple rounds of training parameter adjustments, the error reaches the requirement, for example, less than 4%, and the training of the high wind occlusion predictor is completed.

[0080] Using the trained high wind shading predictor, the current multiple high wind power generation parameter combinations are input and analyzed to identify the shading fault types of multiple target photovoltaic modules, obtain multiple first vegetation shading probabilities and multiple first dust shading probabilities, and provide a basis for subsequent fault diagnosis and maintenance decisions. The above steps identify the probability of shading fault types based on the different effects of vegetation shading and dust shading before and after high wind weather, which not only improves the accuracy of photovoltaic module fault identification, but also provides data support for operation and maintenance management, and enhances the overall operation efficiency of photovoltaic power stations.

[0081] Step S30 in the method provided in the embodiment of the present application includes:

[0082] According to the historical fault monitoring data of multiple photovoltaic modules, a sample rainfall power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample rainfall power generation parameter combinations is obtained, and the calculation is marked as the sample second vegetation blocking probability set and the sample second dust blocking probability set;

[0083] Using the sample rainfall power generation parameter combination set, the sample second vegetation shading probability set and the sample second dust shading probability set to train a rainfall shading predictor;

[0084] The rainfall shading predictor is used to analyze the shading fault types of the multiple target photovoltaic components for the multiple rainfall power generation parameter combinations, and a plurality of second vegetation shading probabilities and a plurality of second dust shading probabilities are obtained.

[0085] In an embodiment of the present application, based on the steps of analyzing the shading fault types of multiple target photovoltaic components according to multiple strong wind power generation parameter combinations in the aforementioned content, the shading fault types of multiple target photovoltaic components are analyzed according to multiple rainfall power generation parameter combinations.

[0086] According to the historical fault monitoring data of multiple PV modules, a set of sample rainfall power generation parameter combinations is collected, and the proportion of PV modules blocked by vegetation or dust under each sample rainfall power generation parameter combination is obtained, and the sample second vegetation blocking probability and the sample second dust blocking probability are calculated. In this way, the sample second vegetation blocking probability set and the sample second dust blocking probability set are obtained by marking.

[0087] Furthermore, a sample rainfall power generation parameter combination set is used as input data, a sample second vegetation shading probability set and a sample second dust shading probability set are used as output data, and the three are combined as supervised training data. Based on machine learning, a rainfall shading predictor is trained. The rainfall shading predictor is used to predict the probability of a shading failure caused by a photovoltaic component being blocked by vegetation or dust according to the input rainfall power generation parameter combination, and output the second vegetation shading probability and the second dust shading probability.

[0088] Exemplarily, the rain occlusion predictor is trained based on a feedforward neural network. The training process is the same as the training process of the high wind occlusion predictor, but the specific training data is different. The training process steps refer to the aforementioned content and will not be repeated here.

[0089] The trained rainfall shading predictor is used to input multiple rainfall power generation parameter combinations, and the shading fault types of multiple target photovoltaic modules are analyzed to obtain multiple second vegetation shading probabilities and multiple second dust shading probabilities.

[0090] The above steps identify the probability of shading fault types based on the different effects of vegetation shading and dust shading before and after rainfall. This not only improves the accuracy of photovoltaic module fault identification, but also provides data support for operation and maintenance management, and enhances the overall operation efficiency of photovoltaic power stations.

[0091] S40: Based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, multiple shading probability distributions are generated, and combined with the position information of the multiple target photovoltaic components, a fault monitoring and positioning result of the photovoltaic power station is generated.

[0092] In the embodiment of the present application, based on the multiple first vegetation shading probabilities and multiple first dust shading probabilities, multiple second vegetation shading probabilities and multiple second dust shading probabilities obtained by the analysis in the above content, a comprehensive vegetation shading probability and dust shading probability of each photovoltaic component being shaded by vegetation or dust are generated, and multiple shading probability distributions of multiple photovoltaic components are generated. Among them, if the vegetation shading probability in a shading probability distribution is large, then the photovoltaic component is likely to be shaded by vegetation and cause a shading fault.

[0093] Based on the multiple shading probability distributions, combined with the location information of multiple target photovoltaic modules, the fault monitoring and positioning results of the photovoltaic power station are generated. The fault monitoring and positioning results include the location information of multiple target photovoltaic modules where multiple power generation parameters are abnormal and may cause shading accidents, as well as the shading probability distribution of multiple target photovoltaic modules being blocked by vegetation and dust. Technicians can perform reference operations for photovoltaic module maintenance based on the fault monitoring and positioning results.

[0094] The embodiment of the present application not only improves the operation and maintenance efficiency of photovoltaic power stations, but also can identify potential faults in advance and perform targeted maintenance, thereby optimizing overall power generation performance and reducing operating costs. Through a data-driven approach, combined with historical monitoring data and real-time meteorological information, an intelligent fault monitoring and positioning method is constructed to provide strong support for the efficient management of photovoltaic power stations.

[0095] Step S40 in the method provided in the embodiment of the present application includes:

[0096] According to the gale meteorological parameters and the rainfall meteorological parameters in the gale meteorological data and the rainfall meteorological data, weights are assigned, and the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities are weightedly calculated to obtain multiple vegetation shading probabilities and dust shading probabilities;

[0097] Based on the multiple vegetation occlusion probabilities and dust occlusion probabilities, generating multiple occlusion probability distributions;

[0098] The position information of the multiple target photovoltaic components is obtained, and combined with the multiple shading probability distributions, a fault monitoring and positioning result is generated.

[0099] In the embodiment of the present application, in order to more accurately evaluate the shading condition of the photovoltaic components, the existing shading probability is weightedly calculated based on the meteorological parameters of the strong wind meteorological data and the rainfall meteorological data.

[0100] Weights are allocated according to the gale meteorological parameters and rainfall meteorological parameters in the gale meteorological data and the rainfall meteorological data. Exemplarily, the gale meteorological ratio is obtained according to the ratio of the gale meteorological parameters, such as wind force, in the gale meteorological data to the maximum wind force in the historical meteorological data of the target photovoltaic power station. And the rainfall meteorological ratio is obtained according to the ratio of the rainfall meteorological parameters, such as rainfall, in the rainfall meteorological data to the maximum rainfall in the historical meteorological data of the target photovoltaic power station. According to the gale meteorological ratio and the rainfall meteorological ratio, the first weight and the second weight are allocated, for example, the ratio of the gale meteorological ratio to the sum of the gale meteorological ratio and the rainfall meteorological ratio is calculated as the first weight, and the ratio of the rainfall meteorological ratio to the sum of the gale meteorological ratio and the rainfall meteorological ratio is calculated as the second weight.

[0101] Among them, if the current strong wind weather is stronger, the influence on vegetation shielding and dust shielding will be greater, and the accuracy of the multiple first vegetation shielding probabilities and the multiple first dust shielding probabilities analyzed based on the combination of strong wind power generation parameters under the strong wind weather data will be higher, and the weight will be larger. Conversely, if the current rainfall weather data is stronger, the accuracy of the multiple second vegetation shielding probabilities and the multiple second dust shielding probabilities will be higher, and the weight will be larger.

[0102] Further, the first weight and the second weight are used to weightedly calculate the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, respectively, to obtain the multiple vegetation shading probabilities and the multiple dust shading probabilities. Exemplarily, the first weight and the second weight are used to weightedly calculate the first dust shading probability and the second dust shading probability of each photovoltaic component to obtain the dust shading probability.

[0103] Based on the multiple vegetation shading probabilities and the multiple dust shading probabilities, multiple shading probability distributions are generated, each of which includes the vegetation shading probability and the dust shading probability of a photovoltaic module, reflecting the probability that the photovoltaic module is shading by dust or vegetation. The sum of the vegetation shading probability and the dust shading probability of a single photovoltaic module after weighted calculation may not be 1, and the vegetation shading probability and the dust shading probability may be redistributed in proportion so that the sum of the two is 1.

[0104] Finally, the location information of multiple target PV panels is obtained, and the fault monitoring and positioning results are generated by combining multiple occlusion probability distributions.

[0105] The embodiments of the present application achieve the following technical effects through the above specific implementation methods:

[0106] The embodiment of the present application uses the above scheme to detect and count the power generation parameters of multiple photovoltaic modules in the photovoltaic power station within the preset time range, combine the meteorological data within the preset time, and extract the data of specific meteorological conditions such as strong wind and rainfall to analyze the shielding fault, and use the shielding change characteristics of different shielding objects under different weather conditions to achieve accurate identification of the shielding type of photovoltaic modules. Compared with the traditional camera monitoring method, this scheme effectively avoids the high cost problem of the camera system. By analyzing the changes in the power generation parameters of photovoltaic modules under strong wind weather conditions and rainy weather conditions, based on the characteristics of the changes in the shielding conditions of photovoltaic modules shielded by vegetation and dust under strong wind and rainy weather conditions, it is possible to judge the faults caused by vegetation shielding or dust shielding. This method not only performs a dual analysis of the shielding fault through the power generation parameters under strong wind and rain conditions, but also generates multiple shielding probability distributions, combined with the location information of photovoltaic modules, to achieve accurate positioning of different types of shielding faults in the photovoltaic power station. It can further improve the accuracy of fault diagnosis, provide maintenance personnel with more intuitive positioning and repair solutions, and reduce the workload of operation and maintenance personnel. At the same time, since the solution completely relies on existing meteorological data and power generation parameters without the need for additional equipment deployment, it greatly reduces the operation and maintenance costs of photovoltaic power stations. Overall, the solution not only improves the fault monitoring efficiency of photovoltaic power stations and has high practicality, but also provides a low-cost and efficient solution for the long-term operation of photovoltaic power stations.

[0107] Example 2

[0108] like Figure 2 As shown, based on the same inventive concept as the photovoltaic power station operation and maintenance fault monitoring and positioning method provided in Example 1, an embodiment of the present invention provides a photovoltaic power station operation and maintenance fault monitoring and positioning platform, the platform comprising:

[0109] The photovoltaic power generation acquisition module 11 is used to detect and count the power generation parameters of multiple photovoltaic modules in the photovoltaic power station under operation and maintenance within a preset time range, obtain multiple power generation parameter sequences, process and obtain multiple total power generation parameters, and determine multiple target photovoltaic modules to be analyzed for shading faults in combination with the meteorological data sequence within the preset time range;

[0110] A meteorological data extraction module 12 is used to extract strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data by index;

[0111] The shielding fault analysis module 13 is used to perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple strong wind power generation parameter combinations, obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities, and perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple rainfall power generation parameter combinations, and obtain multiple second vegetation shielding probabilities and multiple second dust shielding probabilities;

[0112] The fault location module 14 is used to generate multiple shading probability distributions based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, and generate fault monitoring and location results of the photovoltaic power station in combination with the position information of the multiple target photovoltaic components.

[0113] Furthermore, the photovoltaic power generation collection module 11 is also used for:

[0114] Perform power generation parameter detection and statistics on multiple photovoltaic modules in a photovoltaic power station under operation and maintenance within a preset time range to obtain multiple power generation parameter sequences;

[0115] Calculating and obtaining a plurality of total power generation parameters according to the plurality of power generation parameter sequences;

[0116] Collecting a meteorological data sequence within the preset time range, predicting power generation parameters of the plurality of photovoltaic modules, and obtaining a theoretical total power generation parameter;

[0117] The power generation parameter deviations between the plurality of total power generation parameters and the theoretical total power generation parameters are calculated, and photovoltaic components corresponding to the power generation parameter deviations greater than a power generation parameter deviation threshold are marked to obtain a plurality of target photovoltaic components.

[0118] The step of collecting the meteorological data sequence within the preset time range and predicting the power generation parameters of the plurality of photovoltaic modules includes:

[0119] According to the historical power generation data of the photovoltaic power station, a set of sample meteorological data sequences is collected, and the theoretical total power generation parameters of a single photovoltaic module under different sample meteorological data sequences are marked to obtain a set of sample theoretical total power generation parameters;

[0120] Using the sample meteorological data sequence set and the sample theoretical total power generation parameter set to train a theoretical power generation predictor;

[0121] The theoretical power generation predictor is used to predict power generation parameters of the meteorological data sequence to obtain theoretical total power generation parameters.

[0122] Furthermore, the meteorological data extraction module 12 is further used to: extract gale meteorological data and rainfall meteorological data in the meteorological data sequence, wherein the gale meteorological data includes gale meteorological time and gale meteorological parameters, and the rainfall meteorological data includes rainfall meteorological time and rainfall meteorological parameters;

[0123] In the plurality of power generation parameter sequences, the power generation parameters before and after the strong wind weather time and before and after the rainfall weather time are respectively collected to obtain a plurality of strong wind power generation parameter combinations and a plurality of rainfall power generation parameter combinations of a plurality of photovoltaic modules.

[0124] Furthermore, the obstruction fault analysis module 13 is also used for:

[0125] According to the historical fault monitoring data of multiple photovoltaic modules, a sample high wind power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample high wind power generation parameter combinations is obtained, and the calculations are marked as the sample first vegetation blocking probability set and the sample first dust blocking probability set;

[0126] The sample high wind power generation parameter combination set, the sample first vegetation shielding probability set and the sample first dust shielding probability set are used to train a high wind shielding predictor;

[0127] The high wind shielding predictor is used to analyze the shielding fault types of the multiple target photovoltaic components for the multiple high wind power generation parameter combinations, and obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities.

[0128] Furthermore, the obstruction fault analysis module 13 is also used for:

[0129] According to the historical fault monitoring data of multiple photovoltaic modules, a sample rainfall power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample rainfall power generation parameter combinations is obtained, and the calculation is marked as the sample second vegetation blocking probability set and the sample second dust blocking probability set;

[0130] Using the sample rainfall power generation parameter combination set, the sample second vegetation shading probability set and the sample second dust shading probability set to train a rainfall shading predictor;

[0131] The rainfall shading predictor is used to analyze the shading fault types of the multiple target photovoltaic components for the multiple rainfall power generation parameter combinations, and a plurality of second vegetation shading probabilities and a plurality of second dust shading probabilities are obtained.

[0132] Furthermore, the fault location module 14 is also used for:

[0133] According to the gale meteorological parameters and the rainfall meteorological parameters in the gale meteorological data and the rainfall meteorological data, weights are assigned, and the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities are weightedly calculated to obtain multiple vegetation shading probabilities and dust shading probabilities;

[0134] Based on the multiple vegetation occlusion probabilities and dust occlusion probabilities, generating multiple occlusion probability distributions;

[0135] The position information of the multiple target photovoltaic components is obtained, and a fault monitoring and positioning result is generated in combination with the multiple shading probability distributions.

[0136] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 100, including a memory 110, a processor 120, and a computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the computer program 111, the steps of the method in Example 1 are implemented.

[0137] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 200 on which a computer program 111 is stored. When the computer program 111 is executed by a processor, the steps of the method in Embodiment 1 are implemented.

[0138] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0143] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0144] Obviously, those skilled in the art can 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 claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A photovoltaic power station operation and maintenance fault monitoring and positioning method, characterized in that: The method comprises: Perform power generation parameter detection and statistics within a preset time range on multiple photovoltaic modules in a photovoltaic power station under operation and maintenance, obtain multiple power generation parameter sequences, process to obtain multiple total power generation parameters, and combine with the meteorological data sequence within the preset time range to determine multiple target photovoltaic modules to be analyzed for shading faults; Extracting strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and indexing to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data; According to the multiple strong wind power generation parameter combinations, the shielding fault type analysis of the multiple target photovoltaic components is performed to obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities; according to the multiple rainfall power generation parameter combinations, the shielding fault type analysis of the multiple target photovoltaic components is performed to obtain multiple second vegetation shielding probabilities and multiple second dust shielding probabilities; Based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, multiple shading probability distributions are generated, and combined with the position information of the multiple target photovoltaic components, a fault monitoring and positioning result of the photovoltaic power station is generated.

2. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 1 is characterized in that: Perform power generation parameter detection and statistics within a preset time range for multiple photovoltaic modules in a photovoltaic power station under operation and maintenance, obtain multiple power generation parameter sequences, process to obtain multiple total power generation parameters, and combine with the meteorological data sequence within the preset time range to determine multiple target photovoltaic modules to be analyzed for shading faults, including: Perform power generation parameter detection and statistics on multiple photovoltaic modules in a photovoltaic power station under operation and maintenance within a preset time range to obtain multiple power generation parameter sequences; Calculating and obtaining a plurality of total power generation parameters according to the plurality of power generation parameter sequences; Collecting a meteorological data sequence within the preset time range, predicting power generation parameters of the plurality of photovoltaic modules, and obtaining a theoretical total power generation parameter; The power generation parameter deviations between the plurality of total power generation parameters and the theoretical total power generation parameters are calculated, and photovoltaic components corresponding to the power generation parameter deviations greater than a power generation parameter deviation threshold are marked to obtain a plurality of target photovoltaic components.

3. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 2 is characterized in that: Collecting a meteorological data sequence within the preset time range to predict power generation parameters of the plurality of photovoltaic modules includes: According to the historical power generation data of the photovoltaic power station, a set of sample meteorological data sequences is collected, and the theoretical total power generation parameters of a single photovoltaic module under different sample meteorological data sequences are marked to obtain a set of sample theoretical total power generation parameters; Using the sample meteorological data sequence set and the sample theoretical total power generation parameter set to train a theoretical power generation predictor; The theoretical power generation predictor is used to predict power generation parameters of the meteorological data sequence to obtain theoretical total power generation parameters.

4. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 1, characterized in that: According to the meteorological data sequence, strong wind meteorological data and rainfall meteorological data are extracted, and multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data are obtained by indexing, including: Extracting gale meteorological data and rainfall meteorological data from the meteorological data sequence, wherein the gale meteorological data includes gale meteorological time and gale meteorological parameters, and the rainfall meteorological data includes rainfall meteorological time and rainfall meteorological parameters; In the plurality of power generation parameter sequences, the power generation parameters before and after the strong wind weather time and before and after the rainfall weather time are respectively collected to obtain a plurality of strong wind power generation parameter combinations and a plurality of rainfall power generation parameter combinations of a plurality of photovoltaic modules.

5. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 1, characterized in that: According to the multiple wind power generation parameter combinations, the shielding fault type analysis of the multiple target photovoltaic components is performed, including: According to the historical fault monitoring data of multiple photovoltaic modules, a sample high wind power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample high wind power generation parameter combinations is obtained, and the calculations are marked as the sample first vegetation blocking probability set and the sample first dust blocking probability set; The sample high wind power generation parameter combination set, the sample first vegetation shielding probability set and the sample first dust shielding probability set are used to train a high wind shielding predictor; The high wind shielding predictor is used to analyze the shielding fault types of the multiple target photovoltaic components for the multiple high wind power generation parameter combinations, and obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities.

6. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 1, characterized in that: According to the plurality of combinations of rainfall power generation parameters, analyzing the types of shading faults of the plurality of target photovoltaic components includes: According to the historical fault monitoring data of multiple photovoltaic modules, a sample rainfall power generation parameter combination set is collected, and the proportion of photovoltaic modules blocked by vegetation or dust under different sample rainfall power generation parameter combinations is obtained, and the calculation is marked as the sample second vegetation blocking probability set and the sample second dust blocking probability set; The sample rainfall power generation parameter combination set, the sample second vegetation shading probability set and the sample second dust shading probability set are used to train a rainfall shading predictor; The rainfall shading predictor is used to analyze the shading fault types of the multiple target photovoltaic components for the multiple rainfall power generation parameter combinations, and a plurality of second vegetation shading probabilities and a plurality of second dust shading probabilities are obtained.

7. The photovoltaic power station operation and maintenance fault monitoring and positioning method according to claim 1, characterized in that: Based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, multiple shading probability distributions are generated, and combined with the position information of the multiple target photovoltaic components, a fault monitoring and positioning result of the photovoltaic power station is generated, including: According to the gale meteorological parameters and the rainfall meteorological parameters in the gale meteorological data and the rainfall meteorological data, weights are assigned, and the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities are weightedly calculated to obtain multiple vegetation shading probabilities and dust shading probabilities; Based on the multiple vegetation occlusion probabilities and dust occlusion probabilities, generating multiple occlusion probability distributions; The position information of the multiple target photovoltaic components is obtained, and combined with the multiple shading probability distributions, a fault monitoring and positioning result is generated.

8. A photovoltaic power station operation and maintenance fault monitoring and positioning platform, characterized in that: The platform includes: Photovoltaic power generation collection module, used to detect and count the power generation parameters of multiple photovoltaic modules in the photovoltaic power station under operation and maintenance within a preset time range, obtain multiple power generation parameter sequences, process to obtain multiple total power generation parameters, and combine the meteorological data sequence within the preset time range to determine multiple target photovoltaic modules to be analyzed for shading faults; A meteorological data extraction module, used to extract strong wind meteorological data and rainfall meteorological data according to the meteorological data sequence, and to obtain multiple strong wind power generation parameter combinations and multiple rainfall power generation parameter combinations of the multiple target photovoltaic components before and after the strong wind meteorological data and rainfall meteorological data by index; A shielding fault analysis module, used to perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple strong wind power generation parameter combinations, obtain multiple first vegetation shielding probabilities and multiple first dust shielding probabilities, and perform shielding fault type analysis of the multiple target photovoltaic components according to the multiple rainfall power generation parameter combinations, and obtain multiple second vegetation shielding probabilities and multiple second dust shielding probabilities; A fault location module is used to generate multiple shading probability distributions based on the multiple first vegetation shading probabilities and the multiple first dust shading probabilities, the multiple second vegetation shading probabilities and the multiple second dust shading probabilities, and generate fault monitoring and location results of the photovoltaic power station in combination with the position information of the multiple target photovoltaic components.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the photovoltaic power station operation and maintenance fault monitoring and positioning method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the photovoltaic power station operation and maintenance fault monitoring and positioning method according to any one of claims 1 to 7 is implemented.

Images