Photovoltaic string anomaly diagnosis method and device, storage medium and electronic equipment

Abstract

The application provides an abnormality diagnosis method and device of a photovoltaic string, a storage medium and an electronic device. The method comprises the following steps: in response to a diagnosis instruction, obtaining operation monitoring data of a combiner box and a pre-generated historical feature table. The operation monitoring data comprises at least one of string current, DC bus voltage and total DC power of each photovoltaic string connected to the combiner box within a preset time. The historical feature table comprises operation characteristics of the combiner box in a plurality of target time periods. The operation monitoring data and the historical feature table are used to diagnose each photovoltaic string, and an abnormality diagnosis result of each photovoltaic string is obtained. That is, the photovoltaic string can be diagnosed efficiently and accurately by the application.

Description

Technical Field

[0001] This application relates to the field of new energy technology, and more specifically, to a method, apparatus, storage medium, and electronic equipment for diagnosing anomalies in photovoltaic strings. Background Technology

[0002] With the rapid development of photovoltaic power generation technology, the scale of photovoltaic power plants is constantly expanding, and the number of photovoltaic strings is also increasing. As the basic unit of a photovoltaic power generation system, the operating status of the photovoltaic string directly affects the power generation efficiency and stability of the entire system. In actual operation, photovoltaic strings may experience performance degradation or malfunctions due to component aging, shading, wiring faults, etc., leading to power generation loss or even safety hazards.

[0003] Currently, anomaly diagnosis in photovoltaic power plants mainly relies on manual inspections and regular maintenance. However, manual inspections are inefficient, costly, and struggle to detect anomalies in real time. Furthermore, while existing automated monitoring systems can collect operational data from photovoltaic strings, they typically only perform simple threshold checks and cannot deeply analyze the correlations between data points, resulting in low accuracy and efficiency in anomaly diagnosis. This is particularly problematic in large-scale photovoltaic power plants, where the sheer number of strings and the massive amount of data make it difficult for traditional diagnostic methods to quickly locate abnormal strings, severely impacting operation and maintenance efficiency. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, storage medium, and electronic device for diagnosing anomalies in photovoltaic strings, which can efficiently and accurately complete the diagnosis of photovoltaic strings. The specific solution is as follows:

[0005] A method for diagnosing anomalies in photovoltaic strings, comprising:

[0006] In response to diagnostic commands, acquire the junction box's operational monitoring data and a pre-generated historical feature table;

[0007] Based on the operational monitoring data and historical feature table, each photovoltaic string is diagnosed to obtain anomaly diagnosis results for each photovoltaic string.

[0008] Optionally, the above method, in which the acquisition of the combiner box's operational monitoring data and the pre-generated historical feature table, includes:

[0009] Obtain the target status information of the combiner box, wherein the target status information includes at least one of the following: operating status information, environmental status information, and data acquisition status information;

[0010] Determine whether the junction box meets the diagnostic conditions based on the target status information;

[0011] If the combiner box is found to meet the diagnostic conditions, the operation monitoring data of the combiner box and a pre-generated historical feature table are obtained. The operation monitoring data includes at least one of the string current, DC bus voltage and total DC power of each photovoltaic string connected to the combiner box within a preset time period. The historical feature table includes the operation characteristics of the combiner box in multiple target time periods.

[0012] Optionally, in the above method, detecting whether the combiner box meets the diagnostic conditions based on the target status information includes:

[0013] If the operating status information indicates that the junction box is online, the environmental status information indicates that there is sufficient light, and the data acquisition status information indicates that the data required for diagnosis has been acquired, then the junction box is determined to meet the diagnostic conditions.

[0014] If the operating status information indicates that the combiner box is offline, the environmental status information indicates insufficient lighting, or the data acquisition status information indicates that no data required for diagnosis has been collected, then it is determined that the combiner box does not meet the diagnostic conditions.

[0015] Optionally, the process of generating the historical feature table in the above method includes:

[0016] The operating parameters of the combiner box for each historical time period are obtained, and the operating parameters include telemetry data and remote signaling data;

[0017] For each historical time period, the number of abnormal photovoltaic strings is determined based on the string current of each photovoltaic string in the telemetry data of the historical time period. If the proportion of the number of abnormal photovoltaic strings in the historical time period to the total number of photovoltaic strings is not greater than the proportion threshold, then the historical time period is determined as the target time period.

[0018] Feature extraction is performed on the operating parameters during the target time period to obtain the operating characteristics of the combiner box during the target time period;

[0019] The operational characteristics of the target time period are stored in a preset data table to obtain a historical characteristic table.

[0020] Optionally, in the above method, determining the historical time period as the target time period includes:

[0021] The weather type for the historical time period is determined based on the string current in the operating parameters of the historical time period.

[0022] If the weather type of the historical time period is sunny, then the historical time period is determined as the target time period.

[0023] Optionally, the above method may involve diagnosing each photovoltaic string based on the operational monitoring data and historical feature table to obtain anomaly diagnosis results for each photovoltaic string, including:

[0024] The output dispersion rate of each photovoltaic string is calculated based on the operation monitoring data.

[0025] Based on the preset anomaly identification rules, the operation monitoring data, and the historical feature table, the identification result of each photovoltaic string is obtained, and the identification result indicates whether the photovoltaic string has experienced a preset type of anomaly.

[0026] Based on the output dispersion rate of each photovoltaic string and the identification result, the abnormal diagnosis result of each photovoltaic string is obtained.

[0027] Optionally, after obtaining the anomaly diagnosis result for each of the photovoltaic strings, the above method further includes:

[0028] For each photovoltaic string, if the abnormal diagnosis result indicates that the photovoltaic string is abnormal, then the fault cause and repair suggestion information of the photovoltaic string are generated; the abnormal diagnosis result, fault cause and repair suggestion information of the photovoltaic string are output.

[0029] An anomaly diagnosis device for photovoltaic strings includes:

[0030] The acquisition unit is used to acquire the operation monitoring data of the combiner box and the pre-generated historical feature table in response to diagnostic commands;

[0031] The diagnostic unit is used to diagnose each photovoltaic string based on the operation monitoring data and the historical feature table, and to obtain the abnormal diagnostic results of each photovoltaic string.

[0032] A storage medium comprising stored instructions, wherein, when the instructions are executed, the device in which the storage medium resides executes the abnormal diagnosis method for a photovoltaic string as described in the first aspect.

[0033] An electronic device includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in the first aspect, using an anomaly diagnosis method for a photovoltaic string.

[0034] Compared with the prior art, this application has the following beneficial effects:

[0035] This application provides a method, apparatus, storage medium, and electronic device for anomaly diagnosis of photovoltaic (PV) strings. The method includes: responding to a diagnostic command, acquiring operational monitoring data of a combiner box and a pre-generated historical feature table. The operational monitoring data includes at least one of the string current, DC bus voltage, and total DC power of each PV string connected to the combiner box within a preset time period. The historical feature table includes the operational characteristics of the combiner box over multiple target time periods. The method is then used to diagnose each PV string based on the operational monitoring data and the historical feature table to obtain an anomaly diagnosis result for each PV string. Applying the method provided in this application, the automated data acquisition and diagnostic process reduces reliance on manual inspections and lowers maintenance costs. Furthermore, by combining real-time monitoring data with the historical feature table for anomaly diagnosis of PV strings, abnormal string states can be identified more accurately, improving the reliability and efficiency of the diagnosis. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0037] Figure 1 This is a schematic diagram of the structure of a photovoltaic string anomaly diagnosis system provided in an embodiment of this application;

[0038] Figure 2 A flowchart illustrating an anomaly diagnosis method for photovoltaic strings provided in this application embodiment;

[0039] Figure 3 A flowchart illustrating the process for identifying the causes of abnormalities in a photovoltaic string, as provided in this application embodiment;

[0040] Figure 4 A schematic diagram of the structure of a photovoltaic string anomaly diagnosis device provided in an embodiment of this application;

[0041] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] Currently, anomaly diagnosis in photovoltaic power plants mainly relies on manual inspections and regular maintenance. However, manual inspections are inefficient, costly, and struggle to detect anomalies in real time. Furthermore, while existing automated monitoring systems can collect operational data from photovoltaic strings, they typically only perform simple threshold checks and cannot deeply analyze the correlations between data points, resulting in low accuracy and efficiency in anomaly diagnosis. This is particularly problematic in large-scale photovoltaic power plants, where the sheer number of strings and the massive amount of data make it difficult for traditional diagnostic methods to quickly locate abnormal strings, severely impacting operation and maintenance efficiency.

[0044] Based on this, embodiments of this application also provide a method for diagnosing anomalies in photovoltaic strings, which can be applied to electronic devices. The flowchart of this method is as follows: Figure 1 As shown, it specifically includes:

[0045] S101: In response to diagnostic commands, acquire the junction box's operational monitoring data and a pre-generated historical feature table.

[0046] Optionally, the operation monitoring data includes at least one of the following: string current, DC bus voltage, and total DC power of each photovoltaic string connected to the combiner box within a preset time period. The historical characteristic table includes the operation characteristics of the combiner box in multiple target time periods.

[0047] In this embodiment, the diagnostic command can be used to instruct the start of the diagnostic process. The diagnostic command can be triggered by the user clicking a preset button or control, or by a scheduled task reaching a preset time point, or by an abnormal alarm. This can enable on-demand diagnosis and avoid unnecessary resource consumption.

[0048] Optionally, there can be one or more combiner boxes, each of which connects to at least one photovoltaic string. The string current of each photovoltaic string can reflect the output current of each photovoltaic string. The DC bus voltage is the voltage of the DC bus in the combiner box. The total DC power can be the total power output by the combiner box. The duration of the preset time can be shorter than the duration of the target time period. The preset time can be a period of time before the current time. For example, the operation monitoring data within the preset time period can be the string current, DC bus voltage, and total DC power of each photovoltaic string within the last 30 minutes.

[0049] In this embodiment, the historical feature table may include the combiner box ID, combiner box identifier, string identifier, and operating features for each target time period. The operating features may include at least one of the following: string dispersion rate features, a first feature indicating whether there is shading, a second feature indicating the type of shading, a third feature indicating whether the string is inefficient, and output features (such as output current curve features and output power curve features). The shading type may be a shading time type, such as early shading type and late shading type.

[0050] Optionally, the target time period can be a time period in which the operating parameters meet the preset data quality conditions and the weather type is sunny.

[0051] In this embodiment, telemetry data may include total DC power, string current of each photovoltaic string, DC bus voltage, etc., while telemetry data may include the operating status of the combiner box.

[0052] Optionally, data quality conditions may include at least one of the following: the proportion of abnormal string currents in the operating parameters to the total number of photovoltaic strings is less than a proportion threshold, and the proportion of abnormal string currents in the operating parameters to the total number of photovoltaic strings is less than a quantity threshold.

[0053] In this embodiment, the target time period can be any time such as an hour, a day, or a week. This application does not limit the duration of the target time period.

[0054] S102: Diagnose each photovoltaic string based on the operation monitoring data and historical feature table to obtain the abnormal diagnosis results for each photovoltaic string.

[0055] In this embodiment, the anomaly diagnosis results can characterize whether there is an anomaly in the photovoltaic string and the type of anomaly.

[0056] Optionally, the exception types may include string output exceptions, string communication exceptions, and string environment exceptions.

[0057] In this embodiment, string output anomalies may include data dead values, data exceeding limits, abnormal shutdown, zero power, negative current, power limit, and zero current. String communication anomalies may include string interruption anomalies. String environment anomalies may include inconsistent orientation, partial period occlusion, and all-day occlusion or inefficiency.

[0058] The method provided in this application reduces reliance on manual inspections and lowers operation and maintenance costs through automated data acquisition and diagnostic processes. Furthermore, by combining real-time monitoring data with historical feature tables for anomaly diagnosis of photovoltaic strings, abnormal string conditions can be identified more accurately, improving the reliability and efficiency of diagnosis.

[0059] In some embodiments, each photovoltaic string can be diagnosed by analyzing the operation monitoring data according to preset anomaly identification rules, and the diagnosis result of each photovoltaic string can be obtained by combining the historical feature table. The anomaly identification rules can be generated based on the anomaly simulation results of various heterogeneous types.

[0060] Optionally, the photovoltaic strings in the combiner box can be placed under each anomaly type to obtain the anomaly simulation results for each anomaly type, and then anomaly identification rules can be generated based on the anomaly simulation results for each anomaly type.

[0061] For example, the process of simulating a data dead value anomaly is as follows: First, multiple combiner boxes are set to operate normally, ensuring all diagnostic conditions are met and no anomalies occur. Then, the DC bus voltage of one of the combiner boxes is set to a fixed value (e.g., 500V) and maintained in this state for more than 10 minutes. Finally, the user initiates diagnostics. If the DC bus voltage remains unchanged and non-zero for an extended period, it is determined to be a "data dead value" anomaly, and an alarm is marked on the target string. The user can click to view detailed information. Accordingly, the rule for identifying data dead values ​​can be set as follows: if the DC bus voltage data remains unchanged and non-zero within a set time, it is determined to be a data dead value. The target string is the photovoltaic string used for simulation.

[0062] Simulation process for data limit exceedance anomalies: Set the string current value of a combiner box to exceed a preset threshold (e.g., 35A), run for more than 10 minutes, and after diagnosis, mark the alarm result of this anomaly type on the target string. The corresponding anomaly identification rule is set as follows: the string current value exceeds the preset threshold and continues for a certain duration.

[0063] The simulation process for abnormal shutdown is as follows: The total DC power value of a certain combiner box is set to be greater than 10% of the maximum DC power in the 60-day historical data for at least 3 minutes at a certain point in time. Then, it is set to 0 for a running time exceeding 10 minutes. After the diagnosis, the alarm results for this abnormal type can be viewed. The corresponding anomaly identification rules are set as follows: The total DC power value is greater than 10% of the maximum DC power in the historical data at a certain point in time, and the duration exceeds at least a second duration, then it drops to 0 and continues for a third duration.

[0064] Simulation process for zero-power anomaly type: Set the total DC power value of a combiner box to 0 and run it continuously for more than 30 minutes. After the diagnosis is completed, the alarm results for this anomaly type can be viewed. The corresponding anomaly identification rule is set as follows: the total DC power value is 0, and there is no abnormal shutdown of the equipment, and this situation lasts for more than four hours.

[0065] Simulation process for negative current anomaly: Set some string current values ​​in a combiner box to negative values, run for more than 10 minutes, and view the alarm results for this anomaly type after diagnosis. The corresponding anomaly identification rule is set as follows: string current value is negative, and the duration exceeds five hours.

[0066] Simulation process for power limit anomaly type: Modify the DC bus voltage of the combiner box equipment to the same value, maintain it for at least 5 minutes with data fluctuation not exceeding 1%, and run for more than 5 minutes. After the diagnosis is completed, the alarm results for this anomaly type can be viewed. The corresponding anomaly identification rule is set as follows: the DC bus voltage remains at the same value within the sixth time period, and the data fluctuation does not exceed the set fluctuation range.

[0067] Simulation process for zero-current anomaly type: Set the string current of a combiner box to 0 and run continuously for more than 30 minutes. After the diagnosis is completed, the alarm results for this anomaly type can be viewed. The corresponding anomaly identification rule is set as follows: the string current value is 0, and the duration is at least seven hours.

[0068] Simulation process for string interruption anomaly: The string current of a combiner box is disconnected, and the operation time exceeds 10 minutes. When the current exceeds or equals 10% of a preset threshold (e.g., 35A) at a certain moment, it drops to 0. After the diagnosis is completed, the alarm result for this anomaly type can be viewed. The corresponding anomaly identification rule is set as follows: the string current exceeds or equals 10% of the preset current threshold (e.g., 35A) at a certain moment, then drops to 0 and remains at 0 for eight consecutive hours.

[0069] Simulation process for orientation inconsistency anomaly type: Set the photovoltaic panel orientation of the target string to be inconsistent with other strings, run for two days, and then perform a diagnosis. After the diagnosis is completed, the alarm results for this anomaly type can be viewed. The corresponding anomaly identification rule is set as follows: the current or power output of the string is lower than that of other strings, and the output difference between this string and other strings is greater than a first output difference threshold.

[0070] Simulation process for partial-time shading anomalies: The photovoltaic panels of the target string are shaded with black plastic sheeting for 30 minutes to 5 hours. This shading is repeated for the same time period on two consecutive sunny days. The alarm results for this anomaly type can be viewed after the diagnosis is completed on the third day. The corresponding anomaly identification rule is set as follows: the current or power output of string 1 is lower than that of other strings within a specific sub-time period, and the output difference between string 1 and other strings within this sub-time period is greater than a second output difference threshold.

[0071] Simulation process for full-day shading or inefficiency anomalies: The photovoltaic panels of the target string are shaded with black plastic sheeting for more than 6 hours, for two consecutive sunny days. After the diagnosis is completed on the third day, the alarm results for this anomaly type can be viewed. The corresponding anomaly identification rules are set as follows: the current or power output of the string is lower than that of other strings throughout the entire time period, and the output difference between this string and other strings during this time period is greater than a third output difference threshold.

[0072] In one embodiment provided in this application, based on the above-described scheme, optionally, the process of acquiring the combiner box's operational monitoring data and a pre-generated historical feature table, such as... Figure 2 As shown, it includes:

[0073] S201: Obtain the target status information of the junction box. The target status information includes at least one of the following: operating status information, environmental status information, and data acquisition status information.

[0074] In this embodiment, the operating status information can indicate whether the combiner box is online, the environmental status information can indicate whether the lighting is sufficient (such as whether the light intensity and irradiance meet the diagnostic requirements), and the data acquisition information can indicate whether the data required for diagnosis has been collected (such as real-time data within 30 minutes and valid operating data within the past two months).

[0075] S202: Determine whether the junction box meets the diagnostic conditions based on the target status information.

[0076] In this embodiment, it can be determined whether the combiner box meets the diagnostic conditions based on at least one of the following: operating status information, environmental status information, and data acquisition status information.

[0077] In this embodiment, the process of detecting whether the combiner box meets the diagnostic conditions based on the target status information includes:

[0078] If the operating status information indicates that the combiner box is online, the environmental status information indicates that there is sufficient light, and the data acquisition status information indicates that the data required for diagnosis has been collected, then the combiner box meets the diagnostic conditions.

[0079] If the operating status information indicates that the combiner box is offline, the environmental status information indicates insufficient lighting, or the data acquisition status information indicates that no data required for diagnosis has been collected, then the combiner box is determined not to meet the diagnostic conditions.

[0080] S203: If the junction box meets the diagnostic conditions, acquire the junction box's operation monitoring data and the pre-generated historical feature table.

[0081] By applying the method provided in the embodiments of this application, the diagnostic conditions are determined in advance, thus avoiding invalid diagnoses under conditions such as insufficient light, missing data, or offline devices, and ensuring the accuracy of the diagnostic results.

[0082] In some embodiments, diagnostic conditions include:

[0083] The combiner box is not currently in the initialization or automatic learning process;

[0084] At least some of the junction boxes are currently online and in operation;

[0085] The current illumination meets the minimum requirements for diagnosis, and the irradiance has reached the preset threshold.

[0086] The device has collected at least 30 minutes of real-time data.

[0087] The junction box contains valid data over the past two months.

[0088] Optionally, if the diagnostic conditions are met, the operation monitoring data of the combiner box and the pre-generated historical feature table are obtained, and each photovoltaic string is diagnosed based on the operation monitoring data and the historical feature table to obtain the abnormal diagnosis result.

[0089] Optionally, if the diagnostic criteria are not met, a corresponding prompt message will be output based on the specific criteria. The prompt message may include at least one of the following:

[0090] 1. Currently in the initialization or automatic learning process, diagnosis is not possible;

[0091] 2. All combiner boxes are currently offline and in a state of communication interruption, making intelligent diagnostics impossible;

[0092] 3. If the lighting does not meet the minimum diagnostic requirements within 30 minutes, only abnormalities caused by environmental factors such as string orientation and occlusion can be identified;

[0093] 4. The current irradiance is low, and the diagnostic results may contain errors. The results are for reference only.

[0094] 5. No valid data was available in the past two months, making it impossible to identify anomalies caused by environmental factors such as string orientation and obstruction;

[0095] 6. Currently, all or some of the online combiner boxes are not in operation, making intelligent diagnostics impossible;

[0096] 7. None of the devices have 30 minutes of real-time data, making intelligent diagnostics impossible.

[0097] In one embodiment provided in this application, the process of generating a historical feature table includes:

[0098] Obtain the operating parameters of the combiner box for each historical time period, including telemetry data and remote signaling data;

[0099] For each historical time period, the number of abnormal photovoltaic strings is determined based on the string current of each photovoltaic string in the telemetry data of that historical time period. If the proportion of the number of abnormal photovoltaic strings in that historical time period to the total number of photovoltaic strings is not greater than the proportion threshold, then that historical time period is determined as the target time period. The total number of photovoltaic strings is the total number of photovoltaic strings connected to the combiner box.

[0100] Feature extraction is performed on the operating parameters during the target time period to obtain the operating characteristics of the combiner box during the target time period;

[0101] Store the operational characteristics of the target time period into a preset data table to obtain a historical characteristic table.

[0102] In this embodiment, if the string current value of the photovoltaic string remains constant, the string current is negative, or the string current value exceeds the limit, it indicates that the photovoltaic string is an abnormal photovoltaic string and the string current data quality of the photovoltaic string is substandard.

[0103] Optionally, the operating parameters can be identified using anomaly identification rules to obtain the operating characteristics of the target time period.

[0104] In some embodiments, if the number of abnormal photovoltaic strings in the historical time period accounts for no more than a number threshold, the historical time period can also be determined as the target time period.

[0105] By applying the method provided in the embodiments of this application, a reliable data foundation is provided for the anomaly diagnosis and performance optimization of photovoltaic strings by screening high-quality historical operating parameters, extracting operating features and generating a historical feature table.

[0106] In one embodiment provided in this application, based on the above-described solution, optionally, the historical time period is determined as the target time period, including:

[0107] The weather type for a historical time period is determined based on the string current in the operating parameters of that period.

[0108] If the weather type for the historical time period is sunny, then the historical time period is determined as the target time period.

[0109] In this embodiment, if the difference between the maximum value of the string current and the rated current of the string is less than the difference threshold and the fluctuation range of the string current is within the preset range, then the weather type of the historical time period can be determined to be sunny.

[0110] By applying the method provided in the embodiments of this application, abnormal misjudgments caused by weather factors can be avoided, thereby improving the accuracy of diagnostic results.

[0111] In one embodiment provided in this application, based on the above-described scheme, optionally, each photovoltaic string is diagnosed according to operational monitoring data and a historical feature table to obtain anomaly diagnosis results for each photovoltaic string, including:

[0112] The output dispersion rate of each photovoltaic string is calculated based on the operation monitoring data.

[0113] Based on the preset anomaly identification rules, operation monitoring data, and historical feature table, the identification result of each photovoltaic string is obtained. The identification result indicates whether the photovoltaic string has experienced a preset type of anomaly.

[0114] Based on the output dispersion rate and identification results of each photovoltaic string, the abnormal diagnosis results of each photovoltaic string are obtained.

[0115] In this embodiment, the output dispersion rate may include at least one of the output current dispersion rate and the output power dispersion rate.

[0116] Optionally, after obtaining the output dispersion rate of each photovoltaic string, the dispersion rate level of the output dispersion rate of each photovoltaic string can be determined. The dispersion rate levels include the following:

[0117] If the string dispersion rate is within the range of 0% to 5%, it is in the first level, indicating that the strings under the combiner box are operating stably and the situation is excellent.

[0118] If the string dispersion rate is within the range of 5% to 10%, it is in the second level, indicating that the strings under this combiner box are operating well;

[0119] If the string dispersion rate is within the range of 10% to 20%, it is in the third level, indicating that the operation of each string under the combiner box needs to be improved.

[0120] If the string dispersion rate exceeds 20%, it is classified as Level 4, indicating that the operation of each string under the combiner box is poor, affecting the power generation of the power station, and rectification is required.

[0121] Optionally, the operation monitoring data can be identified through anomaly identification rules to obtain anomaly characteristics. Then, based on the anomaly characteristics, output dispersion rate, dispersion rate level, and operation characteristics in the historical characteristic table, anomaly diagnosis results for each photovoltaic string can be generated.

[0122] In this embodiment, each photovoltaic string is diagnosed by calculating the output dispersion rate, combining preset rules and historical feature tables, and generating detailed anomaly diagnosis results. This improves the accuracy, efficiency, and real-time performance of the diagnosis. It can be applied to the operation and maintenance, fault diagnosis, and performance optimization of photovoltaic power plants, significantly improving diagnostic efficiency and accuracy.

[0123] In one embodiment provided in this application, based on the above-described scheme, optionally, after obtaining the abnormal diagnosis results for each photovoltaic string, the method further includes:

[0124] For each photovoltaic string's abnormal diagnosis result, if the abnormal diagnosis result indicates that the photovoltaic string has an abnormality, then generate the cause of the fault and repair suggestion information for the photovoltaic string; output the abnormal diagnosis result, cause of the fault, and repair suggestion information for the photovoltaic string.

[0125] In this embodiment, the fault causes and repair suggestions corresponding to different anomaly types can be recorded in a preset configuration file. If the anomaly diagnosis result of the photovoltaic string indicates that the photovoltaic string has an anomaly, the configuration file can be queried according to the anomaly type to obtain the fault causes and repair suggestions corresponding to that anomaly type.

[0126] For example, if the anomaly type is "all-day obstruction," the suggested repair information would be to remove obstructions, etc.

[0127] The method provided in this application's embodiments helps maintenance personnel quickly locate and resolve problems by generating fault causes and repair suggestions, reducing fault handling time. Furthermore, new anomaly types and repair suggestions can be added according to actual needs, improving the system's adaptability.

[0128] See Figure 3 The flowchart provided in this application embodiment illustrates a process for identifying the causes of abnormalities in a photovoltaic string, specifically including the following steps:

[0129] Step 1: Collect historical data and equipment information tables. Historical data may include telemetry data such as total DC power, string current, and DC bus voltage. Equipment information tables may include telemetry data such as combiner box operating status, combiner box information, and equipment model.

[0130] Step 2: Clean the historical data collected in Step 1 and identify abnormal strings. Abnormal situations include strings with a continuous and constant current value, strings with a negative current value, and strings with a current value exceeding the limit.

[0131] Step 3: Calculate the proportion of data segments that do not meet the data quality standards; if the proportion is greater than the preset data quality threshold, the data quality of the array is determined to be poor for that day, and the algorithm calculation task for that day is skipped; if the proportion is not greater than the preset data quality threshold, proceed to Step 4.

[0132] Step 4: Perform data filling and smoothing on the string current values ​​within the start-stop range.

[0133] Step 5: Determine whether the day is a typical day (i.e., a period of time with sunny weather) based on the data for that day. If it is a typical day, proceed to step 6; otherwise, skip the algorithm calculation task for that day.

[0134] Step 6: Extract feature curves from the data for the day and store the curve features in the historical feature table.

[0135] Step 7: Collect data within 30 minutes in real time. After the user triggers the diagnosis, the diagnostic conditions are checked before the diagnosis to determine if the current conditions are met. If the diagnostic conditions are met, proceed to Step 8; otherwise, end the task.

[0136] Step 8: Read real-time data and historical feature tables.

[0137] Step 9: Calculate the dispersion rate using the dispersion rate calculation formula, and classify the dispersion rates into different levels.

[0138] Step 10: Based on the real-time data and historical feature table in Step 8, identify the cause of the string anomaly, and mark the alarm after the anomaly occurs, displaying the specific fault cause and repair suggestions.

[0139] and Figure 1 Corresponding to the method described herein, embodiments of this application also provide an anomaly diagnosis device for photovoltaic strings, used for... Figure 1 The specific implementation of the method is shown in the following structural diagram. Figure 4 As shown, it includes:

[0140] The acquisition unit 401 is used to acquire the operation monitoring data of the combiner box and the pre-generated historical feature table in response to the diagnostic command;

[0141] The diagnostic unit 402 is used to diagnose each photovoltaic string based on the operation monitoring data and the historical characteristic table, and obtain the abnormal diagnostic results of each photovoltaic string.

[0142] In one embodiment provided in this application, based on the above-described solution, optionally, the acquisition unit 401 includes:

[0143] The first acquisition subunit is used to acquire the target status information of the combiner box. The target status information includes at least one of the following: operating status information, environmental status information, and data acquisition status information.

[0144] The first determining subunit is used to determine whether the combiner box meets the diagnostic conditions based on the target status information.

[0145] The second acquisition subunit is used to acquire the operation monitoring data of the combiner box and a pre-generated historical feature table when the combiner box is detected to meet the diagnostic conditions. The operation monitoring data includes at least one of the string current, DC bus voltage and total DC power of each photovoltaic string connected to the combiner box within a preset time period. The historical feature table includes the operation characteristics of the combiner box in multiple target time periods.

[0146] In one embodiment provided in this application, based on the above-described solution, optionally, the first determining subunit includes:

[0147] The first determining module is used to determine that the junction box meets the diagnostic conditions if the operating status information indicates that the junction box is online, the environmental status information indicates that the lighting is sufficient, and the data acquisition status information indicates that the data required for diagnosis has been acquired.

[0148] The second determining module is used to determine that the junction box does not meet the diagnostic conditions if the operating status information indicates that the junction box is offline, the environmental status information indicates insufficient lighting, or the data acquisition status information indicates that no data required for diagnosis has been acquired.

[0149] In one embodiment provided in this application, based on the above-described solution, optionally, the acquisition unit 401 includes:

[0150] The third acquisition subunit is used to acquire the operating parameters of the combiner box for each historical time period. The operating parameters include telemetry data and remote signaling data.

[0151] The second determining subunit is used to determine the number of abnormal photovoltaic strings based on the string current of each photovoltaic string in the telemetry data of each historical time period. If the proportion of the number of abnormal photovoltaic strings in the historical time period to the total number of photovoltaic strings is not greater than the proportion threshold, then the historical time period is determined as the target time period.

[0152] The feature extraction subunit is used to extract features from the operating parameters in the target time period to obtain the operating features of the combiner box in the target time period.

[0153] The first execution subunit is used to store the operational characteristics of the target time period into a preset data table to obtain a historical characteristic table.

[0154] In one embodiment provided in this application, based on the above-described solution, optionally, the second determining subunit includes:

[0155] The third determination module is used to determine the weather type for a historical time period based on the string current in the operating parameters of the historical time period.

[0156] The fourth determination module is used to determine the historical time period as the target time period if the weather type of the historical time period is sunny.

[0157] In one embodiment provided in this application, based on the above-described solution, optionally, the diagnostic unit 402 includes:

[0158] The calculation subunit is used to calculate the output dispersion rate of each photovoltaic string based on the operation monitoring data.

[0159] The identification subunit is used to obtain the identification result of each photovoltaic string based on the preset anomaly identification rules, operation monitoring data and historical feature table. The identification result indicates whether the photovoltaic string has experienced a preset type of anomaly.

[0160] The second execution subunit is used to obtain the abnormal diagnosis result of each photovoltaic string based on the output dispersion rate of each photovoltaic string and the identification result.

[0161] In one embodiment provided in this application, based on the above-described solution, optionally, it further includes:

[0162] The output unit is used for the abnormal diagnosis results of each photovoltaic string. If the abnormal diagnosis results of the photovoltaic string indicate that the photovoltaic string has an abnormality, it generates the fault cause and repair suggestion information of the photovoltaic string; and outputs the abnormal diagnosis results, fault cause and repair suggestion information of the photovoltaic string.

[0163] This application embodiment also provides a storage medium, which includes stored instructions, wherein, when the instructions are executed, the device where the storage medium is located executes the above-described photovoltaic string anomaly diagnosis method.

[0164] This application also provides an electronic device, the structural schematic diagram of which is shown below. Figure 5 As shown, it specifically includes a memory 501 and one or more instructions 502, wherein one or more instructions 502 are stored in the memory 501 and are configured to be executed by one or more processors 503 to perform the above-mentioned abnormal diagnosis method for photovoltaic strings.

[0165] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0166] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0167] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0168] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0169] The above provides a detailed description of an abnormality diagnosis method for photovoltaic strings provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for diagnosing anomalies in photovoltaic strings, characterized in that, include: In response to diagnostic commands, acquire the junction box's operational monitoring data and a pre-generated historical feature table; Based on the operational monitoring data and historical feature table, each photovoltaic string is diagnosed to obtain anomaly diagnosis results for each photovoltaic string.

2. The method according to claim 1, characterized in that, The acquisition of the combiner box's operational monitoring data and the pre-generated historical feature table includes: Obtain the target status information of the combiner box, wherein the target status information includes at least one of the following: operating status information, environmental status information, and data acquisition status information; Determine whether the junction box meets the diagnostic conditions based on the target status information; If the combiner box is found to meet the diagnostic conditions, the operation monitoring data of the combiner box and a pre-generated historical feature table are obtained. The operation monitoring data includes at least one of the string current, DC bus voltage and total DC power of each photovoltaic string connected to the combiner box within a preset time period. The historical feature table includes the operation characteristics of the combiner box in multiple target time periods.

3. The method according to claim 2, characterized in that, The step of detecting whether the combiner box meets the diagnostic conditions based on the target status information includes: If the operating status information indicates that the junction box is online, the environmental status information indicates that there is sufficient light, and the data acquisition status information indicates that the data required for diagnosis has been acquired, then the junction box is determined to meet the diagnostic conditions. If the operating status information indicates that the combiner box is offline, the environmental status information indicates insufficient lighting, or the data acquisition status information indicates that no data required for diagnosis has been collected, then it is determined that the combiner box does not meet the diagnostic conditions.

4. The method according to claim 1, characterized in that, The process of generating the historical feature table includes: The operating parameters of the combiner box for each historical time period are obtained, and the operating parameters include telemetry data and remote signaling data; For each historical time period, the number of abnormal photovoltaic strings is determined based on the string current of each photovoltaic string in the telemetry data of the historical time period. If the proportion of the number of abnormal photovoltaic strings in the historical time period to the total number of photovoltaic strings is not greater than the proportion threshold, then the historical time period is determined as the target time period. Feature extraction is performed on the operating parameters during the target time period to obtain the operating characteristics of the combiner box during the target time period; The operational characteristics of the target time period are stored in a preset data table to obtain a historical characteristic table.

5. The method according to claim 4, characterized in that, The step of determining the historical time period as the target time period includes: The weather type for the historical time period is determined based on the string current in the operating parameters of the historical time period. If the weather type of the historical time period is sunny, then the historical time period is determined as the target time period.

6. The method according to claim 1, characterized in that, Based on the operational monitoring data and historical feature table, each photovoltaic string is diagnosed to obtain anomaly diagnosis results for each photovoltaic string, including: The output dispersion rate of each photovoltaic string is calculated based on the operation monitoring data. Based on the preset anomaly identification rules, the operation monitoring data, and the historical feature table, the identification result of each photovoltaic string is obtained, and the identification result indicates whether the photovoltaic string has experienced a preset type of anomaly. Based on the output dispersion rate of each photovoltaic string and the identification result, the abnormal diagnosis result of each photovoltaic string is obtained.

7. The method according to any one of claims 1 to 6, characterized in that, After obtaining the abnormal diagnosis result for each of the photovoltaic strings, the method further includes: For each photovoltaic string, if the abnormal diagnosis result indicates that the photovoltaic string is abnormal, then the fault cause and repair suggestion information of the photovoltaic string are generated; the abnormal diagnosis result, fault cause and repair suggestion information of the photovoltaic string are output.

8. A device for diagnosing abnormalities in photovoltaic strings, characterized in that, include: The acquisition unit is used to acquire the operation monitoring data of the combiner box and the pre-generated historical feature table in response to diagnostic commands; The diagnostic unit is used to diagnose each photovoltaic string based on the operation monitoring data and the historical feature table, and to obtain the abnormal diagnostic results of each photovoltaic string.

9. A storage medium, characterized in that, The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the abnormal diagnosis method for photovoltaic strings as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1 to 7, for the abnormal diagnosis method of photovoltaic strings.

Images