Method and device for diagnosing failure of bypass diode

Abstract

The application discloses a bypass diode fault diagnosis method and device, and belongs to the technical field of photovoltaic system fault identification. The bypass diode fault diagnosis method comprises the following steps: obtaining target electric data of a target branch in a target period; in the case that the MPPT voltage of a diagnosis group string in the target branch is abnormal, determining a voltage rise mutation point and first electric data corresponding to the voltage rise mutation point based on the target electric data; and determining a fault group string based on the first electric data. The bypass diode fault diagnosis method can diagnose the fault of the bypass diode in real time, has high real-time performance and high efficiency, does not need to install additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

Description

Technical Field

[0001] This application belongs to the field of photovoltaic system fault identification technology, and in particular relates to a fault diagnosis method and device for a bypass diode. Background Technology

[0002] Short circuits in bypass diodes are one of the most common faults in electrical components. These faults are difficult for maintenance personnel to detect and can easily lead to significant power generation losses. Common methods for diagnosing bypass diode faults include infrared thermal imaging and IV curve scanning, but both methods require specific equipment and instruments for detection, resulting in high testing costs. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a fault diagnosis method and apparatus for bypass diodes, which can diagnose faults of bypass diodes in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not rely on specific equipment and instruments, has low detection costs, and is convenient and easy to implement.

[0004] In a first aspect, this application provides a fault diagnosis method for a bypass diode, the method comprising:

[0005] Acquire the target electrical data of the target branch within the target time period;

[0006] In the event of an abnormal MPPT voltage in the diagnostic string within the target branch, a boost inflection point and a first electrical data point corresponding to the boost inflection point are determined based on the target electrical data; the first electrical data point is the current data corresponding to the boost inflection point.

[0007] Based on the first electrical data, a fault string is identified, and the bypass diode corresponding to the fault string is faulty.

[0008] The step of determining the fault string based on the first electrical data includes:

[0009] Based on the first electrical data, a first branch is determined, which is the branch where the current change at the boost abrupt point exceeds the current threshold.

[0010] A benchmark string is determined based on the first current value of the first branch. The benchmark string is a normally functioning string, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch.

[0011] If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the fault string.

[0012] According to the bypass diode fault diagnosis method provided in the embodiments of this application, by acquiring the target electrical data of the target branch within the target time period, in the case of MPPT voltage abnormality, the boost voltage change point and the first electrical data corresponding to the boost voltage change point are determined based on the target electrical data, and then the fault string is determined based on the first electrical data. It can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0013] A method for diagnosing the fault of a bypass diode according to an embodiment of this application, wherein determining the fault string based on the first electrical data includes:

[0014] Based on the first electrical data, determine the voltage rise amplitude corresponding to the voltage jump point;

[0015] If the number of boost abrupt change points corresponding to the voltage rise amplitude greater than the voltage rise threshold exceeds the number threshold, based on the first electrical data, determine the first branch whose current change corresponding to the boost abrupt change point exceeds the current threshold.

[0016] Based on the first current value of the first branch, the benchmark string is determined;

[0017] If the diagnostic branch meets the target conditions, the location of the voltage surge point is determined to be below the benchmark string and at a target distance. The diagnostic string is then identified as the fault string. The target conditions refer to the current drop in the diagnostic branch in the target branch being greater than the current drop in the benchmark string.

[0018] According to an embodiment of the bypass diode fault diagnosis method of this application, a first branch is determined by first electrical data, and a benchmark string is determined based on the first current value of the first branch. Then, when the diagnostic branch meets the target conditions, it is determined that the position of the boost abrupt change point is below the benchmark string and reaches the target distance, and the diagnostic string is determined as the fault string. The fault string can be determined based on the current characteristics at the boost abrupt change point. The diagnosis method is convenient and easy to implement.

[0019] A method for fault diagnosis of a bypass diode according to an embodiment of this application, wherein determining the location of the boost abrupt change point is below the benchmark string and reaches a target distance, and identifying the diagnostic string as the fault string, includes:

[0020] Obtain the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch;

[0021] If the difference between the second current value and the third current value is less than the second threshold, and the second current value is less than the second current value of the target proportion, the diagnostic string is determined to be the fault string.

[0022] According to an embodiment of the bypass diode fault diagnosis method of this application, by obtaining the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch, and then when the difference between the second current value and the third current value is less than a second threshold and the second current value is less than the second current value of the target ratio, it can be determined that the position of the boost sudden change point of the diagnostic string is below the benchmark string and reaches the target distance, thereby identifying the diagnostic string as a fault string. The fault string can be determined based on the current characteristics at the boost sudden change point. The diagnosis method is convenient and easy to implement, further improving the accuracy of fault diagnosis.

[0023] One embodiment of the bypass diode fault diagnosis method of this application, wherein determining the benchmark string based on the first current value of the first branch includes:

[0024] Based on the first-order difference value of the first current value, obtain the difference value corresponding to all branches;

[0025] The string in the branch corresponding to the smallest difference value is determined as the benchmark string.

[0026] According to an embodiment of the bypass diode fault diagnosis method of this application, based on the first-order differential value of the first current value, the differential values ​​corresponding to all branches are obtained, and then the string in the branch corresponding to the smallest differential value is determined as the benchmark string. It is possible to obtain the normally functioning string based on the differential value, which facilitates the judgment of the faulty string based on the differential value of the benchmark string in subsequent applications, thereby improving the accuracy of fault detection.

[0027] In one embodiment of the bypass diode fault diagnosis method of this application, before determining the boost voltage inflection point and the first current value corresponding to the boost voltage inflection point based on the target electrical data in the event of an abnormal MPPT voltage, the method further includes:

[0028] Based on the target electrical data, a target threshold is determined, which is used to identify sudden inefficiencies;

[0029] The theoretical MPPT voltage is determined based on the string's basic and environmental parameters.

[0030] Based on the theoretical MPPT voltage and the actual MPPT voltage, determine whether the MPPT voltage is abnormal.

[0031] According to an embodiment of the bypass diode fault diagnosis method of this application, a target threshold is determined based on target electrical data, and then the theoretical MPPT voltage is determined based on the basic parameters and environmental parameters of the string. Then, based on the theoretical MPPT voltage and the actual MPPT voltage, it is determined whether the MPPT voltage is abnormal, so as to facilitate the identification of faulty strings based on the abnormal MPPT voltage in subsequent applications.

[0032] One embodiment of the bypass diode fault diagnosis method of this application, wherein the theoretical MPPT voltage is determined based on the basic parameters and environmental parameters of the string, includes:

[0033] The basic parameters and environmental parameters are input into the MPPT voltage anomaly diagnostic model to obtain the theoretical MPPT voltage output by the MPPT voltage anomaly diagnostic model, wherein...

[0034] The MPPT voltage anomaly diagnostic model is trained using basic sample parameters and environmental sample parameters as samples, and using the theoretical MPPT voltage corresponding to the basic sample parameters and environmental sample parameters as sample labels.

[0035] According to an embodiment of the bypass diode fault diagnosis method of this application, the basic parameters and environmental parameters of the string are input into a pre-trained MPPT voltage anomaly diagnosis model to obtain the theoretical MPPT voltage. In practical applications, only pre-training is required before use, and then the data can be directly obtained. The calculation efficiency is high and the accuracy is good. Moreover, the MPPT voltage anomaly diagnosis model has strong learning ability. The data in each application process can be used as training data in the next training process, thereby improving the accuracy and precision of the model, making it easier for users to use, and improving the accuracy of the final fault diagnosis.

[0036] A fault diagnosis method for a bypass diode according to an embodiment of this application, wherein determining a target threshold based on the target electrical data includes:

[0037] The target electrical data is preprocessed based on at least one of communication dead value, interruption and over-limit value to obtain second electrical data;

[0038] The target threshold is determined based on the second electrical data.

[0039] According to an embodiment of the bypass diode fault diagnosis method of this application, by preprocessing the target electrical data based on at least one of communication dead value, interruption and over-limit value, noise data can be filtered out to obtain second electrical data. Then, based on the second electrical data, the target threshold is determined, which improves the accuracy of the determined target threshold and facilitates the judgment of sudden inefficiency based on the target threshold in the subsequent execution process, thereby improving the accuracy of the final fault diagnosis.

[0040] A bypass diode fault diagnosis method according to an embodiment of this application, after determining the fault string based on the first electrical data, the method further includes:

[0041] The fault sequence is processed using the closed-loop work order processing results;

[0042] Update the sudden inefficient state to a normal state.

[0043] According to an embodiment of the bypass diode fault diagnosis method of this application, the faulty string is processed using the closed-loop work order processing result, and then the sudden inefficient state is updated to the normal state, forming a processing closed loop. It can use historical diagnostic data for fault processing, thereby improving the accuracy and efficiency of fault diagnosis.

[0044] Secondly, this application provides a fault diagnosis device for a bypass diode, the device comprising:

[0045] The first processing module is used to acquire the target electrical data of the target branch within the target time period;

[0046] The second processing module is used to determine, based on the target electrical data, a boost voltage inversion point and the first electrical data corresponding to the boost voltage inversion point when the MPPT voltage of the diagnostic string in the target branch is abnormal; the first electrical data is the current data corresponding to the boost voltage inversion point.

[0047] The third processing module is used to determine the fault string based on the first electrical data, wherein the bypass diode corresponding to the fault string is faulty.

[0048] The third processing module is used for:

[0049] Based on the first electrical data, a first branch is determined, which is the branch where the current change at the boost abrupt point exceeds the current threshold.

[0050] A benchmark string is determined based on the first current value of the first branch. The benchmark string is a normally functioning string, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch.

[0051] If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the fault string.

[0052] The bypass diode fault diagnosis device provided in the embodiments of this application acquires the target electrical data of the target branch within the target time period. In the case of MPPT voltage abnormality, it determines the boost voltage change point and the first electrical data corresponding to the boost voltage change point based on the target electrical data. Then, based on the first electrical data, it determines the fault string. It can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0053] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the bypass diode fault diagnosis method as described in the first aspect above.

[0054] The above-described one or more technical solutions in the embodiments of this application have at least one of the following technical effects:

[0055] By acquiring the target electrical data of the target branch within the target time period, in the case of MPPT voltage abnormality, the boost abrupt change point and the first electrical data corresponding to the boost abrupt change point are determined based on the target electrical data. Then, based on the first electrical data, the fault string is determined. It can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0056] Furthermore, the first branch is determined by the first electrical data, and the benchmark string is determined based on the first current value of the first branch. Then, if the diagnostic branch meets the target conditions, the location of the boost abrupt change point is determined to be below the benchmark string and reaches the target distance. The diagnostic string is then identified as the fault string. The fault string can be determined based on the current characteristics at the boost abrupt change point. The diagnostic method is convenient and easy to implement.

[0057] Furthermore, by obtaining the second current value after the sudden change in the benchmark string and the third current value after the sudden change in the diagnostic string corresponding to the diagnostic branch, and then, if the difference between the second current value and the third current value is less than the second threshold and the second current value is less than the target proportion of the second current value, it can be determined that the position of the boost change point of the diagnostic string is below the benchmark string and reaches the target distance. Thus, the diagnostic string is identified as the fault string. The fault string can be determined based on the current characteristics at the boost change point. The diagnostic method is convenient and easy to implement, further improving the accuracy of fault diagnosis.

[0058] Furthermore, by inputting the basic parameters and environmental parameters of the string into the pre-trained MPPT voltage anomaly diagnosis model, the theoretical MPPT voltage can be obtained. In practical applications, pre-training is only required before use, and then data can be directly obtained, resulting in high computational efficiency and accuracy. Moreover, the MPPT voltage anomaly diagnosis model has strong learning capabilities, and the data from each application process can be used as training data for the next training process, thereby improving the model's precision and accuracy, making it easier for users to use, and improving the accuracy of the final fault diagnosis.

[0059] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0060] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0061] Figure 1 This is one of the flowcharts illustrating the fault diagnosis method for bypass diodes provided in the embodiments of this application;

[0062] Figure 2 This is a second schematic flowchart of the bypass diode fault diagnosis method provided in the embodiments of this application;

[0063] Figure 3 This is one of the schematic diagrams illustrating the principle of the bypass diode fault diagnosis method provided in the embodiments of this application;

[0064] Figure 4 This is the third flowchart illustrating the fault diagnosis method for bypass diodes provided in this application embodiment;

[0065] Figure 5 This is a schematic diagram of the structure of the bypass diode fault diagnosis device provided in the embodiments of this application;

[0066] Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0067] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0068] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0069] The following is combined Figures 1 to 4 This application describes a method for diagnosing faults in bypass diodes according to embodiments of the present application.

[0070] It should be noted that the entity executing the fault diagnosis method for the bypass diode can be a server, a fault diagnosis device for the bypass diode, or a user's terminal, including but not limited to mobile terminals and non-mobile terminals.

[0071] For example, mobile terminals include, but are not limited to, mobile phones, PDA smart terminals, tablets, and in-vehicle smart terminals; non-mobile terminals include, but are not limited to, PCs.

[0072] like Figure 1 As shown, the fault diagnosis method for the bypass diode includes steps 110, 120 and 130.

[0073] Step 110: Obtain the target electrical data of the target branch within the target time period;

[0074] In this step, the target branch is at least a portion of the branches of a single device, for example, it can be all branches.

[0075] Individual devices can be inverters or combiner boxes, etc.

[0076] The target time period can be any time period, such as 8:00-14:00, 9:00-15:00, or 10:00-16:00, etc., and can be user-defined. This application does not impose any restrictions on it.

[0077] The target electrical data can be represented as time-series data, and may include at least one of string current and DC bus voltage.

[0078] In actual operation, the string current and DC bus voltage of the target branch under a single device can be obtained at a 5-minute resolution during the period from 9:00 to 15:00.

[0079] Step 120: In the event of an abnormal MPPT voltage in the diagnostic string within the target branch, determine the boost abrupt change point and the first electrical data corresponding to the boost abrupt change point based on the target electrical data.

[0080] In this step, MPPT (Maximum Power Point Tracking) refers to maximum power point tracking, the MPPT voltage is the voltage corresponding to the maximum power point of the diagnostic string, and the diagnostic string is the string within the target branch.

[0081] The voltage surge point is the point at which the DC bus voltage corresponding to the combiner box experiences a sudden increase.

[0082] The first electrical data is the current data corresponding to the voltage boost abrupt change point.

[0083] In actual execution, the target electrical data of the target branch under a single device within the target time period can be obtained. The maximum value of the DC bus voltage in the target electrical data is normalized, and then first-order differential is performed to obtain the boost change point. Under the condition of MPPT voltage abnormality, the DC bus voltage of the combiner box will show an upward trend and maintain a high voltage level during the power restriction time period.

[0084] In some embodiments, prior to step 120, the fault diagnosis method for the bypass diode may include:

[0085] Based on the target electrical data, a target threshold is determined, which is used to identify sudden inefficiencies.

[0086] The theoretical MPPT voltage is determined based on the string's basic and environmental parameters.

[0087] Based on the theoretical MPPT voltage and the actual MPPT voltage, determine whether the MPPT voltage is abnormal.

[0088] In this embodiment, the target threshold may include at least one of the following: a threshold for the number of boost abrupt change points, a threshold for the voltage rise of boost abrupt change points, a ratio of the current downward deviation, the current value of the current downward deviation, the difference in current values ​​after the current downward deviation, and the ratio of current values ​​after the current downward deviation.

[0089] Sudden inefficiency occurs when a string is in an abnormal operating state. For example, sudden inefficiency can manifest as a short circuit in the string.

[0090] The target threshold is used to determine whether a diagnostic string is a sudden, inefficient string.

[0091] The target threshold can be obtained through statistical analysis of the data, or it can be customized based on the actual situation; this application does not impose any restrictions.

[0092] For example, the threshold for the number of boost inflection points can be set as follows: ,For example, It can be 3, 4, or 5, etc.;

[0093] Set the voltage rise threshold at the boost abrupt point to: ,For example, It can be 0.03, 0.04, or 0.05, etc.;

[0094] Set the downward deviation ratio of the current to ,For example, It can be 1.1, 1.2, or 1.3, etc.;

[0095] Set the current downward deviation magnitude current value to ,For example, It can be 0.2, 0.3, or 0.4, etc.;

[0096] The difference in current values ​​after the current deviates downward by a certain amount is set as... ,For example, It can be -0.2, -0.3, or -0.4, etc.;

[0097] Set the ratio of the current value after the current deviates downward by the magnitude to... ,For example, It can be 0.97, 0.98, or 0.99, etc.

[0098] In some embodiments, determining a target threshold based on target electrical data may include:

[0099] Preprocess the target electrical data based on at least one of communication dead value, interruption and over-limit value to obtain the second electrical data;

[0100] The target threshold is determined based on the second electrical data.

[0101] In this embodiment, the target electrical data may include at least one type of noise data, such as communication dead value, interruption, and over-limit value.

[0102] Preprocessing the target electrical data may include at least one of the following: filtering strings of all zero values, filtering strings of continuous half-hour constant values, filtering strings of values ​​exceeding limits, and filtering strings of disconnected data.

[0103] The second electrical data is obtained after preprocessing the target electrical data.

[0104] In actual execution, the number of daily current sampling points in the target electrical data acquired within the target time period is 72, and the number of daily current sampling points in the second electrical data corresponding to the preprocessed string needs to be greater than 63.

[0105] Based on the second electrical data and sample statistical analysis, the target threshold was determined.

[0106] According to the bypass diode fault diagnosis method provided in the embodiments of this application, by preprocessing the target electrical data based on at least one of communication dead value, interruption and over-limit value, noise data can be filtered out to obtain second electrical data. Then, based on the second electrical data, the target threshold is determined, which improves the accuracy of the determined target threshold and facilitates the judgment of sudden inefficiency based on the target threshold in the subsequent execution process, thereby improving the accuracy of the final fault diagnosis.

[0107] The basic parameters of a string may include at least one of the string temperature, string voltage temperature coefficient, and string nameplate maximum power point voltage.

[0108] Environmental parameters may include at least one of irradiance, air temperature, and wind speed.

[0109] In some embodiments, determining the theoretical MPPT voltage based on the string's basic parameters and environmental parameters may include:

[0110] Input the basic parameters and environmental parameters into the MPPT voltage anomaly diagnosis model to obtain the theoretical MPPT voltage output by the MPPT voltage anomaly diagnosis model.

[0111] In this embodiment, the MPPT voltage anomaly diagnostic model is a pre-trained model, which is trained using sample basic parameters and sample environment parameters as samples, and sample theoretical MPPT voltages corresponding to the sample basic parameters and sample environment parameters as sample labels.

[0112] In actual implementation, the basic parameters and environmental parameters of the string are input into the MPPT voltage anomaly diagnosis model, and the theoretical MPPT voltage can be calculated in real time.

[0113] According to the fault diagnosis method for bypass diodes provided in this application, the basic parameters and environmental parameters of the string are input into a pre-trained MPPT voltage anomaly diagnosis model to obtain the theoretical MPPT voltage. In practical applications, pre-training is only required before use, and then the data can be directly obtained. The calculation efficiency is high and the accuracy is good. Furthermore, the MPPT voltage anomaly diagnosis model has strong learning ability. The data from each application process can be used as training data for the next training process, thereby improving the accuracy and precision of the model, making it easier for users to use, and improving the accuracy of the final fault diagnosis.

[0114] The actual MPPT voltage is obtained, and the magnitude of the theoretical MPPT voltage and the actual MPPT voltage are compared. If the difference between the theoretical MPPT voltage and the actual MPPT voltage is greater than a preset threshold, the MPPT voltage is determined to be abnormal. The preset threshold can be customized based on actual needs, and this application does not limit it.

[0115] According to the bypass diode fault diagnosis method provided in the embodiments of this application, a target threshold is determined based on the target electrical data, and then the theoretical MPPT voltage is determined based on the basic parameters and environmental parameters of the string. Then, based on the theoretical MPPT voltage and the actual MPPT voltage, it is determined whether the MPPT voltage is abnormal, so as to facilitate the identification of faulty strings based on the abnormal MPPT voltage in subsequent applications.

[0116] Step 130: Based on the first electrical data, determine the faulty string.

[0117] In this step, the first electrical data is the current data corresponding to the voltage boost abrupt change point.

[0118] Faulty strings are strings that suddenly become inefficient.

[0119] In some embodiments, step 130 further includes:

[0120] Based on the first electrical data, the first branch is determined. The first branch is the branch where the current change exceeds the current threshold corresponding to the voltage boost abrupt change point.

[0121] The benchmark string is determined based on the first current value of the first branch. The benchmark string is the string that is working normally, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch.

[0122] If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the faulty string.

[0123] During the research and development process, the inventors discovered that in related technologies, outliers in the high-segment current curves and non-high-segment current curves of each branch are used to determine whether the string bypass diodes corresponding to the branch are faulty. However, the implementation of this method is cumbersome and not easy for users to learn.

[0124] This application first acquires the target electrical data of the target branch within the target time period. In the case of MPPT voltage abnormality, it determines the boost voltage change point and the first electrical data corresponding to the boost voltage change point based on the target electrical data. Then, based on the first electrical data, it determines the fault string. The fault diagnosis method of this application can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. It does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0125] According to the bypass diode fault diagnosis method provided in the embodiments of this application, by acquiring the target electrical data of the target branch within the target time period, in the case of MPPT voltage abnormality, the boost voltage change point and the first electrical data corresponding to the boost voltage change point are determined based on the target electrical data, and then the fault string is determined based on the first electrical data. It can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0126] In some embodiments, step 130 may include:

[0127] Based on the first electrical data, determine the voltage rise amplitude corresponding to the voltage jump point;

[0128] If the number of boost abrupt points corresponding to voltage rise amplitudes greater than the voltage rise threshold exceeds the number threshold, based on the first electrical data, determine the first branch whose current change exceeds the current threshold corresponding to the boost abrupt point.

[0129] Based on the first current value of the first branch, determine the benchmark string;

[0130] If the diagnostic branch meets the target conditions, the location of the voltage surge point is determined to be below the benchmark string and at the target distance. The diagnostic string is then identified as the fault string. The target condition refers to the current drop in the diagnostic branch in the target branch being greater than the current drop in the benchmark string.

[0131] In this embodiment, the voltage rise is the rise of the DC bus voltage of the combiner box when the MPPT voltage is abnormal.

[0132] The voltage rise threshold is used to determine whether the voltage rise amplitude meets the requirements. The voltage rise threshold can be 0.03, 0.04 or 0.05, and can be user-defined. This application does not limit it.

[0133] The quantity threshold is used to determine whether the number of boost inflection points meets the requirements. The quantity threshold can be 3, 4 or 5, and can be user-defined. This application does not limit it.

[0134] The current threshold is used to determine whether the current change corresponding to the voltage boost abrupt change point meets the requirements.

[0135] The first branch is the branch where the current change at the voltage boost abrupt change point exceeds the current threshold.

[0136] In actual implementation, such as Figure 2 As shown, the voltage rise threshold can be set to... Set the quantity threshold as During the voltage rise satisfy:

[0137]

[0138] And the number of voltage rise abrupt change points corresponding to the voltage rise magnitude satisfy:

[0139]

[0140] In this case, determine the first branch, in which, The voltage rise rate This is the voltage rise threshold. The number of boost inflection points, This is the quantity threshold.

[0141] The first current value is the current value corresponding to the first branch.

[0142] The benchmark string is determined based on the first current value of the first branch and is a string that is operating normally.

[0143] In some embodiments, determining the benchmark string based on the first current value of the first branch may include:

[0144] Based on the first-order difference value of the first current value, obtain the difference value corresponding to all branches;

[0145] The string in the branch corresponding to the smallest difference value is determined as the benchmark string.

[0146] In this embodiment, the first-order differential value is obtained based on the first current value of the first branch.

[0147] The benchmark string is the string that is working normally, and the difference value corresponding to the benchmark string is the smallest difference value among all branches.

[0148] In actual implementation, we can first identify the first branch where the current change exceeds the current threshold at the boost abrupt change point, then obtain the first current value corresponding to the first branch. Based on the first-order difference value of the first current value, we then obtain the difference values ​​corresponding to all branches. Finally, we identify the branch with the smallest difference value among all branches and define the string within that branch as the benchmark string. The difference value of the benchmark string can be represented as... .

[0149] According to the fault diagnosis method for bypass diodes provided in the embodiments of this application, based on the first-order differential value of the first current value, the differential values ​​corresponding to all branches are obtained. Then, the string in the branch corresponding to the smallest differential value is determined as the benchmark string. It is possible to obtain the normally functioning string based on the differential value, which facilitates the judgment of the faulty string based on the differential value of the benchmark string in subsequent applications, thereby improving the accuracy of fault detection.

[0150] Target conditions can be user-defined; in this application, for example... Figure 2 As shown, the differential value of the diagnostic branch can be expressed as... ,exist satisfy:

[0151]

[0152] And it satisfies:

[0153]

[0154] In this case, if the location of the voltage boost abrupt change point is determined to be below the benchmark string and within the target distance, the diagnostic string is identified as the faulty string. This is the ratio of the downward deviation of the current. The downward deviation of the current from the rated current value. To diagnose the differential values ​​of the branches, The difference value of the benchmark string. and Customization is possible based on actual circumstances; this application does not impose any limitations.

[0155] The target distance can be customized based on actual needs.

[0156] In the event of an MPPT voltage anomaly, the DC bus voltage of the combiner box will show an upward trend and maintain a high voltage level during the power outage period, such as... Figure 3 As shown, when the DC bus voltage above is rising and maintaining a high voltage level, the currents corresponding to the diagnostic string and the benchmark string will deviate downwards to different degrees. Moreover, the current drop of the diagnostic string at the voltage surge point is greater than the current drop of the benchmark string. The target distance can be determined based on the difference between the current values ​​of the diagnostic string and the benchmark string at the corresponding time points.

[0157] In some embodiments, determining that the location of the boost abrupt change point is below the benchmark string and reaches a target distance, and identifying the diagnostic string as the fault string, may include:

[0158] Obtain the second current value after the sudden change in the benchmark string and the third current value after the sudden change in the diagnostic string corresponding to the diagnostic branch;

[0159] If the difference between the second current value and the third current value is less than the second threshold, and the second current value is less than the second current value of the target proportion, the diagnostic string is identified as a fault string.

[0160] In this embodiment, the second current value is the current value corresponding to the sudden change in the benchmark string.

[0161] The third current value is the current value corresponding to the diagnostic string mutation.

[0162] The second threshold is used to determine whether the difference between the values ​​of the second current value and the third current value meets the preset conditions.

[0163] The target ratio is used to determine whether the ratio of the second current value to the third current value meets the preset conditions.

[0164] A fault string is a string that is not functioning normally; for example, a fault string could be a string that experiences a sudden inefficiency.

[0165] In actual implementation, such as Figure 2 As shown, the second current value is expressed as The third current value is expressed as ,exist and satisfy:

[0166]

[0167] And it satisfies:

[0168]

[0169] In this case, the diagnostic string is identified as the fault string, where, This is the current value after the current deviates downward by the magnitude. This is the ratio of the current values ​​after the current deviates downward by a certain amount. This is the second current value. This is the third current value. and Customization is possible based on actual circumstances; this application does not impose any limitations.

[0170] According to the fault diagnosis method for bypass diodes provided in this application, by obtaining the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch, and then when the difference between the second current value and the third current value is less than a second threshold and the second current value is less than the second current value of the target ratio, it can be determined that the position of the boost sudden change point of the diagnostic string is below the benchmark string and reaches the target distance, thereby identifying the diagnostic string as a fault string. The fault string can be determined based on the current characteristics at the boost sudden change point. The diagnosis method is convenient and easy to implement, further improving the accuracy of fault diagnosis.

[0171] In this application, based on the first electrical data, the voltage rise amplitude corresponding to the boost abrupt change point is determined. Then, when the number of boost abrupt change points corresponding to voltage rise amplitudes greater than the voltage rise threshold exceeds the number threshold, based on the first electrical data, the first branch whose current change exceeds the current threshold is determined. Based on the first current value of the first branch, a benchmark string is determined, which facilitates the judgment of fault strings based on the difference value of the benchmark string in subsequent applications, thereby improving the accuracy of fault detection.

[0172] If the diagnostic branch meets the target conditions, the location of the boost abrupt change point is determined to be below the benchmark string and within the target distance. The diagnostic string is then identified as the fault string. The fault string can be determined based on the current characteristics at the boost abrupt change point. The diagnostic method is convenient and easy to implement.

[0173] According to the fault diagnosis method for bypass diodes provided in the embodiments of this application, a first branch is determined by first electrical data, and a benchmark string is determined based on the first current value of the first branch. Then, when the diagnostic branch meets the target conditions, it is determined that the position of the boost abrupt change point is below the benchmark string and reaches the target distance, and the diagnostic string is determined as the fault string. The fault string can be determined based on the current characteristics at the boost abrupt change point. The diagnosis method is convenient and easy to implement.

[0174] In some embodiments, after step 130, the fault diagnosis method for the bypass diode may further include:

[0175] Fault sequences are processed using the results of closed-loop work order processing.

[0176] Update the sudden inefficient state to a normal state.

[0177] In this embodiment, the closed-loop work order processing result is obtained based on historical processing data, such as... Figure 4 As shown, when the diagnostic string is a fault string, the output bypass diode short-circuits the fault string and stores it in the database.

[0178] The sudden inefficiency state is the working state of the faulty series. The faulty series is processed using the closed-loop work order processing results, the fault is restored and an alarm is triggered, and then the sudden inefficiency state is updated to the normal state.

[0179] According to the fault diagnosis method for bypass diodes provided in the embodiments of this application, the faulty string is processed using the closed-loop work order processing results, and then the sudden inefficient state is updated to the normal state, forming a processing closed loop. This method can utilize historical diagnostic data for fault processing, thereby improving the accuracy and efficiency of fault diagnosis.

[0180] The fault diagnosis device for the bypass diode provided in this application is described below. The fault diagnosis device for the bypass diode described below can be referred to in correspondence with the fault diagnosis method for the bypass diode described above.

[0181] The bypass diode fault diagnosis method provided in this application can be executed by a bypass diode fault diagnosis device. This application uses the bypass diode fault diagnosis device executing the bypass diode fault diagnosis method as an example to illustrate the bypass diode fault diagnosis device provided in this application.

[0182] This application also provides a fault diagnosis device for bypass diodes.

[0183] like Figure 5 As shown, the fault diagnosis device for the bypass diode includes: a first processing module 510, a second processing module 520 and a third processing module 530.

[0184] The first processing module 510 is used to acquire the target electrical data of the target branch within the target time period;

[0185] The second processing module 520 is used to determine the boost voltage mutation point and the first electrical data corresponding to the boost voltage mutation point based on the target electrical data when the MPPT voltage of the diagnostic string in the target branch is abnormal; the first electrical data is the current data corresponding to the boost voltage mutation point.

[0186] The third processing module 530 is used to determine the fault string based on the first electrical data, and the bypass diode corresponding to the fault string is faulty.

[0187] The third processing module 530 is used for:

[0188] Based on the first electrical data, the first branch is determined. The first branch is the branch where the current change exceeds the current threshold corresponding to the voltage boost abrupt change point.

[0189] The benchmark string is determined based on the first current value of the first branch. The benchmark string is the string that is working normally, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch.

[0190] If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the faulty string.

[0191] The bypass diode fault diagnosis device provided in the embodiments of this application acquires the target electrical data of the target branch within the target time period. In the case of MPPT voltage abnormality, it determines the boost voltage change point and the first electrical data corresponding to the boost voltage change point based on the target electrical data. Then, based on the first electrical data, it determines the fault string. It can diagnose the fault of the bypass diode in real time, with high real-time performance and efficiency. Moreover, it does not require the installation of additional sensors, does not depend on specific equipment and instruments, has low detection cost, and is convenient and easy to implement.

[0192] In some embodiments, the third processing module 530 can also be used to determine the voltage rise amplitude corresponding to the voltage rise abrupt change point based on the first electrical data.

[0193] If the number of boost abrupt points corresponding to voltage rise amplitudes greater than the voltage rise threshold exceeds the number threshold, based on the first electrical data, determine the first branch whose current change exceeds the current threshold corresponding to the boost abrupt point.

[0194] Based on the first current value of the first branch, determine the benchmark string;

[0195] If the diagnostic branch meets the target conditions, the location of the voltage surge point is determined to be below the benchmark string and at the target distance. The diagnostic string is then identified as the fault string. The target condition refers to the current drop in the diagnostic branch in the target branch being greater than the current drop in the benchmark string.

[0196] According to the bypass diode fault diagnosis device provided in the embodiments of this application, a first branch is determined by the first electrical data, and a benchmark string is determined based on the first current value of the first branch. Then, when the diagnostic branch meets the target conditions, the position of the boost abrupt change point is determined to be below the benchmark string and reaches the target distance, and the diagnostic string is determined to be the fault string. The fault string can be determined based on the current characteristics at the boost abrupt change point. The diagnosis method is convenient and easy to implement.

[0197] In some embodiments, the fault diagnosis device for the bypass diode may further include a fourth processing module for obtaining the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch.

[0198] If the difference between the second current value and the third current value is less than the second threshold, and the second current value is less than the second current value of the target proportion, the diagnostic string is identified as a fault string.

[0199] According to the fault diagnosis device for bypass diodes provided in the embodiments of this application, by acquiring the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch, and then when the difference between the second current value and the third current value is less than a second threshold and the second current value is less than the second current value of the target ratio, it can be determined that the position of the boost change point of the diagnostic string is below the benchmark string and reaches the target distance, thereby identifying the diagnostic string as a fault string. The fault string can be determined based on the current characteristics at the boost change point. The diagnosis method is convenient and easy to implement, further improving the accuracy of fault diagnosis.

[0200] In some embodiments, the fault diagnosis device for the bypass diode may further include a fifth processing module for obtaining the differential values ​​corresponding to all branches based on the first-order differential value of the first current value.

[0201] The string in the branch corresponding to the smallest difference value is determined as the benchmark string.

[0202] According to the bypass diode fault diagnosis device provided in the embodiments of this application, based on the first-order differential value of the first current value, the differential value corresponding to all branches is obtained, and then the string in the branch corresponding to the smallest differential value is determined as the benchmark string. It can obtain the normally functioning string based on the differential value, which facilitates the judgment of the faulty string based on the differential value of the benchmark string in subsequent applications, thereby improving the accuracy of fault detection.

[0203] In some embodiments, the fault diagnosis device for the bypass diode may further include a sixth processing module for determining a target threshold based on the target electrical data, the target threshold being used to determine sudden inefficiency.

[0204] The theoretical MPPT voltage is determined based on the string's basic and environmental parameters.

[0205] Based on the theoretical MPPT voltage and the actual MPPT voltage, determine whether the MPPT voltage is abnormal.

[0206] According to the bypass diode fault diagnosis device provided in the embodiments of this application, a target threshold is determined based on the target electrical data, and then the theoretical MPPT voltage is determined based on the basic parameters and environmental parameters of the string. Then, based on the theoretical MPPT voltage and the actual MPPT voltage, it is determined whether the MPPT voltage is abnormal, so as to facilitate the identification of faulty strings based on the abnormal MPPT voltage in subsequent applications.

[0207] In some embodiments, the fault diagnosis device for the bypass diode may further include a seventh processing module, used to input basic parameters and environmental parameters into the MPPT voltage anomaly diagnosis model, and obtain the theoretical MPPT voltage output by the MPPT voltage anomaly diagnosis model, wherein...

[0208] The MPPT voltage anomaly diagnostic model is trained using basic sample parameters and environmental parameters as samples, and the theoretical MPPT voltage corresponding to the basic sample parameters and environmental parameters as sample labels.

[0209] The bypass diode fault diagnosis device provided in this application obtains the theoretical MPPT voltage by inputting the basic parameters and environmental parameters of the string into a pre-trained MPPT voltage anomaly diagnosis model. In practical applications, pre-training is only required before use, and data can be directly obtained afterward. The calculation efficiency is high and the accuracy is good. Furthermore, the MPPT voltage anomaly diagnosis model has strong learning ability. Data from each application process can be used as training data for the next training process, thereby improving the accuracy and precision of the model, making it easier for users to use, and improving the accuracy of the final fault diagnosis.

[0210] In some embodiments, the fault diagnosis device for the bypass diode may further include an eighth processing module for preprocessing the target electrical data based on at least one of communication dead value, interruption and over-limit value, to obtain second electrical data.

[0211] The target threshold is determined based on the second electrical data.

[0212] According to the fault diagnosis device for bypass diode provided in the embodiments of this application, by preprocessing the target electrical data based on at least one of communication dead value, interruption and over-limit value, noise data can be filtered out to obtain second electrical data. Then, based on the second electrical data, the target threshold is determined, which improves the accuracy of the determined target threshold and facilitates the judgment of sudden inefficiency based on the target threshold in the subsequent execution process, thereby improving the accuracy of the final fault diagnosis.

[0213] In some embodiments, the fault diagnosis device for the bypass diode may further include a ninth processing module for processing fault strings using the closed-loop work order processing results.

[0214] Update the sudden inefficient state to a normal state.

[0215] The bypass diode fault diagnosis device provided in the embodiments of this application processes faulty strings using closed-loop work order processing results, and then updates the sudden inefficient state to the normal state, forming a processing closed loop. It can use historical diagnostic data for fault processing, thereby improving the accuracy and efficiency of fault diagnosis.

[0216] The fault diagnosis device for the bypass diode in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the specific device.

[0217] The bypass diode fault diagnosis device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0218] The bypass diode fault diagnosis device provided in this application embodiment can achieve Figures 1 to 4 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0219] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640. The processor 610, communication interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logic instructions in the memory 630 to execute a fault diagnosis method for the bypass diode. This method includes: acquiring target electrical data of the target branch within a target time period; determining the boost voltage abrupt change point and the corresponding first electrical data based on the target electrical data in the event of an MPPT voltage anomaly; and determining the fault string based on the first electrical data.

[0220] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0221] On the other hand, this application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer is able to execute the bypass diode fault diagnosis method provided by the above methods. The method includes: acquiring target electrical data of the target branch within a target time period; determining the boost voltage mutation point and the first electrical data corresponding to the boost voltage mutation point based on the target electrical data in the case of MPPT voltage abnormality; and determining the fault string based on the first electrical data.

[0222] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the fault diagnosis methods for bypass diodes provided above. The method includes: acquiring target electrical data of a target branch within a target time period; determining a boost voltage abrupt change point and corresponding first electrical data based on the target electrical data in the event of an MPPT voltage anomaly; and determining a fault string based on the first electrical data.

[0223] In another aspect, embodiments of this application provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the above-mentioned fault diagnosis method for bypass diodes. The method includes: acquiring target electrical data of the target branch within a target time period; determining the boost voltage mutation point and the first electrical data corresponding to the boost voltage mutation point based on the target electrical data in the case of MPPT voltage abnormality; and determining the fault string based on the first electrical data.

[0224] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0225] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0226] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, 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 computer-readable 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 the various embodiments or some parts of the embodiments.

[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A fault diagnosis method for a bypass diode, characterized in that, include: Acquire the target electrical data of the target branch within the target time period; In the event of an abnormal MPPT voltage in the diagnostic string within the target branch, a boost inflection point and a first electrical data point corresponding to the boost inflection point are determined based on the target electrical data; the first electrical data is the current data corresponding to the boost inflection point. Based on the first electrical data, a fault string is identified, and the bypass diode corresponding to the fault string is faulty. The step of determining the fault string based on the first electrical data includes: Based on the first electrical data, a first branch is determined, which is the branch where the current change at the boost abrupt point exceeds the current threshold. A benchmark string is determined based on the first current value of the first branch. The benchmark string is a normally functioning string, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch. If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the fault string.

2. The fault diagnosis method for bypass diodes according to claim 1, characterized in that, The step of determining the fault string based on the first electrical data includes: Based on the first electrical data, determine the voltage rise amplitude corresponding to the voltage jump point; If the number of boost abrupt change points corresponding to the voltage rise amplitude greater than the voltage rise threshold exceeds the number threshold, based on the first electrical data, determine the first branch whose current change exceeds the current threshold corresponding to the boost abrupt change point. Based on the first current value of the first branch, the benchmark string is determined; If the diagnostic branch meets the target conditions, the location of the voltage surge point is determined to be below the benchmark string and at a target distance. The diagnostic string is then identified as the fault string. The target conditions refer to the current drop in the diagnostic branch in the target branch being greater than the current drop in the benchmark string.

3. The fault diagnosis method for bypass diodes according to claim 2, characterized in that, Determining the location of the boost abrupt change point below the benchmark string and reaching the target distance, and identifying the diagnostic string as the fault string, includes: Obtain the second current value after the sudden change of the benchmark string and the third current value after the sudden change of the diagnostic string corresponding to the diagnostic branch; If the difference between the second current value and the third current value is less than the second threshold, and the second current value is less than the second current value of the target proportion, the diagnostic string is determined to be the fault string.

4. The fault diagnosis method for bypass diodes according to claim 2, characterized in that, The determination of the benchmark string based on the first current value of the first branch includes: Based on the first-order difference value of the first current value, obtain the difference value corresponding to all branches; The string in the branch corresponding to the smallest difference value is determined as the benchmark string.

5. The fault diagnosis method for the bypass diode according to any one of claims 1-4, characterized in that, In the event of an MPPT voltage anomaly, before determining the boost inflection point and the first electrical data corresponding to the boost inflection point based on the target electrical data, the method further includes: Based on the target electrical data, a target threshold is determined, which is used to identify sudden inefficiencies; The theoretical MPPT voltage is determined based on the string's basic and environmental parameters. Based on the theoretical MPPT voltage and the actual MPPT voltage, determine whether the MPPT voltage is abnormal.

6. The fault diagnosis method for bypass diodes according to claim 5, characterized in that, The determination of the theoretical MPPT voltage based on the string's basic parameters and environmental parameters includes: The basic parameters and environmental parameters are input into the MPPT voltage anomaly diagnostic model to obtain the theoretical MPPT voltage output by the MPPT voltage anomaly diagnostic model, wherein... The MPPT voltage anomaly diagnostic model is trained using basic sample parameters and environmental sample parameters as samples, and using the theoretical MPPT voltage corresponding to the basic sample parameters and environmental sample parameters as sample labels.

7. The fault diagnosis method for bypass diodes according to claim 5, characterized in that, Determining the target threshold based on the target electrical data includes: The target electrical data is preprocessed based on at least one of communication dead value, interruption and over-limit value to obtain second electrical data; The target threshold is determined based on the second electrical data.

8. The fault diagnosis method for a bypass diode according to any one of claims 1-4, characterized in that, After determining the fault string based on the first electrical data, the method further includes: The fault sequence is processed using the closed-loop work order processing results; Update the sudden inefficient state to a normal state.

9. A fault diagnosis device for a bypass diode, characterized in that, include: The first processing module is used to acquire the target electrical data of the target branch within the target time period; The second processing module is used to determine, based on the target electrical data, a boost abrupt change point and the first electrical data corresponding to the boost abrupt change point when the MPPT voltage of the diagnostic string in the target branch is abnormal; the first electrical data is the current data corresponding to the boost abrupt change point. The third processing module is used to determine the fault string based on the first electrical data, wherein the bypass diode corresponding to the fault string is faulty. The third processing module is used for: Based on the first electrical data, a first branch is determined, which is the branch where the current change at the boost abrupt point exceeds the current threshold. A benchmark string is determined based on the first current value of the first branch. The benchmark string is a normally functioning string, and the difference value corresponding to the benchmark string is the smallest difference value among all strings in the first branch. If the current drop in the diagnostic branch within the target branch is greater than the current drop in the benchmark string, the diagnostic string within the diagnostic branch is identified as the fault string.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the fault diagnosis method for the bypass diode as described in any one of claims 1-8.

Images