Fault detection method and system for photovoltaic water pump inverter

Abstract

The invention relates to the field of photovoltaic water pump inverter control, and discloses a photovoltaic water pump inverter fault detection method and system, and the method comprises the steps: obtaining a time sequence broadcast voltage value and a time sequence broadcast current value of a main inverter in a main-slave inverter control group, obtaining a time sequence output voltage value and a time sequence output current value of each slave inverter in a plurality of slave inverters of the inverter control group; determining a time sequence difference value corresponding to the time sequence broadcast voltage value and the time sequence output voltage value of each slave inverter as a time sequence voltage deviation value; determining a time sequence difference value between the time sequence broadcast current value and the time sequence output current value of each slave inverter, and taking the time sequence difference value as a time sequence current deviation value; and through an inverter state identification model, according to the time sequence voltage deviation values and the time sequence current deviation values of the plurality of slave inverters in the master-slave inverter control group, determining fault probability values corresponding to the plurality of slave inverters. According to the invention, the photovoltaic inverter with a poor working state can be quickly positioned in a master-slave control scheme.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic water pump inverter control, and more specifically, to a fault detection method and system for a photovoltaic water pump inverter. Background Art

[0002] Photovoltaic water pump inverter is a device specially used in photovoltaic power generation system. Its main function is to convert the direct current generated by photovoltaic panels into alternating current to drive the water pump to work. Photovoltaic water pump inverter usually includes components such as inverter bridge, control logic and filter circuit. Photovoltaic water pump inverter can adjust the output frequency in real time according to the change of sunshine intensity, realize maximum power point tracking (MPPT), and maximize the use of solar energy. In addition, photovoltaic water pump inverter also has a variety of operating modes and MPPT control methods to choose from. The water pump speed range can be freely set according to the actual system conditions, and it has lightning protection, overvoltage, undervoltage, overcurrent, overload and other protection functions.

[0003] As the capacity of AC loads for electric energy demand increases, the power of photovoltaic inverters also becomes larger and larger. Increasing the power of photovoltaic inverters will make the appearance larger and larger, which is not convenient for the mobile transportation of the inverter; on the other hand, it will increase the difficulty of selecting internal electronic components. In order to meet this demand, the function of paralleling the output ends of multiple photovoltaic inverters to jointly bear the AC load that exceeds its own power has become a necessary function of photovoltaic inverters. There are four main methods for parallel control of existing inverters: master-slave control scheme, centralized control scheme, wireless parallel droop control scheme, and instantaneous average current control. At present, the master-slave control scheme can quickly identify the photovoltaic inverter as the host and realize the rapid positioning of the master and slave. However, the current master-slave control scheme cannot quickly locate the photovoltaic inverter with poor working status, resulting in the reliability of the master-slave control method of the photovoltaic inverter being affected. Summary of the invention

[0004] The purpose of this application is to provide a fault detection method and system for a photovoltaic water pump inverter, which solves the technical problem that the current master-slave control scheme cannot quickly locate the photovoltaic inverter in poor working condition, and achieves the technical effect of quickly locating the photovoltaic inverter in poor working condition in the master-slave control scheme.

[0005] A fault detection method for a photovoltaic water pump inverter provided in an embodiment of the present application includes: obtaining a time-series broadcast voltage value and a time-series broadcast current value of a master inverter in a master-slave inverter control group, and obtaining a time-series output voltage value and a time-series output current value of each slave inverter in a plurality of slave inverters in the inverter control group; determining a time-series difference value corresponding to a time-series broadcast voltage value and a time-series output voltage value of each slave inverter as a time-series voltage deviation value; and determining a time-series difference value between a time-series broadcast current value and a time-series output current value of each slave inverter as a time-series current deviation value; determining fault probability values ​​corresponding to each of the plurality of slave inverters in the master-slave inverter control group according to the time-series voltage deviation value and the time-series current deviation value of the plurality of slave inverters in the master-slave inverter control group through an inverter state recognition model; and marking the first slave inverter as a faulty slave inverter when the fault probability value of the first slave inverter is greater than a preset fault probability value.

[0006] In a possible implementation, the method further includes: determining a sequential voltage fluctuation value corresponding to a sequential voltage deviation value of each slave inverter, and determining a sequential current fluctuation value corresponding to a sequential current deviation value of each slave inverter; wherein the sequential voltage fluctuation value includes a fluctuation time and a fluctuation amplitude of the sequential voltage deviation value, and the sequential current fluctuation value includes a fluctuation time and a fluctuation amplitude of the sequential current deviation value; clustering multiple slave inverters in the master-slave inverter control group according to similar features of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter, and obtaining Multiple slave inverter subsets, and determine the mean of the sequential voltage fluctuation values ​​and the mean of the sequential current fluctuation values ​​of the multiple slave inverters in each slave inverter subset; through the inverter state recognition model, according to the mean of the sequential voltage deviation values ​​and the mean of the sequential current deviation values ​​of the multiple slave inverter subsets, determine the fault probability values ​​corresponding to the multiple slave inverter subsets respectively; when the fault probability value of the first slave inverter subset is greater than the preset fault probability value, mark the first slave inverter subset as a faulty slave inverter subset, and determine the faulty slave inverter in the faulty slave inverter subset.

[0007] In another possible implementation, multiple slave inverters in a master-slave inverter control group are clustered according to similar features of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter, including: obtaining the sequential irradiance change value and the sequential temperature change value of the photovoltaic solar panel corresponding to each slave inverter, and determining a first overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential irradiance change value of each slave inverter, and determining a second overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential temperature change value; in the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter, deleting the sequential voltage fluctuation value and the sequential current fluctuation value corresponding to the first overlapping time period and the second overlapping time period; clustering multiple slave inverters in a master-slave inverter control group according to similar features of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter.

[0008] In another possible implementation, determining a faulty slave inverter in a faulty slave inverter subset includes: determining a voltage fluctuation variance value of a sequential voltage fluctuation value and a current fluctuation variance value of a sequential current fluctuation value of each slave inverter in the faulty slave inverter subset; and determining a mean voltage fluctuation variance value and a mean current fluctuation variance value of all slave inverters in the faulty slave inverter subset; when a first voltage fluctuation variance value of a first slave inverter is greater than or equal to a mean voltage fluctuation variance value, or when a first current fluctuation variance value of a first slave inverter is greater than or equal to a mean current fluctuation variance value, determining that the first slave inverter is a faulty inverter.

[0009] In another possible implementation, the method also includes: determining a target slave inverter subset with the smallest fault probability value among multiple slave inverter subsets, and determining the voltage fluctuation variance value of the timing voltage fluctuation value and the current fluctuation variance value of the timing current fluctuation value of each slave inverter in the target slave inverter subset, and determining the sum of the voltage fluctuation variance value and the current fluctuation variance value of each slave inverter in the target slave inverter subset as the comprehensive evaluation value of the slave inverter; determining the target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset, and using the target slave inverter as a backup master inverter; obtaining the main inverter failure probability value of the main inverter, and when the main inverter failure probability value is greater than or equal to the preset main inverter failure probability value, switching the backup main inverter to the main inverter.

[0010] In another possible implementation, the method also includes: determining a preset number of target slave inverter subsets whose failure probability values ​​are arranged from small to large among multiple slave inverter subsets, and determining the communication failure probability between each slave inverter and the master inverter in each target slave inverter subset, and determining the mean communication failure probability of all slave inverters in each target slave inverter subset; determining a target slave inverter subset with the smallest mean communication failure probability among a preset number of target slave inverter subsets, and determining a target slave inverter with the smallest comprehensive evaluation value of slave inverters in the target slave inverter subset, and using the target slave inverter as a backup master inverter.

[0011] In another possible implementation, a main inverter failure probability value of a main inverter is obtained, including: obtaining a failure probability value of the main inverter, and obtaining a communication failure probability between the main inverter and a plurality of slave inverters; determining the sum of a product of a first weight factor and a failure probability value, and a product of a second weight factor and a communication failure probability, as the main inverter failure probability value; wherein the first weight factor is 1 minus the difference between the second weight factor and the master inverter, and the second weight factor is determined according to the output load fluctuation of the master-slave inverter control group.

[0012] In another possible implementation, a second weight factor is determined based on the output load fluctuation of the master-slave inverter control group, including: obtaining the fluctuation variance value of the output load of the master-slave inverter control group within a preset time period, and obtaining the preset maximum fluctuation variance value of the output load of the master-slave inverter control group; determining the ratio of the fluctuation variance value to the preset maximum fluctuation variance value as the second weight factor.

[0013] In another possible implementation, the method also includes: obtaining the number of inverters in the master-slave inverter control group, and obtaining a threshold value of the number of inverters in the master-slave inverter control group; determining a ratio of the number of inverters to the threshold value of the number of inverters as an inverter number adjustment factor; and multiplying the second weight factor by the inverter number adjustment factor to adjust the second weight factor.

[0014] An embodiment of the present application also provides a fault detection system for a photovoltaic water pump inverter, comprising a unit for executing any of the methods described above.

[0015] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: An embodiment of the present application provides a fault detection method for a photovoltaic water pump inverter, and the method includes: obtaining a time-series broadcast voltage value and a time-series broadcast current value of a master inverter in a master-slave inverter control group, and obtaining a time-series output voltage value and a time-series output current value of each slave inverter in a plurality of slave inverters in the inverter control group; determining a time-series difference value corresponding to a time-series broadcast voltage value and a time-series output voltage value of each slave inverter as a time-series voltage deviation value; and determining a time-series difference value between a time-series broadcast current value and a time-series output current value of each slave inverter as a time-series current deviation value; determining, through an inverter state recognition model, fault probability values ​​corresponding to each of the plurality of slave inverters in the master-slave inverter control group according to the time-series voltage deviation values ​​and the time-series current deviation values ​​of the plurality of slave inverters in the master-slave inverter control group; when the fault probability value of a first slave inverter is greater than a preset fault probability value, marking the first slave inverter as a faulty slave inverter. The method in the embodiment of the present application can determine the fault probability values ​​corresponding to multiple slave inverters in the master-slave inverter control group according to the timing voltage deviation values ​​and timing current deviation values ​​of multiple slave inverters in the master-slave inverter control group, thereby realizing the identification of faulty inverters among the multiple slave inverters, improving the accuracy of identifying faulty slave inverters in the master-slave control scheme, and being able to improve the stability of the inverter system in the master-slave control scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 A schematic flow chart of a first photovoltaic water pump inverter fault detection method provided in an embodiment of the present application; Figure 2 A schematic flow chart of a second photovoltaic water pump inverter fault detection method provided in an embodiment of the present application; Figure 3 A schematic flow chart of a third photovoltaic water pump inverter fault detection method provided in an embodiment of the present application; Figure 4 A schematic flow chart of a fourth photovoltaic water pump inverter fault detection method provided in an embodiment of the present application; Figure 5 A schematic flow chart of a fifth photovoltaic water pump inverter fault detection method provided in an embodiment of the present application; Figure 6 A schematic diagram of the logical structure of a fault detection system for a photovoltaic water pump inverter provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0019] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0020] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0021] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0023] The master-slave control scheme can quickly identify the photovoltaic inverter as the master, and realize the rapid positioning of the master and slave. However, the current master-slave control scheme cannot quickly locate the photovoltaic inverter in poor working condition, resulting in the reliability of the master-slave control mode of the photovoltaic inverter being affected.

[0024] Based on the above reasons, an embodiment of the present application provides a fault detection method for a photovoltaic water pump inverter, which includes: obtaining the timed broadcast voltage value and the timed broadcast current value of the master inverter in the master-slave inverter control group, and obtaining the timed output voltage value and the timed output current value of each slave inverter in the multiple slave inverters of the inverter control group; determining the timing difference corresponding to the timed broadcast voltage value and the timing output voltage value of each slave inverter as the timing voltage deviation value; and determining the timing difference between the timing broadcast current value and the timing output current value of each slave inverter as the timing current deviation value; through the inverter state recognition model, according to the timing voltage deviation value and the timing current deviation value of the multiple slave inverters in the master-slave inverter control group, determine the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group; when the fault probability value of the first slave inverter is greater than the preset fault probability value, mark the first slave inverter as a faulty slave inverter. The method in the embodiment of the present application can determine the fault probability values ​​corresponding to multiple slave inverters in the master-slave inverter control group according to the timing voltage deviation values ​​and timing current deviation values ​​of multiple slave inverters in the master-slave inverter control group, thereby realizing the identification of faulty inverters among the multiple slave inverters, improving the accuracy of identifying faulty slave inverters in the master-slave control scheme, and being able to improve the stability of the inverter system in the master-slave control scheme.

[0025] In some scenarios, a fault detection method for a photovoltaic water pump inverter of an embodiment of the present application can be applied to inverter control in a master-slave control scheme, which can improve the working stability of the inverter in the master-slave control scheme and improve the use effect of the master-slave control scheme.

[0026] A photovoltaic water pump inverter fault detection method provided in an embodiment of the present application is described in detail below with reference to specific examples.

[0027] Figure 1 A schematic diagram of a flow chart of a first photovoltaic water pump inverter fault detection method provided in an embodiment of the present application, such as Figure 1 As shown, the method includes S110 to S120, and S110 to S120 are described in detail below.

[0028] S110, obtaining the time-series broadcast voltage value and the time-series broadcast current value of the master inverter in the master-slave inverter control group, and obtaining the time-series output voltage value and the time-series output current value of each slave inverter in the multiple slave inverters of the inverter control group. Determine the time-series difference value corresponding to the time-series broadcast voltage value and the time-series output voltage value of each slave inverter as the time-series voltage deviation value. And determine the time-series difference value between the time-series broadcast current value and the time-series output current value of each slave inverter as the time-series current deviation value.

[0029] In the master-slave parallel control scheme of the inverter, the master-slave control scheme realizes the stable operation of the parallel system by setting a master inverter and multiple slave inverters. The master inverter is responsible for voltage control, while the slave inverter is responsible for current control. The master inverter ensures that the output voltage of the entire system is constant by adjusting the amplitude and phase of the output voltage, while the slave inverter adjusts its own output current according to the instructions of the master module to achieve equal distribution of the load current. In the master-slave parallel control scheme, the master inverter usually adopts a voltage control mode (such as SPWM control), is responsible for adjusting the reference voltage of the system, and exchanges data with the slave inverter through communication methods (such as pulse synchronization or high-speed communication). At the same time, the slave inverter adopts a current control mode to adjust its own output current according to the instructions provided by the master inverter to achieve balanced distribution of the load current.

[0030] In the master-slave parallel control scheme, when the master inverter fails, the system can upgrade a slave inverter to the master inverter through a switching mechanism, thereby ensuring the continuous operation of the system.

[0031] In the master-slave parallel control scheme, in order to accurately identify the fault of the inverter, the time-series broadcast voltage value and the time-series broadcast current value of the master inverter in the master-slave inverter control group can be first obtained. The time-series broadcast voltage value and the time-series broadcast current value are the control voltage value and the control current value distributed by the master inverter to multiple slave inverters at multiple moments in time sequence. Then, the time-series broadcast voltage value and the time-series broadcast current value can be used as indicators to judge the working status of the slave inverter.

[0032] In the master-slave parallel control scheme, the timing output voltage value and the timing output current value of each slave inverter among the multiple slave inverters in the inverter control group can also be obtained. The timing output voltage value and the timing output current value are the actual output values ​​of each slave inverter under control. Then, the output state of the slave inverter can be evaluated according to the timing output voltage value and the timing output current value to determine the faulty slave inverter.

[0033] After obtaining the sequential output voltage value, the sequential difference between the sequential broadcast voltage value and the sequential output voltage value of each slave inverter can be determined as a sequential voltage deviation value, which characterizes the sequential voltage output characteristics of the slave inverter.

[0034] After obtaining the sequential output current value, the sequential difference between the sequential broadcast current value and the sequential output current value of each slave inverter can be determined as a sequential current deviation value, which characterizes the sequential current output characteristics of the slave inverter.

[0035] S120, determining the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group respectively according to the sequential voltage deviation values ​​and the sequential current deviation values ​​of the multiple slave inverters in the master-slave inverter control group through the inverter state identification model. When the fault probability value of the first slave inverter is greater than the preset fault probability value, the first slave inverter is marked as a faulty slave inverter.

[0036] After obtaining the timing voltage deviation value and the timing current deviation value, the inverter state identification model can be used to determine the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group according to the timing voltage deviation value and the timing current deviation value of the multiple slave inverters in the master-slave inverter control group, thereby realizing simultaneous evaluation of the multiple slave inverters in the master-slave inverter control group.

[0037] It should be noted that, since the multiple slave inverters in the master-slave inverter control group work under the control of the master inverter, the multiple slave inverters in the master-slave inverter control group work together. In order to efficiently identify the multiple slave inverters in the master-slave inverter control group, in the embodiment of the present application, the multiple slave inverters in the master-slave inverter control group are used to perform overall fault identification. The deviation data of the multiple slave inverters in the master-slave inverter control group can form a time-space correlation feature (such as phase deviation synchronization, current deviation amplitude consistency), and then cross-validation can be used to exclude accidental interference. For example, if the voltage deviation of a slave inverter is abnormal but the synchronization of the other slave inverters is normal, it is more likely to be local noise; if multiple slave inverter devices have the same deviation, it is more likely to point to the fault of the master inverter or the drift of the system parameters, and then the problem of the fault of the master inverter or the drift of the system parameters can be eliminated, and the accurate identification of the faulty multiple slave inverters in the multiple slave inverters can be achieved.

[0038] In addition, a more accurate maintenance plan can be formulated based on the health status assessment of group data. For example, if the failure probability of a slave inverter is continuously higher than the group average, it can be given priority for maintenance instead of using a unified cycle maintenance, which improves the maintenance efficiency of the slave inverter.

[0039] After the fault probability value of the slave inverter is obtained, when the fault probability value of the first slave inverter is greater than the preset fault probability value, the first slave inverter is marked as a faulty slave inverter, thereby accurately identifying the fault of the faulty slave inverter.

[0040] Exemplarily, the preset failure probability value may be 0.6, 0.7 or 0.8.

[0041] Exemplarily, the inverter state identification model can be obtained by training the timing voltage deviation values ​​and timing current deviation values ​​of multiple slave inverters in the marked master-slave inverter control group and the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group. The inverter state identification model can predict the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group.

[0042] The beneficial effect of the above-mentioned implementation method is that according to the timing voltage deviation value and the timing current deviation value of the multiple slave inverters in the master-slave inverter control group, the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group are determined, so that the faulty inverter among the multiple slave inverters can be identified, the accuracy of identifying the faulty slave inverter in the master-slave control scheme is improved, and the stability of the inverter system in the master-slave control scheme can be improved.

[0043] The beneficial effect of the above-mentioned implementation method is that overall fault identification is performed through multiple slave inverters in the master-slave inverter control group. The deviation data of multiple slave inverters in the master-slave inverter control group can form time-space correlation characteristics, and accidental interference can be eliminated through cross-validation, thereby improving the fault identification accuracy of multiple slave inverters in the master-slave inverter control group.

[0044] Figure 2 A schematic diagram of a flow chart of a second photovoltaic water pump inverter fault detection method provided in an embodiment of the present application, such as Figure 2 As shown, the above method further includes S210 to S230, and S210 to S230 are described in detail below.

[0045] S210, determining a sequential voltage fluctuation value corresponding to the sequential voltage deviation value of each slave inverter, and determining a sequential current fluctuation value corresponding to the sequential current deviation value of each slave inverter. The sequential voltage fluctuation value includes a fluctuation time and a fluctuation amplitude of the sequential voltage deviation value, and the sequential current fluctuation value includes a fluctuation time and a fluctuation amplitude of the sequential current deviation value.

[0046] When identifying faults of slave inverters, when the number of slave inverters is large, for example, when the number of slave inverters reaches 1,000, in order to perform overall fault identification on multiple slave inverters in the slave inverter control group at this time, the characteristic scale of the input corresponding to the multiple slave inverters to the inverter state identification model may be too large. Therefore, the input characteristic size of the multiple slave inverters can be reduced, thereby enabling fault identification of the multiple slave inverters.

[0047] When there are a large number of slave inverters and a faulty inverter among multiple master-slave inverters is determined, the timing voltage fluctuation value corresponding to the timing voltage deviation value of each slave inverter can be determined, and the timing current fluctuation value corresponding to the timing current deviation value of each slave inverter can be determined. The timing voltage fluctuation value and the timing current fluctuation value characterize the voltage fluctuation and current fluctuation of each slave inverter. Similar slave inverters can then be clustered according to the voltage fluctuation and current fluctuation, so as to identify slave inverter faults through the clustered slave inverter set, thereby improving the accuracy of fault identification for the slave inverter set.

[0048] It should be noted that the timing voltage fluctuation value includes the fluctuation time and fluctuation amplitude of the timing voltage deviation value. The timing voltage fluctuation value can be the timing voltage fluctuation value obtained by subtracting the reference timing voltage deviation value from the timing voltage deviation value, thereby realizing the filtering of smaller voltage fluctuation values. The timing voltage fluctuation value can characterize the voltage fluctuation characteristics of the inverter in the time sequence.

[0049] It should be noted that the timing current fluctuation value includes the fluctuation time and fluctuation amplitude of the timing current deviation value. The timing current fluctuation value can be the timing current fluctuation value obtained by subtracting the reference timing current deviation value from the timing current deviation value, thereby realizing the filtering of smaller current fluctuation values. The timing current fluctuation value can characterize the current fluctuation characteristics of the inverter in the time sequence.

[0050] S220. Clustering multiple slave inverters in the master-slave inverter control group according to similar characteristics of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter to obtain multiple slave inverter subsets, and determining the mean value of the sequential voltage fluctuation value and the mean value of the sequential current fluctuation value of the multiple slave inverters in each slave inverter subset.

[0051] After obtaining the sequential voltage fluctuation value and the sequential current fluctuation value, multiple slave inverters in the master-slave inverter control group can be clustered according to the similar characteristics of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter to obtain multiple slave inverter subsets, and the sequential voltage fluctuation values ​​and the sequential current fluctuation values ​​of the slave inverters in each slave inverter subset have similarities.

[0052] Exemplarily, when the slave inverters are clustered according to similar features of the time-sequential voltage fluctuation values ​​and the time-sequential current fluctuation values, the slave inverters may be clustered according to the time-sequential voltage fluctuation values ​​and the time-sequential current fluctuation values ​​based on a K-means++ clustering algorithm.

[0053] In the embodiment of the present application, after obtaining multiple slave inverter subsets, the average of the timing voltage fluctuation values ​​and the average of the timing current fluctuation values ​​of the multiple slave inverters in each slave inverter subset can be determined, and then fault identification can be performed on each slave inverter subset according to the average of the timing voltage fluctuation values ​​and the average of the timing current fluctuation values ​​of the multiple slave inverters to locate the faulty slave inverter subset among the multiple slave inverter subsets.

[0054] It should be noted that in the embodiment of the present application, the devices can be divided into slave inverter subsets with similar behavior patterns through similarity clustering of fluctuation characteristics. For example, the slave inverters in the slave inverter subset in the photovoltaic power station have a synchronous increase in voltage fluctuation amplitude when the light changes in the early morning, while other slave inverter subsets do not have this phenomenon. This pattern difference can help quickly locate regional faults related to the MPPT algorithm.

[0055] In addition, by determining the mean of the sequential voltage fluctuation values ​​and the mean of the sequential current fluctuation values ​​of multiple slave inverters, the observability of gradual faults can be enhanced through further mean analysis. For example, the voltage fluctuation amplitude of the slave inverter increases by 0.5% per month due to insulation aging, which may be ignored in a single slave inverter, but the mean curve in the slave inverter subset will clearly show this linear growth trend, which is convenient for fault observation.

[0056] S230. Through the inverter state identification model, determine the fault probability values ​​corresponding to the multiple slave inverter subsets respectively according to the mean values ​​of the timing voltage deviation values ​​and the mean values ​​of the timing current deviation values ​​of the multiple slave inverter subsets; when the fault probability value of the first slave inverter subset is greater than the preset fault probability value, mark the first slave inverter subset as a faulty slave inverter subset, and determine the faulty slave inverter in the faulty slave inverter subset.

[0057] When identifying a faulty slave inverter subset among multiple slave inverter subsets, the inverter state identification model can be used to determine the fault probability values ​​corresponding to the multiple slave inverter subsets according to the mean values ​​of the timing voltage deviation values ​​and the mean values ​​of the timing current deviation values ​​of the multiple slave inverter subsets. The fault probability value of each slave inverter subset represents the probability value of failure of each slave inverter subset.

[0058] After obtaining the fault probability values ​​corresponding to multiple slave inverter subsets, when the fault probability value of the first slave inverter subset is greater than the preset fault probability value, it means that the failure probability of the inverters in the first slave inverter subset is relatively large, and the first slave inverter subset can be marked as a faulty slave inverter subset.

[0059] In the embodiment of the present application, after obtaining multiple slave inverter subsets through clustering, the synchronization of fluctuation moments can be analyzed, the phase correlation between devices can be revealed, and then the slave inverter subset can be analyzed for faults according to the phase correlation. For example, when multiple inverters simultaneously have current fluctuation spikes near the zero-crossing point of the grid voltage, it may point to a systematic fault of phase-locked loop parameter drift, while independent analysis of a single slave inverter is difficult to find such phase-related features.

[0060] After obtaining the faulty slave inverter subset, the inverters in the faulty slave inverter subset are further identified, so that the faulty slave inverters in the faulty slave inverter subset can be determined, thereby achieving accurate identification of the faulty slave inverters.

[0061] Exemplarily, the inverter state identification model can be trained by the mean of the timing voltage deviation values ​​of multiple labeled slave inverter subsets, the mean of the timing current deviation values, and the fault probability values ​​corresponding to multiple slave inverter subsets. The inverter state identification model can identify the fault probability values ​​of the slave inverter subsets.

[0062] The beneficial effect of the above-mentioned implementation method is that when overall fault identification is performed on multiple slave inverters in the slave inverter control group, the characteristic scale of the input corresponding to the multiple slave inverters to the inverter state identification model may be too large. Clustering can reduce the input characteristic size of the multiple slave inverters, thereby enabling efficient fault identification of multiple master-slave inverters.

[0063] The beneficial effect of the above implementation method is that by determining the mean of the sequential voltage fluctuation values ​​and the mean of the sequential current fluctuation values ​​of multiple slave inverters, the observability of gradual faults can be enhanced through mean analysis, thereby improving the identification accuracy of the faulty slave inverter subset.

[0064] The beneficial effect of the above-mentioned implementation method is that after obtaining multiple slave inverter subsets through clustering, the synchronization of the fluctuation moments can be analyzed, the phase correlation between the devices can be revealed, and then the slave inverter subsets can be analyzed for faults according to the phase correlation, thereby improving the accurate identification of faults in the slave inverter subsets.

[0065] In some implementations, in the above S220, multiple slave inverters in the master-slave inverter control group are clustered according to similar characteristics of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter, including S221 to S222. S221 to S222 are described in detail below.

[0066] S221. Obtain the sequential irradiance change value and the sequential temperature change value of the photovoltaic solar panel corresponding to each slave inverter, and determine the first overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential irradiance change value of each slave inverter, and determine the second overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential temperature change value.

[0067] When detecting the working state of the slave inverter, in order to accurately detect the state of the slave inverter, the influence of the light intensity and temperature of the solar panel can be eliminated, thereby further improving the accuracy of detecting the state of the inverter.

[0068] When the influence of the light intensity and temperature of the solar panels are excluded, the time-series irradiance change value and the time-series temperature change value of each photovoltaic solar panel corresponding to the inverter can be obtained. The time-series irradiance change value and the time-series temperature change value of the photovoltaic solar panel can be obtained through the light sensor data and the temperature sensor data on the solar panel.

[0069] After obtaining the sequential irradiance change value and the sequential temperature change value, the first overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential irradiance change value of each slave inverter can be determined, and the second overlapping time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential temperature change value can be determined, and then the influence of the light intensity and temperature of the solar panel can be eliminated according to the first overlapping time period and the second overlapping time period.

[0070] S222: Delete the sequential voltage fluctuation values ​​and the sequential current fluctuation values ​​corresponding to the first coincidence time period and the second coincidence time period from the sequential voltage fluctuation values ​​and the sequential current fluctuation values ​​of each slave inverter. Cluster the multiple slave inverters in the master-slave inverter control group according to the similar characteristics of the sequential voltage fluctuation values ​​and the sequential current fluctuation values ​​of each slave inverter.

[0071] When the influence of the light intensity and temperature of the solar panel is eliminated, the timing voltage fluctuation value and the timing current fluctuation value corresponding to the first overlap time period and the second overlap time period can be deleted from the timing voltage fluctuation value and the timing current fluctuation value of each slave inverter, so that the timing voltage fluctuation value and the timing current fluctuation value of each slave inverter only retain the timing voltage fluctuation value and the timing current fluctuation value after the influence of the light intensity and temperature of the solar panel is eliminated.

[0072] After obtaining the adjusted sequential voltage fluctuation value and sequential current fluctuation value, multiple slave inverters in the master-slave inverter control group can be clustered according to the similar characteristics of the sequential voltage fluctuation value and sequential current fluctuation value of each slave inverter, thereby improving the accuracy of subsequent fault identification of multiple slave inverters based on the clustering results.

[0073] The beneficial effect of the above implementation is that the state of the inverter can be accurately detected, the influence of the light intensity and temperature of the solar panel can be eliminated, and the accuracy of detecting the state of the inverter can be further improved.

[0074] In some implementations, in the above S230, determining the faulty slave inverter in the faulty slave inverter subset includes S231 to S232, and S231 to S232 are described in detail below.

[0075] S231. Determine the voltage fluctuation variance value of the sequential voltage fluctuation value and the current fluctuation variance value of the sequential current fluctuation value of each slave inverter in the faulty slave inverter subset; and determine the mean value of the voltage fluctuation variance value and the mean value of the current fluctuation variance value of all slave inverters in the faulty slave inverter subset.

[0076] When determining the faulty slave inverter in the faulty slave inverter subset, the voltage fluctuation variance value of the sequential voltage fluctuation value and the current fluctuation variance value of the sequential current fluctuation value of each slave inverter in the faulty slave inverter subset can be determined, and the voltage fluctuation variance value and the current fluctuation variance value characterize the voltage and current fluctuation amplitudes of each slave inverter in the faulty slave inverter subset.

[0077] At the same time, the mean voltage fluctuation variance value and the mean current fluctuation variance value of all slave inverters in the faulty slave inverter subset can be determined, and then the faulty slave inverter in the faulty slave inverter subset can be identified based on the mean voltage fluctuation variance value and the mean current fluctuation variance value of all slave inverters in the faulty slave inverter subset.

[0078] S232: When the first voltage fluctuation variance value of the first slave inverter is greater than or equal to the voltage fluctuation variance value mean, or when the first current fluctuation variance value of the first slave inverter is greater than or equal to the current fluctuation variance value mean, determine that the first slave inverter is a faulty inverter.

[0079] Within the scope of the faulty slave inverter subset, when the voltage or current fluctuation amplitude of the first slave inverter in the faulty slave inverter subset is too large, that is, the first voltage fluctuation variance value of the first slave inverter is greater than or equal to the mean voltage fluctuation variance value, or the first current fluctuation variance value of the first slave inverter is greater than or equal to the mean current fluctuation variance value, the first slave inverter is determined to be a faulty inverter, and the first slave inverter within the scope of the faulty slave inverter subset can be accurately located.

[0080] The beneficial effect of the above-mentioned implementation method is that when the first voltage fluctuation variance value of the first slave inverter is greater than or equal to the mean voltage fluctuation variance value, or when the first current fluctuation variance value of the first slave inverter is greater than or equal to the mean current fluctuation variance value, the first slave inverter is determined to be a faulty inverter, thereby achieving the purpose of further accurately determining the faulty inverter within the scope of the faulty slave inverter subset, and improving the detection accuracy of the faulty inverter.

[0081] Figure 3 A schematic diagram of a flow chart of a third photovoltaic water pump inverter fault detection method provided in an embodiment of the present application, such as Figure 3 As shown, the above method also includes S310 to S320, and S310 to S320 are described in detail below.

[0082] S310. Determine a target slave inverter subset with the smallest fault probability value among multiple slave inverter subsets, and determine the voltage fluctuation variance value of the sequential voltage fluctuation value and the current fluctuation variance value of the sequential current fluctuation value of each slave inverter in the target slave inverter subset, and determine the sum of the voltage fluctuation variance value and the current fluctuation variance value of each slave inverter in the target slave inverter subset as the comprehensive evaluation value of the slave inverter.

[0083] When the inverters are controlled in a master-slave manner, a target slave inverter subset with the smallest fault probability value among multiple slave inverter subsets can be determined, and the slave inverter in the target slave inverter subset has the smallest fault probability, and then the slave inverter can be determined from the target slave inverter subset.

[0084] After obtaining the target slave inverter subset, the voltage fluctuation variance value of the sequential voltage fluctuation value and the current fluctuation variance value of the sequential current fluctuation value of each slave inverter in the target slave inverter subset can be determined, and the sum of the voltage fluctuation variance value and the current fluctuation variance value of each slave inverter in the target slave inverter subset can be determined as the comprehensive evaluation value of the slave inverter. The comprehensive evaluation value of the slave inverter comprehensively characterizes the sum of the voltage fluctuation amplitude and the current fluctuation amplitude of the slave inverter.

[0085] S320, determining a target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset, and using the target slave inverter as a backup master inverter. Obtaining a master inverter failure probability value of the master inverter, and when the master inverter failure probability value is greater than or equal to a preset master inverter failure probability value, switching the backup master inverter to the master inverter.

[0086] After obtaining the slave inverter comprehensive evaluation value of the slave inverter, the target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset can be determined. The target slave inverter is the slave inverter with the smallest failure probability in the target slave inverter subset with the smallest failure probability. The target slave inverter can then be used as a backup master inverter. The backup master inverter can serve as a replacement inverter for the current master inverter, thereby improving the switching speed of the master inverter.

[0087] When controlling the main inverter, the main inverter failure probability value of the main inverter can be obtained. When the main inverter failure probability value is greater than or equal to the preset main inverter failure probability value, the standby main inverter is switched to the main inverter to achieve effective switching of the main inverter.

[0088] Exemplarily, the preset main inverter failure probability value may be 0.6, 0.65 or 0.7.

[0089] The beneficial effect of the above-mentioned implementation method is to determine a target slave inverter subset with the smallest failure probability value among multiple slave inverter subsets, and to determine a target slave inverter with the smallest slave inverter comprehensive evaluation value among the target slave inverter subset as a backup master inverter, so as to improve the switching speed of the backup master inverter and improve the control effect of the master inverter in the master-slave inverter control group.

[0090] Figure 4 A schematic diagram of a fourth photovoltaic water pump inverter fault detection method provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the above method further includes S410 to S420, and S410 to S420 are described in detail below.

[0091] S410. Determine a preset number of target slave inverter subsets whose fault probability values ​​are arranged from small to large in a plurality of slave inverter subsets, determine the communication failure probability between each slave inverter in each target slave inverter subset and the master inverter, and determine the mean communication failure probability of all slave inverters in each target slave inverter subset.

[0092] A communication failure of the slave inverter will also affect the working effect after the slave inverter is switched to the master inverter, and the communication status of the slave inverter can be evaluated to further improve the accuracy of determining the standby master inverter among multiple slave inverters.

[0093] When determining a backup master inverter, a preset number of target slave inverter subsets whose failure probability values ​​are arranged from small to large can be determined among multiple slave inverter subsets. The preset number of target slave inverter subsets are multiple slave inverter subsets with smaller failure probabilities, and then a slave inverter with excellent communication status can be determined among the preset number of target slave inverter subsets as a backup master inverter.

[0094] When determining the backup master inverter, the communication failure probability between each slave inverter and the master inverter in each target slave inverter subset can be determined, and the mean communication failure probability of all slave inverters in each target slave inverter subset can be determined, and the communication status of the target slave inverter subset can be evaluated based on the mean communication failure probability.

[0095] S420, determining a target slave inverter subset with the smallest mean value of communication failure probability among a preset number of target slave inverter subsets, and determining a target slave inverter with the smallest slave inverter comprehensive evaluation value among the target slave inverter subsets, and using the target slave inverter as a backup master inverter.

[0096] After obtaining the mean communication failure probability, a target slave inverter subset with the smallest mean communication failure probability among a preset number of target slave inverter subsets can be determined. The failure probability of the slave inverters in the target slave inverter subset is small and the communication failure probability is minimized, and thus a backup master inverter can be determined in the target slave inverter subset.

[0097] After obtaining the target slave inverter subset, when the target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset can be determined, the target slave inverter can be used as a backup master inverter, and then the slave inverter can be replaced according to the backup master inverter.

[0098] Exemplarily, when determining the target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset, the standby master inverter may be determined according to the method in S310 to S320.

[0099] The beneficial effect of the above-mentioned implementation method is that by determining a target slave inverter subset with the smallest mean communication failure probability among a preset number of target slave inverter subsets, and determining a target slave inverter with the smallest slave inverter comprehensive evaluation value among the target slave inverter subsets, the accuracy of determining the backup master inverter is improved, and the control effect of the master-slave inverter control group is improved.

[0100] In some implementations, in the above S320, obtaining the main inverter failure probability value of the main inverter includes S321 to S322, and S321 to S322 are described in detail below.

[0101] S321. Obtain a fault probability value of a master inverter, and obtain a communication fault probability between the master inverter and a plurality of slave inverters.

[0102] When evaluating the state of the master inverter, the fault probability value of the master inverter can be obtained, and the fault probability value is the working fault probability of the master inverter. At the same time, the communication fault probability of the master inverter and multiple slave inverters can be obtained, and the communication fault probability is the communication fault probability of the master inverter during operation. After obtaining the fault probability value and the communication fault probability, the working state of the master inverter can be evaluated according to the fault probability value and the communication fault probability.

[0103] S322, determining the sum of the product of the first weight factor and the fault probability value and the product of the second weight factor and the communication fault probability as the master inverter fault probability value. The first weight factor is 1 minus the difference between the second weight factor and the master-slave inverter control group output load fluctuations to determine the second weight factor.

[0104] After obtaining the failure probability value and communication failure probability of the main inverter, the sum of the product of the first weight factor and the failure probability value and the product of the second weight factor and the communication failure probability can be determined as the failure probability value of the main inverter, and then whether the main inverter needs to be switched to the backup main inverter can be evaluated based on the failure probability value of the main inverter.

[0105] Exemplarily, the second weight factor is determined according to the output load fluctuation of the master-slave inverter control group. When the output load fluctuation states of the master-slave inverter control group are different, the communication requirements for the master inverter in the master-slave inverter control group are different, and the second weight factor can be adjusted according to the output load fluctuation of the master-slave inverter control group.

[0106] Exemplarily, the first weight factor is a difference between 1 and the second weight factor, so that the first weight factor can be dynamically adjusted according to the value of the second weight factor.

[0107] The beneficial effect of the above-mentioned implementation method is that the working state of the master inverter is evaluated according to the fault probability value and the communication failure probability. When the output load fluctuation states of the master-slave inverter control group are different, the communication requirements for the master inverter in the master-slave inverter control group are different. The second weight factor is adjusted according to the output load fluctuation of the master-slave inverter control group, thereby achieving the accuracy of the evaluation of the working state of the master inverter.

[0108] In some implementations, in the above S322, the second weight factor is determined according to the output load fluctuation of the master-slave inverter control group, including S322a to S322b, and S322a to S322b are specifically described below.

[0109] S322a, obtaining a fluctuation variance value of the output load of the master-slave inverter control group within a preset time period, and obtaining a preset maximum value of the fluctuation variance of the output load of the master-slave inverter control group.

[0110] When determining the second weight factor, the fluctuation variance value of the output load of the master-slave inverter control group within a preset time period can be obtained. The output load of the master-slave inverter control group is the power grid that the master-slave inverter control group needs to output to the power grid. The master-slave inverter control group needs to adjust the output of the master-slave inverter control group according to the demand of the power grid. When adjusting the output of the master-slave inverter control group, the master-slave inverter control group needs to communicate with multiple slave inverters through the master inverter. The level of communication from the master inverter to multiple slave inverters affects the level of communication quality requirements within the master-slave inverter control group. Then, the level of communication quality requirements can be evaluated through the fluctuation variance value of the output load of the master-slave inverter control group within the preset time period.

[0111] After obtaining the fluctuation variance value of the output load of the master-slave inverter control group within the preset time period, the preset maximum fluctuation variance value of the output load of the master-slave inverter control group can be obtained, and the communication quality requirements of the master-slave inverter control group can be evaluated based on the preset maximum fluctuation variance value.

[0112] S322b. Determine a ratio of the volatility variance value to a preset volatility variance maximum value as a second weight factor.

[0113] After obtaining the fluctuation variance value and the preset fluctuation variance maximum value, the ratio of the fluctuation variance value to the preset fluctuation variance maximum value can be determined as a second weight factor, which represents the evaluation of the communication quality requirements of the master-slave inverter control group.

[0114] The beneficial effect of the above-mentioned implementation method is that the communication quality requirements are evaluated by the fluctuation variance value of the output load of the master-slave inverter control group within a preset time period, and the ratio of the fluctuation variance value to the preset fluctuation variance maximum value is determined as the second weight factor, which can improve the accuracy of the dynamic evaluation of the working status of the master inverter.

[0115] Figure 5 A schematic diagram of a fifth photovoltaic water pump inverter fault detection method provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the above method also includes S510 to S520, and S510 to S520 are described in detail below.

[0116] S510: Obtain the number of inverters in the master-slave inverter control group and obtain a threshold value of the number of inverters in the master-slave inverter control group. Determine a ratio between the number of inverters and the threshold value of the number of inverters as an inverter number adjustment factor.

[0117] When evaluating the communication quality requirements of the master-slave inverter control group, the number of inverters in the master-slave inverter control group can also be obtained. The number of inverters represents the communication burden of the master-slave inverter control group, and the communication burden of the master-slave inverter control group can be evaluated by the number of inverters.

[0118] At the same time, the inverter quantity threshold of the master-slave inverter control group can be obtained. The inverter quantity threshold is the maximum inverter quantity corresponding to the master-slave inverter control group. Then, the ratio of the inverter quantity and the inverter quantity threshold can be determined as the inverter quantity adjustment factor. The inverter quantity adjustment factor characterizes the communication burden of the master-slave inverter control group.

[0119] S520: Multiply the second weight factor by the inverter quantity adjustment factor to adjust the second weight factor.

[0120] After the inverter quantity adjustment factor is obtained, the second weight factor may be multiplied by the inverter quantity adjustment factor to adjust the second weight factor, thereby further achieving the purpose of adjusting the second weight factor according to the inverter quantity.

[0121] The beneficial effect of the above-mentioned implementation method is that the second weight factor is multiplied by the inverter quantity adjustment factor, the second weight factor is adjusted, and the communication requirements of the master-slave inverter control group are further evaluated according to the number of inverters, thereby improving the accuracy of determining the standby master inverter of the master-slave inverter control group.

[0122] An embodiment of the present application also provides a fault detection system for a photovoltaic water pump inverter, comprising a unit for executing any of the methods described above.

[0123] Figure 6 A schematic diagram of the logical structure of a fault detection system for a photovoltaic water pump inverter provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0124] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0125] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0127] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0129] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A fault detection method for a photovoltaic water pump inverter, characterized in that: The method comprises: Obtain the time-series broadcast voltage value and the time-series broadcast current value of the master inverter in the master-slave inverter control group, and obtain the time-series output voltage value and the time-series output current value of each slave inverter in the multiple slave inverters of the inverter control group; determine the time-series difference value corresponding to the time-series broadcast voltage value and the time-series output voltage value of each slave inverter as the time-series voltage deviation value; and determine the time-series difference value between the time-series broadcast current value and the time-series output current value of each slave inverter as the time-series current deviation value; Through the inverter state identification model, according to the timing voltage deviation value and the timing current deviation value of the multiple slave inverters in the master-slave inverter control group, the fault probability values ​​corresponding to the multiple slave inverters in the master-slave inverter control group are determined; when the fault probability value of the first slave inverter is greater than the preset fault probability value, the first slave inverter is marked as a faulty slave inverter.

2. The method according to claim 1, characterized in that The method further comprises: Determine the sequential voltage fluctuation value corresponding to the sequential voltage deviation value of each slave inverter, and determine the sequential current fluctuation value corresponding to the sequential current deviation value of each slave inverter; wherein the sequential voltage fluctuation value includes the fluctuation time and fluctuation amplitude of the sequential voltage deviation value, and the sequential current fluctuation value includes the fluctuation time and fluctuation amplitude of the sequential current deviation value; Clustering multiple slave inverters in the master-slave inverter control group according to similar characteristics of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter to obtain multiple slave inverter subsets, and determining the mean value of the sequential voltage fluctuation value and the mean value of the sequential current fluctuation value of the multiple slave inverters in each slave inverter subset; Through the inverter state identification model, the fault probability values ​​corresponding to the multiple slave inverter subsets are determined according to the mean values ​​of the timing voltage deviation values ​​and the mean values ​​of the timing current deviation values ​​of the multiple slave inverter subsets. When the fault probability value of the first slave inverter subset is greater than the preset fault probability value, the first slave inverter subset is marked as a faulty slave inverter subset, and the faulty slave inverter in the faulty slave inverter subset is determined.

3. The method according to claim 2, characterized in that Clustering multiple slave inverters in the master-slave inverter control group is performed according to similar characteristics of the sequential voltage fluctuation value and the sequential current fluctuation value of each slave inverter, including: Obtain the sequential irradiance change value and the sequential temperature change value of the photovoltaic solar panel corresponding to each slave inverter, and determine the first coincidence time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential irradiance change value of each slave inverter, and determine the second coincidence time period of the sequential voltage fluctuation value, the sequential current fluctuation value and the sequential temperature change value; Among the sequential voltage fluctuation values ​​and sequential current fluctuation values ​​of each slave inverter, the sequential voltage fluctuation values ​​and sequential current fluctuation values ​​corresponding to the first coincidence time period and the second coincidence time period are deleted; and multiple slave inverters in the master-slave inverter control group are clustered according to similar characteristics of the sequential voltage fluctuation values ​​and sequential current fluctuation values ​​of each slave inverter.

4. The method according to claim 3, characterized in that A faulty slave inverter in a subset of faulty slave inverters is determined, including: Determine the voltage fluctuation variance value of the sequential voltage fluctuation value and the current fluctuation variance value of the sequential current fluctuation value of each slave inverter in the faulty slave inverter subset; and determine the mean value of the voltage fluctuation variance value and the mean value of the current fluctuation variance value of all slave inverters in the faulty slave inverter subset; When the first voltage fluctuation variance value of the first slave inverter is greater than or equal to the voltage fluctuation variance value mean, or when the first current fluctuation variance value of the first slave inverter is greater than or equal to the current fluctuation variance value mean, the first slave inverter is determined to be a faulty inverter.

5. The method according to claim 4, characterized in that The method further comprises: Determine a target slave inverter subset with the smallest fault probability value among multiple slave inverter subsets, determine a voltage fluctuation variance value of a sequential voltage fluctuation value and a current fluctuation variance value of a sequential current fluctuation value of each slave inverter in the target slave inverter subset, and determine the sum of the voltage fluctuation variance value and the current fluctuation variance value of each slave inverter in the target slave inverter subset as a comprehensive evaluation value of the slave inverter; Determine the target slave inverter with the smallest slave inverter comprehensive evaluation value in the target slave inverter subset, and use the target slave inverter as the backup master inverter; obtain the main inverter failure probability value of the main inverter, and when the main inverter failure probability value is greater than or equal to the preset main inverter failure probability value, switch the backup master inverter to the main inverter.

6. The method according to claim 5, characterized in that The method further comprises: Determine a preset number of target slave inverter subsets whose failure probability values ​​in the multiple slave inverter subsets are arranged from small to large, determine a communication failure probability between each slave inverter in each target slave inverter subset and the master inverter, and determine a mean value of the communication failure probability of all slave inverters in each target slave inverter subset; A target slave inverter subset with the smallest mean value of communication failure probability among a preset number of target slave inverter subsets is determined, and a target slave inverter with the smallest slave inverter comprehensive evaluation value among the target slave inverter subset is determined, and the target slave inverter is used as a backup master inverter.

7. The method according to claim 6, characterized in that Obtain the main inverter failure probability value of the main inverter, including: Obtaining a fault probability value of a master inverter, and obtaining a communication fault probability between the master inverter and a plurality of slave inverters; Determine the sum of the product of the first weight factor and the fault probability value and the product of the second weight factor and the communication fault probability as the main inverter fault probability value; wherein the first weight factor is 1 minus the difference between the second weight factor, and the second weight factor is determined according to the output load fluctuation of the master-slave inverter control group.

8. The method according to claim 7, characterized in that The second weight factor is determined according to the output load fluctuation of the master-slave inverter control group, including: Obtaining a fluctuation variance value of an output load of a master-slave inverter control group within a preset time period, and obtaining a preset maximum value of the fluctuation variance of an output load of the master-slave inverter control group; A ratio of the volatility variance value to a preset volatility variance maximum value is determined as a second weight factor.

9. The method according to claim 8, characterized in that The method further comprises: Obtaining the number of inverters of the master-slave inverter control group and obtaining a threshold value of the number of inverters of the master-slave inverter control group; determining a ratio of the number of inverters to the threshold value of the number of inverters as an inverter number adjustment factor; The second weight factor is multiplied by the inverter quantity adjustment factor to adjust the second weight factor.

10. A fault detection system for a photovoltaic water pump inverter, characterized in that: Comprising means for performing the method according to any one of claims 1 to 9.

Images