Fault analysis method and system for inverter of photovoltaic power generation system

Abstract

The invention relates to the technical field of fault analysis, and discloses a fault analysis method and system for an inverter of a photovoltaic power generation system, and the method comprises the steps: obtaining real-time data information and historical fault information of an inverter to be subjected to fault analysis, and obtaining a stable fault data information sequence, a fluctuation fault data information sequence and a safety data information sequence; analyzing the stable fault data information sequence, the fluctuation fault data information sequence and the safety data information sequence, and calculating a fault analysis coefficient; judging whether a fault exists or not according to the fault analysis coefficient and a preset fault analysis coefficient; and when no fault exists, the next analysis period is calculated, when the fault exists, the early warning level is set according to the fault analysis coefficient and the preset fault analysis coefficient, and the working state of the inverter is monitored and intelligently analyzed in real time, so that the accuracy and efficiency of fault diagnosis are improved, problems can be found in time, and corresponding maintenance measures can be taken. And stable operation and power generation efficiency of the photovoltaic power generation system are ensured.

Description

Technical Field

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

[0002] As the global energy crisis intensifies and environmental awareness increases, solar energy as a clean, renewable energy source is increasingly valued by countries around the world. Photovoltaic power generation is a way of directly converting sunlight into electrical energy using solar cells. It has the advantages of no pollution, no noise, and low operating costs, and has become an important part of the new energy field.

[0003] In the photovoltaic power generation system, the inverter plays a vital role. It converts direct current (DC) into alternating current (AC) to meet the requirements of the power grid or directly supply power to homes and businesses. However, due to the complex and changeable working environment, the inverter may have various faults, such as power device aging, circuit design defects, external environmental factors (such as temperature, humidity, dust, etc.), electromagnetic interference, etc., which may cause the inverter performance to deteriorate or even fail completely.

[0004] Traditional inverter fault diagnosis methods often rely on manual inspection and regular maintenance, which is not only time-consuming and labor-intensive, but also difficult to achieve real-time monitoring and rapid response. In addition, some complex fault phenomena may not be detected by naked eye observation or simple instruments, requiring more accurate and intelligent analysis methods. Summary of the invention

[0005] The embodiment of the present invention provides a fault analysis method and system for an inverter of a photovoltaic power generation system. By real-time monitoring and intelligent analysis of the working status of the inverter, the accuracy and efficiency of fault diagnosis are improved, problems can be discovered in time and corresponding maintenance measures can be taken to ensure the stable operation and power generation efficiency of the photovoltaic power generation system.

[0006] In order to achieve the above object, the present invention provides a fault analysis method for a photovoltaic power generation system inverter, comprising:

[0007] Determine an inverter to be analyzed for faults, obtain real-time data information and historical fault information of the inverter to be analyzed for faults, and obtain a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence, and a safety data information sequence;

[0008] Analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result;

[0009] Determining whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient;

[0010] When it is determined that the inverter to be analyzed for fault has no fault, the next analysis cycle of the inverter to be analyzed for fault is calculated; when it is determined that the inverter to be analyzed for fault has a fault, the warning level is set according to the fault analysis coefficient and the preset fault analysis coefficient.

[0011] Furthermore, before obtaining the data information set according to the real-time data information and the historical fault information, the method further includes:

[0012] Analyze all real-time data information to determine whether there is duplicate real-time data information;

[0013] If yes, extract a duplicate real-time data information and delete the remaining real-time data information;

[0014] Output the data entropy value of each real-time data information based on the pre-trained data entropy value model;

[0015] Obtain a preset data entropy value, and delete all real-time data information that is less than the preset data entropy value;

[0016] Extract all real-time data information that is greater than or equal to the preset data entropy value.

[0017] Further, when acquiring the real-time data information and the historical fault information of the inverter to be analyzed for fault, and obtaining a data information set according to the real-time data information and the historical fault information, it includes:

[0018] Obtaining a preset evaluation value corresponding to the real-time data information;

[0019] Extracting the last historical fault information from the historical fault information, determining the numerical value relationship between the preset evaluation value and the last historical fault information, and determining the first fluctuation value and the second fluctuation value based on the numerical value relationship;

[0020] Determine a fluctuation range according to the first fluctuation value and the second fluctuation value, wherein the first fluctuation value is smaller than the second fluctuation value;

[0021] If the real-time data information is less than or equal to the first fluctuation value, generating the safety data information sequence according to the corresponding real-time data information;

[0022] If the real-time data information is greater than the first fluctuation value, generating a fault mark for the corresponding real-time data information;

[0023] Analyze all historical fault information and determine the abnormal information corresponding to each historical fault information;

[0024] Match the real-time data information that generates the fault identification with all the abnormal information and count the number of matches;

[0025] When the matching number is less than the preset matching number, the fluctuation fault data information sequence is generated according to the corresponding real-time data information;

[0026] When the matching number is greater than or equal to the preset matching number, the stable fault data information sequence is generated according to the corresponding real-time data information.

[0027] Further, when analyzing the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculating the fault analysis coefficient of the inverter to be fault analyzed based on the analysis result, it includes:

[0028] Performing a first processing on the stable fault data information sequence based on a first preset processing method to obtain a first processed information sequence;

[0029] Determine a maximum data value and a minimum data value in the first processing information sequence, and calculate a sum and a difference of the maximum data value and the minimum data value respectively;

[0030] Calculate a first standard processing value of the first processing information sequence according to the sum value and the difference value;

[0031] Processing the stable fault data information sequence for a second time based on a second preset processing method to obtain a second processed information sequence;

[0032] determining a second maximum data value and a second minimum data value in the second processed information sequence, and calculating a second sum and a second difference of the second maximum data value and the second minimum data value, respectively;

[0033] Calculate a second standard processing value of the second processing information sequence according to the second sum value and the second difference value;

[0034] Extracting stable fault data information greater than or equal to the first standard processing value and greater than or equal to the second standard processing value as a sub-stable fault data information sequence;

[0035] Analyze the fluctuation fault data information sequence and the safety data information sequence respectively to determine the corresponding sub-fluctuation fault data information sequence and sub-safety data information sequence;

[0036] The fault analysis coefficient of the inverter to be fault analyzed is calculated according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence.

[0037] Further, when calculating the fault analysis coefficient of the inverter to be fault analyzed according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence, it includes:

[0038] The stable fault coefficient of the sub-stable fault data information sequence is calculated according to the following formula:

[0039]

[0040] Among them, X1 i is the stable fault coefficient of the ith sub-stable fault data information in the sub-stable fault data information sequence, e i is the ith sub-stable fault data information in the sub-stable fault data information sequence, and n1 is the number of sub-stable fault data information in the sub-stable fault data information sequence;

[0041] The fluctuation fault coefficient of the sub-fluctuation fault data information sequence is calculated according to the following formula:

[0042]

[0043] Among them, X2 j is the stable failure coefficient of the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, f j is the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, and n2 is the number of sub-fluctuation fault data information in the sub-fluctuation fault data information sequence;

[0044] The fault analysis coefficient of the inverter to be analyzed is calculated according to the following formula:

[0045]

[0046] Wherein, h is the fault analysis coefficient of the inverter to be fault analyzed, and n3 is the number of sub-safety data information in the sub-safety data information sequence.

[0047] Further, when judging whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient, it includes:

[0048] When the fault analysis coefficient is less than the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed does not have a fault;

[0049] When the fault analysis coefficient is greater than or equal to the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed has a fault.

[0050] Further, when it is determined that the inverter to be analyzed for fault has no fault, the next analysis cycle of the inverter to be analyzed for fault is calculated, including:

[0051] Normalizing the sub-stable fault data information sequence and the sub-fluctuation fault data information sequence, and calculating a normalized mean after the normalization processing;

[0052] The next analysis cycle of the inverter to be analyzed for fault is calculated according to the following formula:

[0053]

[0054] Wherein, T is the next analysis cycle of the inverter to be analyzed for fault, N=n1+n2+n3, g=n1+n2, and q is the normalized mean.

[0055] Further, when it is determined that the inverter to be analyzed for fault has a fault, setting the warning level according to the fault analysis coefficient and the preset fault analysis coefficient includes:

[0056] Calculating a fault analysis coefficient ratio of the fault analysis coefficient and the preset fault analysis coefficient;

[0057] Presetting a first preset warning level, a second preset warning level and a third preset warning level, wherein the first preset warning level is less than the second preset warning level and less than the third preset warning level;

[0058] When 1≤the fault analysis ratio<1.2, the first preset warning level is used as the warning level of the inverter to be analyzed for fault;

[0059] When 1.2≤the fault analysis ratio<1.4, the second preset warning level is used as the warning level of the inverter to be analyzed for fault;

[0060] When 1.4≤the fault analysis ratio, the third preset warning level is used as the warning level of the inverter to be analyzed for fault.

[0061] In order to achieve the above object, the present invention also provides a fault analysis system for a photovoltaic power generation system inverter, comprising:

[0062] The first module is used to determine the inverter to be analyzed for faults, obtain real-time data information and historical fault information of the inverter to be analyzed for faults, and obtain a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence and a safety data information sequence;

[0063] The second module is used to analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result;

[0064] The third module is used to determine whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient;

[0065] The fourth module is used to calculate the next analysis cycle of the inverter to be analyzed for fault analysis when it is determined that there is no fault in the inverter to be analyzed for fault analysis, and to set the warning level according to the fault analysis coefficient and the preset fault analysis coefficient when it is determined that there is a fault in the inverter to be analyzed for fault analysis.

[0066] Furthermore, it also includes:

[0067] An analysis module is used to analyze all real-time data information to determine whether there is duplicate real-time data information;

[0068] A judgment module, for extracting a duplicate real-time data information if yes, and deleting the remaining real-time data information;

[0069] An output model is used to output the data entropy value of each real-time data information based on a pre-trained data entropy value model;

[0070] A deletion module is used to obtain a preset data entropy value and delete all real-time data information that is less than the preset data entropy value;

[0071] The extraction module is used to extract all real-time data information that is greater than or equal to the preset data entropy value.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] Acquire real-time data information and historical fault information of the inverter to be analyzed for fault, and obtain stable fault data information sequence, fluctuating fault data information sequence and safety data information sequence; analyze the stable fault data information sequence, fluctuating fault data information sequence and safety data information sequence, and calculate the fault analysis coefficient; determine whether a fault exists based on the fault analysis coefficient and the preset fault analysis coefficient; when no fault exists, calculate the next analysis cycle; when a fault exists, set the warning level based on the fault analysis coefficient and the preset fault analysis coefficient, and improve the accuracy and efficiency of fault diagnosis by real-time monitoring and intelligent analysis of the working status of the inverter, so as to timely discover problems and take corresponding maintenance measures to ensure the stable operation and power generation efficiency of the photovoltaic power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0075] Figure 1 A schematic flow chart of a fault analysis method for a photovoltaic power generation system inverter in an embodiment of the present invention is shown;

[0076] Figure 2 A schematic structural diagram of a fault analysis system for a photovoltaic power generation system inverter according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0077] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0078] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0079] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0080] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0081] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0082] like Figure 1 As shown, an embodiment of the present invention discloses a fault analysis method for a photovoltaic power generation system inverter, comprising:

[0083] S110: determining an inverter to be analyzed for faults, acquiring real-time data information and historical fault information of the inverter to be analyzed for faults, and obtaining a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence, and a safety data information sequence;

[0084] In this embodiment, the real-time data information includes temperature, voltage, current, vibration frequency, etc.

[0085] In this embodiment, the historical fault information refers to the fault information corresponding to the historical fault behavior. The historical fault behavior refers to the behavior in which the fault occurs. The historical fault behavior may be caused by temperature, and the fault information is the temperature.

[0086] In some embodiments of the present application, before obtaining a data information set according to the real-time data information and the historical fault information, the method further includes:

[0087] Analyze all real-time data information to determine whether there is duplicate real-time data information;

[0088] If yes, extract a duplicate real-time data information and delete the remaining real-time data information;

[0089] Output the data entropy value of each real-time data information based on the pre-trained data entropy value model;

[0090] Obtain a preset data entropy value, and delete all real-time data information that is less than the preset data entropy value;

[0091] Extract all real-time data information that is greater than or equal to the preset data entropy value.

[0092] In this embodiment, the data entropy value model is trained in advance and can output the data entropy value of each real-time data information, that is, the degree of influence of the data information on the inverter.

[0093] The beneficial effect of the above technical solution is that the present invention can obtain effective data information by preprocessing real-time data information, thereby laying a foundation for fault analysis of the inverter.

[0094] In some embodiments of the present application, when acquiring the real-time data information and the historical fault information of the inverter to be analyzed for fault, and obtaining a data information set according to the real-time data information and the historical fault information, it includes:

[0095] Obtaining a preset evaluation value corresponding to the real-time data information;

[0096] Extracting the last historical fault information from the historical fault information, determining the numerical value relationship between the preset evaluation value and the last historical fault information, and determining the first fluctuation value and the second fluctuation value based on the numerical value relationship;

[0097] Determine a fluctuation range according to the first fluctuation value and the second fluctuation value, wherein the first fluctuation value is smaller than the second fluctuation value;

[0098] If the real-time data information is less than or equal to the first fluctuation value, generating the safety data information sequence according to the corresponding real-time data information;

[0099] If the real-time data information is greater than the first fluctuation value, generating a fault mark for the corresponding real-time data information;

[0100] Analyze all historical fault information and determine the abnormal information corresponding to each historical fault information;

[0101] Match the real-time data information that generates the fault identification with all the abnormal information and count the number of matches;

[0102] When the matching number is less than the preset matching number, the fluctuation fault data information sequence is generated according to the corresponding real-time data information;

[0103] When the matching number is greater than or equal to the preset matching number, the stable fault data information sequence is generated according to the corresponding real-time data information.

[0104] In this embodiment, the preset evaluation value refers to a preset standard value, such as the preset evaluation value of temperature is 25°C.

[0105] In this embodiment, the previous historical fault information includes specific fault causes, such as temperature-induced or voltage-induced, and also includes normal data, such as current and the like.

[0106] In this embodiment, the preset judgment value is compared with the previous historical fault information to obtain a larger value and a smaller value. The larger value is used as the second fluctuation value, and the smaller value is used as the first fluctuation value. For example, if the preset judgment value is temperature (25°C), and the fault cause of the previous historical fault information is temperature, specifically 22°C, then the first fluctuation value is 22°C, and the second fluctuation value is 25°C. All temperature values ​​less than 22°C are used as safety data information sequences.

[0107] In this embodiment, the fault information is the specific fault cause mentioned above, such as temperature-induced or voltage-induced.

[0108] The beneficial effect of the above technical solution is that the present invention can provide reliable data support for calculating fault analysis coefficients and ensure calculation accuracy by determining stable fault data information sequences, fluctuating fault data information sequences and safety data information sequences.

[0109] S120: Analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result;

[0110] In some embodiments of the present application, when analyzing the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculating the fault analysis coefficient of the inverter to be fault analyzed based on the analysis result, it includes:

[0111] Performing a first processing on the stable fault data information sequence based on a first preset processing method to obtain a first processed information sequence;

[0112] Determine a maximum data value and a minimum data value in the first processing information sequence, and calculate a sum and a difference of the maximum data value and the minimum data value respectively;

[0113] Calculate a first standard processing value of the first processing information sequence according to the sum value and the difference value;

[0114] Processing the stable fault data information sequence for a second time based on a second preset processing method to obtain a second processed information sequence;

[0115] determining a second maximum data value and a second minimum data value in the second processed information sequence, and calculating a second sum and a second difference of the second maximum data value and the second minimum data value, respectively;

[0116] Calculate a second standard processing value of the second processing information sequence according to the second sum value and the second difference value;

[0117] Extracting stable fault data information greater than or equal to the first standard processing value and greater than or equal to the second standard processing value as a sub-stable fault data information sequence;

[0118] Analyze the fluctuation fault data information sequence and the safety data information sequence respectively to determine the corresponding sub-fluctuation fault data information sequence and sub-safety data information sequence;

[0119] The fault analysis coefficient of the inverter to be fault analyzed is calculated according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence.

[0120] In this embodiment, the difference is the value obtained by taking the absolute value.

[0121] In this embodiment, the first preset processing method is normalization processing, and the first standard processing value=(sum value+difference value) / the number of first processing information sequences.

[0122] In this embodiment, the second difference is a value obtained by taking the absolute value.

[0123] In this embodiment, the second preset processing method is standardization processing, and the second standard processing value=(second sum value+second difference value) / the number of second processing information sequences.

[0124] In this embodiment, data that is greater than or equal to the first standard processing value and greater than or equal to the second standard processing value is extracted, and stable fault data information corresponding to these data is extracted to obtain a sub-stable fault data information sequence.

[0125] In this embodiment, the analysis method of the fluctuating fault data information sequence and the safety data information sequence is the same as that of the stable fault data information sequence, and will not be repeated here.

[0126] The beneficial effect of the above technical solution is: the present invention calculates the fault analysis coefficient of the inverter to be analyzed for fault according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence, thereby ensuring the calculation accuracy of the fault analysis coefficient and avoiding calculation errors caused by manual participation.

[0127] In some embodiments of the present application, when calculating the fault analysis coefficient of the inverter to be fault analyzed according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence, it includes:

[0128] The stable fault coefficient of the sub-stable fault data information sequence is calculated according to the following formula:

[0129]

[0130] Among them, X1 i is the stable fault coefficient of the ith sub-stable fault data information in the sub-stable fault data information sequence, e i is the ith sub-stable fault data information in the sub-stable fault data information sequence, and n1 is the number of sub-stable fault data information in the sub-stable fault data information sequence;

[0131] The fluctuation fault coefficient of the sub-fluctuation fault data information sequence is calculated according to the following formula:

[0132]

[0133] Among them, X2 j is the stable failure coefficient of the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, f j is the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, and n2 is the number of sub-fluctuation fault data information in the sub-fluctuation fault data information sequence;

[0134] The fault analysis coefficient of the inverter to be analyzed is calculated according to the following formula:

[0135]

[0136] Wherein, h is the fault analysis coefficient of the inverter to be fault analyzed, and n3 is the number of sub-safety data information in the sub-safety data information sequence.

[0137] S130: judging whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient;

[0138] In some embodiments of the present application, when judging whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient, the method includes:

[0139] When the fault analysis coefficient is less than the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed does not have a fault;

[0140] When the fault analysis coefficient is greater than or equal to the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed has a fault.

[0141] The beneficial effect of the above technical solution is: the present invention determines whether the inverter to be fault analyzed has a fault based on the relationship between the fault analysis coefficient of the inverter to be fault analyzed and the preset fault analysis coefficient, and can accurately determine whether a fault occurs, thereby improving the accuracy and efficiency of fault diagnosis, and can promptly discover problems and take corresponding maintenance measures to ensure the stable operation and power generation efficiency of the photovoltaic power generation system.

[0142] S140: When it is determined that the inverter to be analyzed for fault has no fault, the next analysis cycle of the inverter to be analyzed for fault is calculated; when it is determined that the inverter to be analyzed for fault has a fault, the warning level is set according to the fault analysis coefficient and the preset fault analysis coefficient.

[0143] In some embodiments of the present application, when it is determined that the inverter to be analyzed for fault does not have a fault, calculating the next analysis cycle of the inverter to be analyzed for fault includes:

[0144] Normalizing the sub-stable fault data information sequence and the sub-fluctuation fault data information sequence, and calculating a normalized mean after the normalization processing;

[0145] The next analysis cycle of the inverter to be analyzed for fault is calculated according to the following formula:

[0146]

[0147] Wherein, T is the next analysis cycle of the inverter to be analyzed for fault, N=n1+n2+n3, g=n1+n2, and q is the normalized mean.

[0148] The beneficial effect of the above technical solution is: the present invention normalizes the sub-stable fault data information sequence and the sub-fluctuation fault data information sequence, calculates the normalized mean after normalization, and calculates the next analysis cycle of the inverter to be analyzed for faults, thereby realizing the dynamic setting of the fault analysis cycle and avoiding the traditional fixed cycle analysis method, which can not only ensure the timeliness of the fault analysis, but also avoid the waste of manpower and material resources.

[0149] In some embodiments of the present application, when it is determined that the inverter to be analyzed for fault has a fault, setting the warning level according to the fault analysis coefficient and the preset fault analysis coefficient includes:

[0150] Calculating a fault analysis coefficient ratio of the fault analysis coefficient and the preset fault analysis coefficient;

[0151] Presetting a first preset warning level, a second preset warning level and a third preset warning level, wherein the first preset warning level is less than the second preset warning level and less than the third preset warning level;

[0152] When 1≤the fault analysis ratio<1.2, the first preset warning level is used as the warning level of the inverter to be analyzed for fault;

[0153] When 1.2≤the fault analysis ratio<1.4, the second preset warning level is used as the warning level of the inverter to be analyzed for fault;

[0154] When 1.4≤the fault analysis ratio, the third preset warning level is used as the warning level of the inverter to be analyzed for fault.

[0155] The beneficial effect of the above technical solution is that the present invention sets different warning levels according to the fault analysis coefficient and the fault analysis coefficient ratio of the preset fault analysis coefficient, which can provide a basis for the work of maintenance personnel, and then implement different maintenance processing plans to improve work efficiency.

[0156] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0157] Correspondingly, such as Figure 2 As shown, the present application also provides a fault analysis system for a photovoltaic power generation system inverter, comprising:

[0158] The first module is used to determine the inverter to be analyzed for faults, obtain real-time data information and historical fault information of the inverter to be analyzed for faults, and obtain a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence and a safety data information sequence;

[0159] The second module is used to analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result;

[0160] The third module is used to determine whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient;

[0161] The fourth module is used to calculate the next analysis cycle of the inverter to be analyzed for fault analysis when it is determined that there is no fault in the inverter to be analyzed for fault analysis, and to set the warning level according to the fault analysis coefficient and the preset fault analysis coefficient when it is determined that there is a fault in the inverter to be analyzed for fault analysis.

[0162] In some embodiments of the present application, it also includes:

[0163] An analysis module is used to analyze all real-time data information to determine whether there is duplicate real-time data information;

[0164] A judgment module, for extracting a duplicate real-time data information if yes, and deleting the remaining real-time data information;

[0165] An output model is used to output the data entropy value of each real-time data information based on a pre-trained data entropy value model;

[0166] A deletion module is used to obtain a preset data entropy value and delete all real-time data information that is less than the preset data entropy value;

[0167] The extraction module is used to extract all real-time data information that is greater than or equal to the preset data entropy value.

[0168] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0169] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0170] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fault analysis method for a photovoltaic power generation system inverter, characterized in that: include: Determine an inverter to be analyzed for faults, obtain real-time data information and historical fault information of the inverter to be analyzed for faults, and obtain a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence, and a safety data information sequence; Analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result; Determining whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient; When it is determined that the inverter to be analyzed for fault has no fault, the next analysis cycle of the inverter to be analyzed for fault is calculated; when it is determined that the inverter to be analyzed for fault has a fault, the warning level is set according to the fault analysis coefficient and the preset fault analysis coefficient.

2. The fault analysis method for a photovoltaic power generation system inverter according to claim 1, characterized in that: Before obtaining a data information set according to the real-time data information and the historical fault information, the method further includes: Analyze all real-time data information to determine whether there is duplicate real-time data information; If yes, extract a duplicate real-time data information and delete the remaining real-time data information; Output the data entropy value of each real-time data information based on the pre-trained data entropy value model; Obtain a preset data entropy value, and delete all real-time data information that is less than the preset data entropy value; Extract all real-time data information that is greater than or equal to the preset data entropy value.

3. The fault analysis method for a photovoltaic power generation system inverter according to claim 1, characterized in that: When acquiring the real-time data information and the historical fault information of the inverter to be analyzed for fault, and obtaining a data information set according to the real-time data information and the historical fault information, it includes: Obtaining a preset evaluation value corresponding to the real-time data information; Extracting the last historical fault information from the historical fault information, determining the numerical value relationship between the preset evaluation value and the last historical fault information, and determining the first fluctuation value and the second fluctuation value based on the numerical value relationship; Determine a fluctuation range according to the first fluctuation value and the second fluctuation value, wherein the first fluctuation value is smaller than the second fluctuation value; If the real-time data information is less than or equal to the first fluctuation value, generating the safety data information sequence according to the corresponding real-time data information; If the real-time data information is greater than the first fluctuation value, generating a fault mark for the corresponding real-time data information; Analyze all historical fault information and determine the abnormal information corresponding to each historical fault information; Match the real-time data information that generates the fault identification with all the abnormal information and count the number of matches; When the matching number is less than the preset matching number, the fluctuation fault data information sequence is generated according to the corresponding real-time data information; When the matching number is greater than or equal to the preset matching number, the stable fault data information sequence is generated according to the corresponding real-time data information.

4. The fault analysis method for a photovoltaic power generation system inverter according to claim 1, characterized in that: When analyzing the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculating the fault analysis coefficient of the inverter to be fault analyzed based on the analysis result, it includes: Performing a first processing on the stable fault data information sequence based on a first preset processing method to obtain a first processed information sequence; Determine a maximum data value and a minimum data value in the first processing information sequence, and calculate a sum and a difference of the maximum data value and the minimum data value respectively; Calculate a first standard processing value of the first processing information sequence according to the sum value and the difference value; Processing the stable fault data information sequence for a second time based on a second preset processing method to obtain a second processed information sequence; determining a second maximum data value and a second minimum data value in the second processed information sequence, and calculating a second sum and a second difference of the second maximum data value and the second minimum data value, respectively; Calculate a second standard processing value of the second processing information sequence according to the second sum value and the second difference value; Extracting stable fault data information greater than or equal to the first standard processing value and greater than or equal to the second standard processing value as a sub-stable fault data information sequence; Analyze the fluctuation fault data information sequence and the safety data information sequence respectively to determine the corresponding sub-fluctuation fault data information sequence and sub-safety data information sequence; The fault analysis coefficient of the inverter to be fault analyzed is calculated according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence.

5. The fault analysis method for a photovoltaic power generation system inverter according to claim 4, characterized in that: When calculating the fault analysis coefficient of the inverter to be fault analyzed according to the sub-stable fault data information sequence, the sub-fluctuation fault data information sequence and the sub-safety data information sequence, it includes: The stable fault coefficient of the sub-stable fault data information sequence is calculated according to the following formula: Among them, X1 i is the stable failure coefficient of the ith sub-stable failure data information in the sub-stable failure data information sequence, e i is the ith sub-stable fault data information in the sub-stable fault data information sequence, and n1 is the number of sub-stable fault data information in the sub-stable fault data information sequence; The fluctuation fault coefficient of the sub-fluctuation fault data information sequence is calculated according to the following formula: Among them, X2 j is the stable failure coefficient of the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, f j is the jth sub-fluctuation fault data information in the sub-fluctuation fault data information sequence, and n2 is the number of sub-fluctuation fault data information in the sub-fluctuation fault data information sequence; The fault analysis coefficient of the inverter to be analyzed is calculated according to the following formula: Wherein, h is the fault analysis coefficient of the inverter to be fault analyzed, and n3 is the number of sub-safety data information in the sub-safety data information sequence.

6. The fault analysis method for a photovoltaic power generation system inverter according to claim 1, characterized in that: When judging whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and the preset fault analysis coefficient, it includes: When the fault analysis coefficient is less than the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed does not have a fault; When the fault analysis coefficient is greater than or equal to the preset fault analysis coefficient, it is determined that the inverter to be fault analyzed has a fault.

7. The fault analysis method for a photovoltaic power generation system inverter according to claim 4, characterized in that: When it is determined that the inverter to be analyzed for fault has no fault, calculating the next analysis cycle of the inverter to be analyzed for fault includes: Normalizing the sub-stable fault data information sequence and the sub-fluctuation fault data information sequence, and calculating a normalized mean after the normalization processing; The next analysis cycle of the inverter to be analyzed for fault is calculated according to the following formula: Wherein, T is the next analysis cycle of the inverter to be analyzed for fault, N=n1+n2+n3, g=n1+n2, and q is the normalized mean.

8. The fault analysis method for a photovoltaic power generation system inverter according to claim 1, characterized in that: When it is determined that the inverter to be analyzed for fault has a fault, setting the warning level according to the fault analysis coefficient and the preset fault analysis coefficient includes: Calculating a fault analysis coefficient ratio of the fault analysis coefficient and the preset fault analysis coefficient; Presetting a first preset warning level, a second preset warning level and a third preset warning level, wherein the first preset warning level is less than the second preset warning level and less than the third preset warning level; When 1≤the fault analysis ratio<1.2, the first preset warning level is used as the warning level of the inverter to be analyzed for fault; When 1.2≤the fault analysis ratio<1.4, the second preset warning level is used as the warning level of the inverter to be analyzed for fault; When 1.4≤the fault analysis ratio, the third preset warning level is used as the warning level of the inverter to be analyzed for fault.

9. A fault analysis system for a photovoltaic power generation system inverter, characterized in that: include: The first module is used to determine the inverter to be analyzed for faults, obtain real-time data information and historical fault information of the inverter to be analyzed for faults, and obtain a data information set according to the real-time data information and the historical fault information, wherein the data information set includes a stable fault data information sequence, a fluctuating fault data information sequence and a safety data information sequence; The second module is used to analyze the stable fault data information sequence, the fluctuating fault data information sequence and the safety data information sequence, and calculate the fault analysis coefficient of the inverter to be analyzed based on the analysis result; The third module is used to determine whether the inverter to be analyzed for fault has a fault according to the relationship between the fault analysis coefficient of the inverter to be analyzed for fault and a preset fault analysis coefficient; The fourth module is used to calculate the next analysis cycle of the inverter to be analyzed for fault analysis when it is determined that there is no fault in the inverter to be analyzed for fault analysis, and to set the warning level according to the fault analysis coefficient and the preset fault analysis coefficient when it is determined that there is a fault in the inverter to be analyzed for fault analysis.

10. The fault analysis system for a photovoltaic power generation system inverter according to claim 9, characterized in that: Also includes: An analysis module is used to analyze all real-time data information to determine whether there is duplicate real-time data information; A judgment module, for extracting a duplicate real-time data information if yes, and deleting the remaining real-time data information; An output model is used to output the data entropy value of each real-time data information based on a pre-trained data entropy value model; A deletion module is used to obtain a preset data entropy value and delete all real-time data information that is less than the preset data entropy value; The extraction module is used to extract all real-time data information that is greater than or equal to the preset data entropy value.

Images