Photovoltaic inverter fan fault diagnosis method, device and electronic equipment

Abstract

The present application discloses a fault diagnosis method, device, and electronic device for a photovoltaic inverter fan, belonging to the field of photovoltaic technology. The method includes: determining a target date as a diagnosis date, obtaining a target maximum power point tracking voltage and a target active power of the target photovoltaic inverter to be diagnosed on the target date; determining a target operating fluctuation characteristic of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power; and comparing the target operating fluctuation characteristic with a first inverter model and a second inverter model to determine a fan fault diagnosis result for the target photovoltaic inverter. The method uses maximum power point tracking voltage and active power data to determine the inverter operating fluctuation characteristic and promptly diagnose inverters with fan faults, thereby helping to promptly eliminate fan faults, avoid derating, and reduce power loss.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic technology, and in particular to a fault diagnosis method, device, and electronic equipment for a photovoltaic inverter fan. Background Art

[0002] Because string-type PV inverters have fans that are directly connected to the outside world, foreign matter often enters and dust accumulates. This leads to a high fan failure rate and frequent inverter derating.

[0003] Existing photovoltaic station monitoring systems are unable to accurately diagnose fan failures in photovoltaic inverters and generally do not issue alarms. Fan failures are highly concealed and difficult for station operation and maintenance personnel to detect. Frequent derating of photovoltaic inverters can easily lead to power loss. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a photovoltaic inverter fan fault diagnosis method, device, and electronic device that can promptly diagnose inverter fan faults, helping to promptly eliminate fan faults, avoid derating, and reduce power loss.

[0005] In a first aspect, the present application provides a method for diagnosing a fault of a photovoltaic inverter fan, the method comprising:

[0006] Determining a target date as a diagnosis date, and obtaining a target maximum power point tracking voltage and a target active power of a target photovoltaic inverter to be diagnosed on the target date;

[0007] determining a target operating fluctuation characteristic of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power;

[0008] Comparing the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter;

[0009] The first inverter model is used to characterize a first operating fluctuation characteristic of the first inverter. The first inverter model is constructed based on a first sample data set of the first inverter on a diagnosis day. The first sample data set includes a first maximum power point tracking voltage and a first active power. The first operating fluctuation characteristic is determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes an inverter with a normally operating fan.

[0010] The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter. The second inverter model is constructed based on a second sample data set of the second inverter on the diagnosis day. The second sample data set includes a second maximum power point tracking voltage and a second active power. The second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power. The second inverter characterizes an inverter with a fan fault.

[0011] According to the photovoltaic inverter fan fault diagnosis method of the present application, by obtaining the target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the diagnosis day, the target operation fluctuation characteristics are determined, and compared with the first inverter model of the non-faulty inverter and the second inverter model of the fan fault, the inverter with the fan fault is diagnosed in time, which helps to eliminate the fan fault in time, avoid the occurrence of derating operation, and reduce power loss.

[0012] According to one embodiment of the present application, comparing the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine the fan fault diagnosis result of the target photovoltaic inverter includes:

[0013] obtaining a first similarity between the target operation fluctuation feature and the first operation fluctuation feature, and obtaining a second similarity between the target operation fluctuation feature and the second operation fluctuation feature;

[0014] If it is determined that the second similarity is greater than the first similarity, it is determined that a fan of the target photovoltaic inverter fails.

[0015] According to one embodiment of the present application, determining the target operating fluctuation characteristics of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power includes:

[0016] Obtaining a target operating trend sequence of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power;

[0017] The target operation trend sequence is subjected to word frequency-inverse document frequency vector conversion to obtain the target operation fluctuation feature.

[0018] According to one embodiment of the present application, obtaining a target operating trend sequence of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power includes:

[0019] Normalizing the target maximum power point tracking voltage and the target active power respectively to obtain a target maximum power point tracking voltage time series and a target active power time series;

[0020] The target maximum power point tracking voltage time series and the target active power time series are difference-calculated to obtain the target operation trend sequence.

[0021] According to one embodiment of the present application, performing word frequency-inverse file frequency vector conversion on the target operation trend sequence to obtain the target operation fluctuation feature includes:

[0022] Performing dimensionality reduction processing, symbolization processing, and discretization processing on the target operation trend sequence in sequence to obtain a target character string;

[0023] The target character string is converted from a word frequency to an inverse file frequency vector to obtain the target operation fluctuation characteristics.

[0024] According to one embodiment of the present application, the second sample data set includes historical sample data and simulation sample data of the second inverter.

[0025] According to one embodiment of the present application, determining the target operating fluctuation characteristics of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power includes:

[0026] performing data processing on the target maximum power point tracking voltage and the target active power according to a target data processing strategy to obtain the target operation fluctuation characteristics;

[0027] The first operating fluctuation characteristic is obtained based on the first maximum power point tracking voltage and the first active power according to the target data processing strategy, and the second operating fluctuation characteristic is obtained based on the second maximum power point tracking voltage and the second active power according to the target data processing strategy.

[0028] According to one embodiment of the present application, determining the target date as the diagnosis date includes:

[0029] Obtaining site irradiation data for the target date;

[0030] Determining a first-order difference of the irradiation data on the target date based on the station irradiation data on the target date;

[0031] When it is determined that the first-order difference of the irradiation data on the target date is less than or equal to a target threshold, the target date is determined to be a diagnosis date.

[0032] In a second aspect, the present application provides a photovoltaic inverter fan fault diagnosis device, the device comprising:

[0033] an acquisition module, configured to determine a target date as a diagnosis date, and acquire a target maximum power point tracking voltage and a target active power of a target photovoltaic inverter to be diagnosed on the target date;

[0034] A first processing module is configured to determine a target operating fluctuation characteristic of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power;

[0035] a second processing module, configured to compare the target operation fluctuation characteristic with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter;

[0036] The first inverter model is used to characterize a first operating fluctuation characteristic of the first inverter. The first inverter model is constructed based on a first sample data set of the first inverter on a diagnosis day. The first sample data set includes a first maximum power point tracking voltage and a first active power. The first operating fluctuation characteristic is determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes an inverter with a normally operating fan.

[0037] The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter. The second inverter model is constructed based on a second sample data set of the second inverter on the diagnosis day. The second sample data set includes a second maximum power point tracking voltage and a second active power. The second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power. The second inverter characterizes an inverter with a fan fault.

[0038] According to the photovoltaic inverter fan fault diagnosis device of the present application, by obtaining the target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the diagnosis day, the target operation fluctuation characteristics are determined, and compared with the first inverter model of non-fault and the second inverter model of fan fault, the inverter with fan fault is diagnosed in time, which helps to eliminate the fan fault in time, avoid the occurrence of derating operation, and reduce power loss.

[0039] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the fault diagnosis method for the photovoltaic inverter fan as described in the first aspect above is implemented.

[0040] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the photovoltaic inverter fan fault diagnosis method as described in the first aspect above.

[0041] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the photovoltaic inverter fan fault diagnosis method as described in the first aspect above.

[0042] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0044] Figure 1 1 is a flow chart of a fault diagnosis method for a photovoltaic inverter fan provided in an embodiment of the present application;

[0045] Figure 2 This is a symbolized target operation trend sequence diagram provided by an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the processing flow of the target data processing strategy provided in the embodiment of the present application;

[0047] Figure 4 1 is a schematic structural diagram of a photovoltaic inverter fan fault diagnosis device provided in an embodiment of the present application;

[0048] Figure 5 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0050] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0051] The photovoltaic inverter fan fault diagnosis method, photovoltaic inverter fan fault diagnosis device, electronic device and readable storage medium provided in the embodiments of the present application are described in detail below with reference to specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0052] The photovoltaic inverter fan fault diagnosis method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0053] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0054] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0055] The photovoltaic inverter fan fault diagnosis method provided in the embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the photovoltaic inverter fan fault diagnosis method. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The photovoltaic inverter fan fault diagnosis method provided in the embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0056] like Figure 1 As shown, the photovoltaic inverter fan fault diagnosis method includes: step 110, step 120 and step 130.

[0057] Step 110: Determine the target date as the diagnosis date, and obtain the target maximum power point tracking voltage and target active power of the target photovoltaic inverter to be diagnosed on the target date.

[0058] The target photovoltaic inverter is a photovoltaic inverter for which fan fault diagnosis is to be performed, and the target photovoltaic inverter may be one of string inverters.

[0059] The target date is the date for fan fault diagnosis, which may be the current date. The target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the target date are obtained, and real-time fault diagnosis is performed on the fan of the target photovoltaic inverter.

[0060] The target date may also be a historical date. The target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the target date are obtained, and it is determined whether a fan failure occurs in the target photovoltaic inverter on the historical date.

[0061] It should be noted that, in actual implementation, fan fault diagnosis is not performed on PV inverters that have faults on the target date to save computing resources.

[0062] In this embodiment, the diagnosis day is related to the operating status of the fan of the target photovoltaic inverter. When the target date is determined to be the diagnosis day, the fan of the target photovoltaic inverter rotates on the target date to detect whether the fan has a fault. When it is not a diagnosis day, the fan of the target photovoltaic inverter does not rotate, and it is impossible to detect whether the fan has a fault.

[0063] For example, the diagnosis day may be a sunny day with high radiation intensity at the station site, the power generation efficiency of the photovoltaic solar panels is high, and the fan of the photovoltaic inverter is in a rotating operation state.

[0064] The target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the target date are obtained, wherein the target maximum power point tracking voltage can be obtained by controlling the solar controller with maximum power point tracking (MPPT).

[0065] Step 120: Determine a target operating fluctuation characteristic of a target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power.

[0066] In this step, the target operating fluctuation characteristics of the target PV inverter on the target date can be determined based on the target maximum power point tracking voltage and target active power of the target PV inverter. Whether the target operating fluctuation characteristics conform to the operating fluctuation characteristics of a normal PV inverter or a PV inverter with a fan failure can be used to determine whether the fan of the target PV inverter has failed.

[0067] It should be noted that, after in-depth research, the inventors of this application discovered for the first time that during the diagnosis day, the photovoltaic solar panels have high power generation efficiency and the fans of the photovoltaic inverters are in a rotating state. When the fan fails, after the active power rises to a certain level, the maximum power point tracking voltage rises, and after the rise, frequent fluctuations occur. The active power fluctuates in the opposite direction to the fluctuation of the maximum power point tracking voltage.

[0068] In this embodiment, the target operation fluctuation characteristics are used to characterize the fluctuation changes of the target maximum power point tracking voltage and the target active power.

[0069] Step 130: Compare the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter.

[0070] Among them, the first inverter model is used to characterize the first operating fluctuation characteristics of the first inverter. The first inverter model is constructed based on the first sample data set of the first inverter on the diagnosis day. The first sample data set includes the first maximum power point tracking voltage and the first active power. The first operating fluctuation characteristics are determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes the inverter with normal operation of the fan.

[0071] The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter. The second inverter model is constructed based on a second sample data set of the second inverter on the diagnosis day. The second sample data set includes a second maximum power point tracking voltage and a second active power. The second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power. The second inverter characterizes an inverter with a fan fault.

[0072] The first inverter model may include first operating fluctuation characteristics of multiple non-faulty first inverters, and the second inverter model may include second operating fluctuation characteristics of multiple second inverters with fan faults. The fan fault types of the multiple second inverters may be different.

[0073] The target operation fluctuation characteristic is used to characterize the fluctuation changes of the target maximum power point tracking voltage and target active power of the target photovoltaic inverter. The first operation fluctuation characteristic is used to characterize the fluctuation changes of the first maximum power point tracking voltage and the first active power of the non-faulty first inverter. The second operation fluctuation characteristic is used to characterize the fluctuation changes of the second maximum power point tracking voltage and the second active power of the second inverter with a fan fault.

[0074] In this embodiment, by comparing the target operating fluctuation characteristics of the target photovoltaic inverter with the first operating fluctuation characteristics in the non-faulty first inverter model and the second operating fluctuation characteristics in the fan faulty second inverter model, it is determined whether the fan of the target photovoltaic inverter has failed, and the fan fault diagnosis result of the target photovoltaic inverter on the target date is obtained. Inverter fan faults that are not shutdown faults can be diagnosed in a timely manner without adding hardware.

[0075] In actual implementation, when a fan fault is diagnosed in the target photovoltaic inverter, the corresponding fault information can be pushed to the operation and maintenance personnel through a work order or other means, so that the operation and maintenance personnel can eliminate the fan fault of the target photovoltaic inverter in time, which helps to reduce the loss of power generation in the station.

[0076] According to the photovoltaic inverter fan fault diagnosis method provided in the embodiment of the present application, the target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the diagnosis day are obtained to determine the target operating fluctuation characteristics, and compared with the first inverter model of the non-faulty inverter and the second inverter model of the fan fault. The inverter with the fan fault is diagnosed in time, which helps to eliminate the fan fault in time, avoid the occurrence of derating operation, and reduce power loss.

[0077] In some embodiments, step 130, comparing the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter, may include:

[0078] Obtaining a first similarity between the target operation fluctuation feature and the first operation fluctuation feature, and obtaining a second similarity between the target operation fluctuation feature and the second operation fluctuation feature;

[0079] When it is determined that the second similarity is greater than the first similarity, it is determined that a fan of the target photovoltaic inverter fails.

[0080] In actual implementation, the first similarity and the second similarity may be cosine similarity between the running fluctuation features, wherein the cosine similarity measures the similarity between two feature vectors by measuring the cosine value of the angle between the two feature vectors.

[0081] In this embodiment, when it is determined that the second similarity is greater than the first similarity, the target operation fluctuation characteristic of the target photovoltaic inverter is more similar to the second operation fluctuation characteristic in the second inverter model of fan failure, and it is determined that the fan of the target photovoltaic inverter has failed.

[0082] When it is determined that the first similarity is greater than the second similarity, the target operation fluctuation characteristic of the target photovoltaic inverter is more similar to the first operation fluctuation characteristic in the non-faulty first inverter model, and it is determined that the fan of the target photovoltaic inverter is not faulty.

[0083] In some embodiments, step 120 of determining a target operating fluctuation characteristic of a target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power may include:

[0084] According to the target data processing strategy, the target maximum power point tracking voltage and target active power are processed to obtain the target operation fluctuation characteristics;

[0085] The first operating fluctuation characteristic is obtained based on the first maximum power point tracking voltage and the first active power according to the target data processing strategy, and the second operating fluctuation characteristic is obtained based on the second maximum power point tracking voltage and the second active power according to the target data processing strategy.

[0086] In this embodiment, the target operating fluctuation characteristic, the first operating fluctuation characteristic, and the second operating fluctuation characteristic are obtained by processing the maximum power point tracking voltage and active power according to the same target data processing strategy. The comparison between the target operating fluctuation characteristic, the first operating fluctuation characteristic, and the second operating fluctuation characteristic is more accurate, which can effectively improve the diagnostic accuracy of the inverter fan fault.

[0087] A specific data processing strategy is introduced below.

[0088] It is understandable that other data processing strategies may also be used to process the maximum power point tracking voltage and active power to obtain corresponding operating fluctuation characteristics.

[0089] In some embodiments, step 120 of determining a target operating fluctuation characteristic of a target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power may include:

[0090] Based on the target maximum power point tracking voltage and target active power, a target operation trend sequence of the target photovoltaic inverter is obtained;

[0091] The target operation trend sequence is converted from word frequency to inverse file frequency vector to obtain the target operation fluctuation characteristics.

[0092] Among them, term frequency-inverse document frequency (TF-IDF) is a commonly used weighting technology used in information retrieval and data mining.

[0093] In this embodiment, the fluctuation of the maximum power point tracking voltage in the target operation trend sequence and the fluctuation of the active power with the fluctuation of the maximum power point tracking voltage are determined through word frequency-inverse file frequency vector conversion, and the target operation fluctuation characteristics are obtained.

[0094] In some embodiments, obtaining a target operating trend sequence of a target photovoltaic inverter based on a target maximum power point tracking voltage and a target active power may include:

[0095] Normalizing the target maximum power point tracking voltage and target active power respectively to obtain the target maximum power point tracking voltage time series and the target active power time series;

[0096] The target maximum power point tracking voltage time series and the target active power time series are difference calculated to obtain the target operation trend series.

[0097] Among them, normalization is a way to simplify calculations. The two dimensional data of target maximum power point tracking voltage and target active power are transformed to obtain a dimensionless time series.

[0098] In this embodiment, after normalization processing is performed to obtain the target maximum power point tracking voltage time series and the target active power time series, the calculation between the target maximum power point tracking voltage and the target active power is simplified, and the target operating trend sequence is obtained by calculating the difference between the target maximum power point tracking voltage time series and the target active power time series.

[0099] In some embodiments, the target operation trend sequence is converted from a word frequency to an inverse file frequency vector to obtain target operation fluctuation characteristics, including:

[0100] The target running trend sequence is processed in turn through dimensionality reduction, symbolization and discretization to obtain the target character string;

[0101] Perform word frequency-inverse file frequency vector conversion on the target string to obtain the target operation fluctuation characteristics.

[0102] In this embodiment, the target operation trend sequence can be subjected to dimensionality reduction processing according to the target compression ratio. The data is easier to process and use in low dimensions, and the relevant operation fluctuation characteristics can be more clearly displayed in the data, which also helps to reduce subsequent computing overhead.

[0103] The target operation trend sequence after dimensionality reduction is symbolically represented, a representation symbol is selected, and the data of the target operation trend sequence is mapped according to the data range splitting point in the selected representation symbol to obtain a symbolized target operation trend sequence.

[0104] Take the example where the selected representation symbols include a, b and c.

[0105] Figure 2 The following is a schematic diagram of a symbolized target operation trend sequence provided by an embodiment of the present application, as shown in FIG. Figure 2 As shown, the data of the target running trend sequence greater than 0.5 is symbolized as c, the data between -0.5 and 0.5 is symbolized as b, and the data less than -0.5 is symbolized as a.

[0106] The symbolized target running trend sequence is discretized to obtain a target character string, for example, the target character string is baabccbc.

[0107] In some embodiments, the second sample data set includes historical sample data and simulation sample data of the second inverter.

[0108] The second inverter represents a photovoltaic inverter with a fan failure. The second sample data set includes historical sample data and simulated sample data. The historical sample data is data such as the maximum power point tracking voltage and active power of the photovoltaic inverter with a fan failure collected from the photovoltaic station. The simulated sample data is data such as the maximum power point tracking voltage and active power of the photovoltaic inverter with a simulated fan failure.

[0109] In this embodiment, by simulating sample data and historical sample data, data such as the maximum power point tracking voltage and active power of various fan fault types can be obtained. The constructed second inverter model can more comprehensively reflect the fluctuation changes between the maximum power point tracking voltage and active power during fan faults, thereby improving the accuracy of fan fault diagnosis.

[0110] In some embodiments, determining the target date as the diagnosis date includes:

[0111] Obtain site irradiation data for the target date;

[0112] Based on the station irradiation data on the target date, determine the first-order difference of the irradiation data on the target date;

[0113] When the first-order difference of the irradiation data on the target date is less than or equal to the target threshold, the target date is determined to be the diagnosis date.

[0114] Among them, the first-order difference is the difference between two consecutive adjacent terms in a discrete function.

[0115] By obtaining the first-order difference of the irradiation data on the target date, we can determine whether the fluctuation of the irradiation data on the target date is regular and whether the fluctuation curve of the irradiation data is stable. The first-order difference of the irradiation data on the target date can reflect the smoothness of the change of the irradiation data on the target date.

[0116] It should be noted that the first-order difference of irradiation data is the absolute value of the difference between two consecutive adjacent irradiation data.

[0117] In this embodiment, when it is determined that the first-order difference of the irradiation data on the target date is less than or equal to the target threshold, the fluctuation pattern of the irradiation data on the target date, the power generation pattern of the photovoltaic solar panel, the gradual improvement of the power generation efficiency, and the fan of the photovoltaic inverter are in a rotating operating state, the fan fault can be diagnosed on the target date.

[0118] A specific embodiment is described below.

[0119] The fault diagnosis process of photovoltaic inverter fans includes: data sample simulation and collection, data processing, model construction, abnormality diagnosis and algorithm output.

[0120] 1. Data sample simulation and collection.

[0121] Various fan failure scenarios are collected and simulated at photovoltaic stations to collect a first sample data set of non-fault conditions and a second sample data set of fault conditions.

[0122] The sample data set includes data such as active power, maximum power point tracking voltage, and irradiation data.

[0123] 2. Data processing.

[0124] Step 1: Determine the diagnosis date.

[0125] Obtain the site irradiation data of the photovoltaic power station, intercept the data from 9:00 to 15:00, calculate the first-order difference of the irradiation data, and determine that the day is a diagnosis day when the absolute value of the first-order difference is less than or equal to the target threshold D.

[0126] First-order difference calculation formula: Diff i =Irr i+1 -Irr i (i∈[9:00,15:00]).

[0127] Diagnosis day judgment condition: Max(abs(Diff i ), D)<=D(i∈[9:00,15:00]).

[0128] Step 2: Obtain the maximum power point tracking voltage and active power data of the faulty and normal inverters on the diagnosis day, and use the normalization formula to normalize the maximum power point tracking voltage and active power respectively to obtain the normalized maximum power point tracking voltage time series Zm and active power time series Zp.

[0129] Step 3: Calculate the difference between the normalized Zm and Zp to obtain the inverter operation trend sequence PM.

[0130] Step 4: Reduce the dimension of the running trend sequence PM and convert the time series PM of length m into a data sequence PM of length w ’ .

[0131] The compression ratio is k=m / w, where w≤m.

[0132] PM=pm1、pm2、...pm m , PM after dimensionality reduction ’ =pm ’ 1.pm ’ 2. ...pm ’ w .

[0133] The dimensionality reduction formula is:

[0134]

[0135] Wherein, i=1, 2, ...w, j=1, 2, ...m.

[0136] Step 5: Symbolize the sequence after dimensionality reduction, select the letter set L = {a, b, c}, map the sequence data according to the splitting points, and map the symbolized sequence data according to the splitting points in the diagram table.

[0137] The symbolized running trend sequence is as follows Figure 2 As shown, it is discretized into a string: baabccbc, and the discretized string is converted into a tf-idf vector.

[0138] 3. Model construction.

[0139] Models of normal and faulty inverters are constructed according to the above data processing method to obtain a first inverter model and a second inverter model.

[0140] 4. Abnormal string diagnosis.

[0141] like Figure 3 As shown, step 1: determine whether the day is a diagnosis day based on meteorological radiation data.

[0142] Step 2: Obtain the target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the diagnosis day.

[0143] Step 3: Clean the target maximum power point tracking voltage and target active power data to remove abnormal values.

[0144] Step 4: Skip the inverter that has a fault on the diagnosis day and do not diagnose it.

[0145] Step 5: Normalize the target maximum power point tracking voltage and target active power after data cleaning.

[0146] Step 6: Use normalized data to construct the inverter operation trend sequence.

[0147] Step 7: Use subsequence method to reduce the dimension of trend data.

[0148] Step 8: Symbolize the data after dimensionality reduction and convert it into a string represented by letters.

[0149] Step 9: Convert the string data into a vector using the tf-idf algorithm.

[0150] Step 10: Calculate the cosine similarity between the converted vector and the first inverter model and the second inverter model respectively.

[0151] Step 11: If the cosine similarity with the abnormal class model is higher, the fault information is pushed.

[0152] Step 12: If the cosine similarity with the normal class model is higher, then load the next inverter for diagnosis.

[0153] 5. Algorithm result output.

[0154] The algorithm program runs diagnostics based on the input inverter data and pushes the diagnostic results to the operation and maintenance personnel through the operation and maintenance system for processing, thus resolving fan failure problems in a timely manner and reducing power generation losses.

[0155] The photovoltaic inverter fan fault diagnosis method provided in the embodiments of the present application can be executed by a photovoltaic inverter fan fault diagnosis device. In the embodiments of the present application, the photovoltaic inverter fan fault diagnosis method is executed by the photovoltaic inverter fan fault diagnosis device as an example to illustrate the photovoltaic inverter fan fault diagnosis device provided in the embodiments of the present application.

[0156] An embodiment of the present application also provides a fault diagnosis device for a photovoltaic inverter fan.

[0157] like Figure 4 As shown, the fault diagnosis device for the photovoltaic inverter fan includes:

[0158] An acquisition module 410 is configured to determine a target date as a diagnosis date and acquire a target maximum power point tracking voltage and a target active power of a target photovoltaic inverter to be diagnosed on the target date;

[0159] A first processing module 420 is configured to determine a target operating fluctuation characteristic of a target photovoltaic inverter based on a target maximum power point tracking voltage and a target active power;

[0160] A second processing module 430 is configured to compare the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter;

[0161] The first inverter model is used to characterize a first operating fluctuation characteristic of the first inverter. The first inverter model is constructed based on a first sample data set of the first inverter on a diagnosis day. The first sample data set includes a first maximum power point tracking voltage and a first active power. The first operating fluctuation characteristic is determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes an inverter with normal fan operation.

[0162] The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter. The second inverter model is constructed based on a second sample data set of the second inverter on the diagnosis day. The second sample data set includes a second maximum power point tracking voltage and a second active power. The second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power. The second inverter characterizes an inverter with a fan fault.

[0163] According to the photovoltaic inverter fan fault diagnosis device provided in the embodiment of the present application, by obtaining the target maximum power point tracking voltage and target active power of the target photovoltaic inverter on the diagnosis day, the target operation fluctuation characteristics are determined, and compared with the first inverter model of the non-faulty inverter and the second inverter model of the fan fault, the inverter with the fan fault is diagnosed in time, which helps to eliminate the fan fault in time, avoid the occurrence of derating operation, and reduce power loss.

[0164] In some embodiments, the second processing module 430 is configured to obtain a first similarity between the target operation fluctuation feature and the first operation fluctuation feature, and obtain a second similarity between the target operation fluctuation feature and the second operation fluctuation feature;

[0165] When it is determined that the second similarity is greater than the first similarity, it is determined that a fan of the target photovoltaic inverter fails.

[0166] In some embodiments, the first processing module 420 is configured to obtain a target operating trend sequence of a target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power;

[0167] The target operation trend sequence is converted from word frequency to inverse file frequency vector to obtain the target operation fluctuation characteristics.

[0168] In some embodiments, the first processing module 420 is configured to perform normalization processing on the target maximum power point tracking voltage and the target active power, respectively, to obtain a target maximum power point tracking voltage time series and a target active power time series;

[0169] The target maximum power point tracking voltage time series and the target active power time series are difference calculated to obtain the target operation trend series.

[0170] In some embodiments, the first processing module 420 is configured to sequentially perform dimensionality reduction processing, symbolization processing, and discretization processing on the target operating trend sequence to obtain a target character string;

[0171] Perform word frequency-inverse file frequency vector conversion on the target string to obtain the target operation fluctuation characteristics.

[0172] In some embodiments, the second sample data set includes historical sample data and simulation sample data of the second inverter.

[0173] In some embodiments, the second processing module 430 is configured to perform data processing on the target maximum power point tracking voltage and the target active power according to the target data processing strategy to obtain a target operation fluctuation characteristic;

[0174] The first operating fluctuation characteristic is obtained based on the first maximum power point tracking voltage and the first active power according to the target data processing strategy, and the second operating fluctuation characteristic is obtained based on the second maximum power point tracking voltage and the second active power according to the target data processing strategy.

[0175] In some embodiments, the acquisition module 410 is configured to acquire the site irradiation data for a target date;

[0176] Based on the station irradiation data on the target date, determine the first-order difference of the irradiation data on the target date;

[0177] When the first-order difference of the irradiation data on the target date is less than or equal to the target threshold, the target date is determined to be the diagnosis date.

[0178] The photovoltaic inverter fan fault diagnosis device in the embodiment of the present application can be an electronic device or a component of the electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other devices other than a terminal. For example, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc. It can also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiment of the present application does not specifically limit it.

[0179] The photovoltaic inverter fan fault diagnosis device in the embodiment of the present application can be a device having an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0180] The photovoltaic inverter fan fault diagnosis device provided in the embodiment of the present application can achieve Figures 1 to 3 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0181] In some embodiments, as Figure 5As shown, an embodiment of the present application further provides an electronic device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the program is executed by the processor 501, each process of the above-mentioned photovoltaic inverter fan fault diagnosis method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0182] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0183] An embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned photovoltaic inverter fan fault diagnosis method embodiment are implemented, and the same technical effects can be achieved. To avoid repetition, they are not further described here.

[0184] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0185] An embodiment of the present application further provides a computer program product, including a computer program, which implements the above-mentioned photovoltaic inverter fan fault diagnosis method when executed by a processor.

[0186] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0187] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, which is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-mentioned photovoltaic inverter fan fault diagnosis method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0188] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0189] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0190] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0191] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0192] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0193] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A fault diagnosis method for a photovoltaic inverter fan, characterized in that: include: Determining a target date as a diagnosis date, and obtaining a target maximum power point tracking voltage and a target active power of a target photovoltaic inverter to be diagnosed on the target date; determining a target operating fluctuation characteristic of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power; Comparing the target operation fluctuation characteristics with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter; The first inverter model is used to characterize a first operating fluctuation characteristic of the first inverter. The first inverter model is constructed based on a first sample data set of the first inverter on a diagnosis day. The first sample data set includes a first maximum power point tracking voltage and a first active power. The first operating fluctuation characteristic is determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes an inverter with a normally operating fan. The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter, the second inverter model is constructed based on a second sample data set of the second inverter on a diagnosis day, the second sample data set includes a second maximum power point tracking voltage and a second active power, the second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power, and the second inverter characterizes an inverter with a fan fault; The determining, based on the target maximum power point tracking voltage and the target active power, a target operating fluctuation characteristic of the target photovoltaic inverter includes: Obtaining a target operating trend sequence of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power; Performing word frequency-inverse document frequency vector conversion on the target operation trend sequence to obtain the target operation fluctuation characteristics; By converting the word frequency to the inverse document frequency vector, the fluctuation of the maximum power point tracking voltage in the target operation trend sequence and the fluctuation of the active power along with the fluctuation of the maximum power point tracking voltage are determined to obtain the target operation fluctuation characteristics.

2. The photovoltaic inverter fan fault diagnosis method according to claim 1, characterized in that: The comparing the target operation fluctuation characteristic with the first inverter model and the second inverter model to determine the fan fault diagnosis result of the target photovoltaic inverter includes: obtaining a first similarity between the target operation fluctuation feature and the first operation fluctuation feature, and obtaining a second similarity between the target operation fluctuation feature and the second operation fluctuation feature; If it is determined that the second similarity is greater than the first similarity, it is determined that a fan of the target photovoltaic inverter fails.

3. The photovoltaic inverter fan fault diagnosis method according to claim 1, characterized in that: The step of obtaining a target operation trend sequence of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power includes: Normalizing the target maximum power point tracking voltage and the target active power respectively to obtain a target maximum power point tracking voltage time series and a target active power time series; The target maximum power point tracking voltage time series and the target active power time series are difference-calculated to obtain the target operation trend sequence.

4. The photovoltaic inverter fan fault diagnosis method according to claim 1, characterized in that: The performing word frequency-inverse file frequency vector conversion on the target operation trend sequence to obtain the target operation fluctuation characteristics includes: Performing dimensionality reduction processing, symbolization processing, and discretization processing on the target operation trend sequence in sequence to obtain a target character string; The target character string is subjected to word frequency-inverse file frequency vector conversion to obtain the target operation fluctuation characteristics.

5. The photovoltaic inverter fan fault diagnosis method according to any one of claims 1 to 4, characterized in that: The second sample data set includes historical sample data and simulation sample data of the second inverter.

6. The photovoltaic inverter fan fault diagnosis method according to any one of claims 1 to 4, characterized in that: The determining, based on the target maximum power point tracking voltage and the target active power, a target operating fluctuation characteristic of the target photovoltaic inverter includes: performing data processing on the target maximum power point tracking voltage and the target active power according to a target data processing strategy to obtain the target operation fluctuation characteristics; The first operating fluctuation characteristic is obtained based on the first maximum power point tracking voltage and the first active power according to the target data processing strategy, and the second operating fluctuation characteristic is obtained based on the second maximum power point tracking voltage and the second active power according to the target data processing strategy.

7. The photovoltaic inverter fan fault diagnosis method according to any one of claims 1 to 4, characterized in that: The target date is the diagnosis date, including: Obtaining site irradiation data for the target date; Determining a first-order difference of the irradiation data on the target date based on the station irradiation data on the target date; When it is determined that the first-order difference of the irradiation data on the target date is less than or equal to a target threshold, the target date is determined to be a diagnosis date.

8. A fault diagnosis device for a photovoltaic inverter fan, characterized in that: include: an acquisition module, configured to determine a target date as a diagnosis date, and acquire a target maximum power point tracking voltage and a target active power of a target photovoltaic inverter to be diagnosed on the target date; A first processing module is configured to determine a target operating fluctuation characteristic of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power; a second processing module, configured to compare the target operation fluctuation characteristic with the first inverter model and the second inverter model to determine a fan fault diagnosis result of the target photovoltaic inverter; The first inverter model is used to characterize a first operating fluctuation characteristic of the first inverter. The first inverter model is constructed based on a first sample data set of the first inverter on a diagnosis day. The first sample data set includes a first maximum power point tracking voltage and a first active power. The first operating fluctuation characteristic is determined based on the first maximum power point tracking voltage and the first active power. The first inverter characterizes an inverter with a normally operating fan. The second inverter model is used to characterize a second operating fluctuation characteristic of the second inverter, the second inverter model is constructed based on a second sample data set of the second inverter on a diagnosis day, the second sample data set includes a second maximum power point tracking voltage and a second active power, the second operating fluctuation characteristic is determined based on the second maximum power point tracking voltage and the second active power, and the second inverter characterizes an inverter with a fan fault; The first processing module, configured to determine the target operating fluctuation characteristics of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power, includes: Obtaining a target operating trend sequence of the target photovoltaic inverter based on the target maximum power point tracking voltage and the target active power; Performing word frequency-inverse document frequency vector conversion on the target operation trend sequence to obtain the target operation fluctuation characteristics; By converting the word frequency to the inverse document frequency vector, the fluctuation of the maximum power point tracking voltage in the target operation trend sequence and the fluctuation of the active power along with the fluctuation of the maximum power point tracking voltage are determined to obtain the target operation fluctuation characteristics.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the photovoltaic inverter fan fault diagnosis method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the fault diagnosis method for a photovoltaic inverter fan according to any one of claims 1 to 7 is implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the fault diagnosis method for a photovoltaic inverter fan according to any one of claims 1 to 7 is implemented.

Images