Fault diagnosis method and device of photovoltaic string, electronic equipment and storage medium

Abstract

The application discloses a fault diagnosis method and device of a photovoltaic string, electronic equipment and a storage medium. The method comprises the following steps: acquiring the string current of the string of the photovoltaic power station to be diagnosed on a diagnosis day; performing spatial analysis on the string according to the start-stop time corresponding to the string current, and determining an inefficient string; performing time sequence analysis on the string current of the inefficient string, and determining the fault type of the inefficient string; and the fault type of the photovoltaic string is diagnosed, and work guidance is provided for the operation and maintenance process of the photovoltaic string by the operation and maintenance personnel.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to fault diagnosis methods, devices, electronic equipment and storage media for photovoltaic strings. Background Technology

[0002] A photovoltaic string is formed by connecting several photovoltaic modules in series. The modules convert the sunlight they receive into electrical energy, which is then transmitted through lines. As the basic unit of a photovoltaic power generation system, strings are numerous. In actual operation, abnormal power generation phenomena frequently occur due to quality problems with the modules themselves and the influence of external environmental factors.

[0003] Traditional string maintenance requires manual inspection of strings at the power plant using specialized tools, followed by expert analysis to determine the cause. This approach results in high maintenance costs and long cycles. However, for faults such as hot spots and microcracks inside the modules, specific instruments like thermal imagers can be used with image processing methods to identify the faults.

[0004] However, due to the complexity of actual on-site operating conditions and the variety of power generation curves, string inefficiency faults of different degrees and types are difficult to diagnose. Summary of the Invention

[0005] This invention provides a method, device, electronic equipment, and storage medium for diagnosing faults in photovoltaic strings, enabling the diagnosis of fault types in photovoltaic strings and providing work guidance for operation and maintenance personnel in the operation and maintenance process of photovoltaic strings.

[0006] According to one aspect of the present invention, a fault diagnosis method for photovoltaic strings is provided, comprising:

[0007] Obtain the string current of the photovoltaic power station to be diagnosed on the diagnosis date;

[0008] Based on the start-stop time corresponding to the string current, spatial analysis is performed on the string to identify inefficient strings;

[0009] A timing analysis is performed on the string current of the inefficient string to determine the fault type of the inefficient string.

[0010] According to another aspect of the present invention, a fault diagnosis device for a photovoltaic string is provided, comprising:

[0011] The acquisition module is used to acquire the string current of the photovoltaic power station to be diagnosed on the diagnosis date.

[0012] The spatial analysis module is used to perform spatial analysis on the strings based on the start-stop time corresponding to the string current, and to identify inefficient strings.

[0013] The timing analysis module is used to perform timing analysis on the string current of the inefficient string and determine the fault type of the inefficient string.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fault diagnosis method for photovoltaic strings according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the fault diagnosis method for photovoltaic strings according to any embodiment of the present invention.

[0019] The technical solution of this invention obtains the string current of the photovoltaic power station to be diagnosed on the diagnosis date; performs spatial analysis on the strings based on the start-up and shutdown times corresponding to the string current to identify inefficient strings; and performs time-series analysis on the string current of the inefficient strings to determine the fault type of the inefficient strings. This solves the problem that traditional operation and maintenance methods have difficulty in determining the fault type of inefficient strings, and achieves the beneficial effect of diagnosing the fault type of photovoltaic strings, providing work guidance for operation and maintenance personnel in the operation and maintenance process of photovoltaic strings.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a photovoltaic string fault diagnosis method provided according to Embodiment 1 of the present invention;

[0023] Figure 2This is a flowchart of a photovoltaic string fault diagnosis method provided according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a fault diagnosis device for a photovoltaic string according to Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the fault diagnosis method for photovoltaic strings according to embodiments of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart illustrating a fault diagnosis method for photovoltaic (PV) strings according to Embodiment 1 of the present invention. This embodiment is applicable to diagnosing fault types in PV strings. The method can be executed by a fault diagnosis device for the PV string, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Obtain the string current of the photovoltaic power station to be diagnosed on the diagnosis date.

[0031] Among them, the photovoltaic power station to be diagnosed can refer to photovoltaic equipment waiting for diagnosis. The photovoltaic power station to be diagnosed includes multiple strings, which can be formed by connecting several photovoltaic modules in series.

[0032] The diagnostic date can be understood as the date on which the string current is collected. Since the principle of photovoltaic power generation is to convert light energy into electrical energy, that is, to generate electricity based on sunlight, the diagnostic date can be several natural days within a certain period of time, such as each day within a month, or five days of each month within a year. This embodiment of the invention does not limit the determination and selection of the diagnostic date.

[0033] Specifically, obtain the string current I of the photovoltaic power station to be diagnosed on the diagnosis date. j To reduce data interference, the string current I can also be adjusted. j Data preprocessing is performed, which may include filtering noisy data such as communication dead values, interruptions, and out-of-limit values. To eliminate the impact of different component specifications on power generation in the power plant, the string current I can also be processed. j For the i-th string, perform a reduction based on the string peak power, and select the string with the most component specifications and the highest peak power W. k As the reference peak power, W j The peak power of the string is I', and the summed string current is I'. j ,

[0034] S120. Perform spatial analysis on the strings based on the start-stop times corresponding to the string current to identify inefficient strings.

[0035] Inefficient strings can be understood as strings whose string current is lower than the benchmark generation level of strings under the same conditions. The start-stop time corresponding to the string current can be understood as the start and stop times when the string generates string current, and the start-stop time can reflect the generation status of the string.

[0036] Specifically, spatial analysis of strings based on the start-stop time corresponding to the string current can be considered as determining the spatial orientation of the strings based on the start-stop time corresponding to the string current, classifying the strings according to different orientations to determine the string orientation set, and identifying inefficient strings for each string orientation set.

[0037] S130. Perform timing analysis on the string current of the inefficient string to determine the fault type of the inefficient string.

[0038] The fault types of inefficient strings can be broadly categorized into two types: internal inefficiency faults and external inefficiency faults. Internal inefficiency faults are mainly caused by internal faults such as component aging, resulting in inefficient string power generation. External inefficiency faults are mainly caused by external faults such as shading from attached or unattached objects. Therefore, external inefficiency faults can be further divided into: shading faults from attached objects and shading faults from unattached objects (such as shading from vegetation). Based on the different timing characteristics of different fault types, timing analysis of the string current of inefficient strings can determine the fault type of the inefficient string.

[0039] The technical solution of this invention obtains the string current of the photovoltaic power station to be diagnosed on the diagnosis date; performs spatial analysis on the strings based on the start-up and shutdown times corresponding to the string current to identify inefficient strings; and performs time-series analysis on the string current of the inefficient strings to determine the fault type of the inefficient strings. By combining spatial analysis and time-series analysis methods, the fault type of photovoltaic strings can be diagnosed, solving the problems of insufficient accuracy and practicality caused by single analysis methods, and providing work guidance for operation and maintenance personnel in the operation and maintenance process of photovoltaic strings.

[0040] Optionally, the step of performing spatial analysis on the strings based on the start-stop times corresponding to the string current to determine inefficient strings includes:

[0041] The start-up and stop times are determined based on the string current.

[0042] Based on the start and stop times, each string is clustered by orientation to determine at least one set of strings with the same orientation.

[0043] Based on the Gaussian kernel density estimation algorithm, the reference power generation level corresponding to each string in the set of strings with the same orientation is determined according to the string current.

[0044] For each string in the set of strings with the same orientation, inefficient strings are determined based on the reference power generation level and the string current.

[0045] The reference power generation level corresponding to the string can be understood as the power generation level of the string under normal conditions, that is, the amount of current generated, which serves as a reference benchmark for diagnosing the inefficient state of the string.

[0046] Specifically, based on the obtained string current I' of the photovoltaic power station j Determine the start and stop times (t) of string j sta ,t sto Since strings with different orientations receive light for different durations, their start and stop times also differ. Therefore, strings with roughly the same start and stop times are grouped into strings with the same orientation. This allows for orientation clustering of each string based on its start and stop time, thus identifying at least one set of strings with the same orientation.

[0047] For strings within a set of strings facing the same direction, they should have the same baseline power generation level. Ideally, the probability distribution of the string current at each sampling time on the diagnostic day should roughly follow a Gaussian kernel density distribution. Therefore, based on the Gaussian kernel density estimation algorithm, the baseline power generation level corresponding to each string in the set of strings facing the same direction is determined according to the string current. For strings within the set of strings facing the same direction, inefficient strings can be identified by comparing the string current with the baseline power generation level.

[0048] For example, based on the Gaussian kernel density estimation algorithm, determining the benchmark power generation level corresponding to each string in the set of strings facing the same direction based on the string current can be as follows: using the Gaussian kernel density estimation method, based on the string current I' at each sampling time on the diagnostic day... j Calculate the current value corresponding to the peak density of strings in the same orientation string set, and obtain the string reference power generation level X = [X1, X2, ..., X...]. m ], where X m This represents the maximum probability generator current value at each sampling time (i.e., the z-th sampling time) on the diagnosis day of the m-th orientation string. The Gaussian kernel density function is:

[0049]

[0050]

[0051] Where σ is the standard deviation of the string current in the set of strings with the same orientation, h is the bandwidth of the Gaussian kernel density function, and n is the total number of strings in the m-th set of strings with the same orientation. For the m-th orientation string set at each sampling time t on the diagnosis day n Average current.

[0052] Optionally, the step of clustering each string according to its orientation based on the start and stop times to determine at least one set of strings with the same orientation includes:

[0053] If the orientation of the photovoltaic power station to be diagnosed is known, the start-up and shutdown times of each string are clustered using the K-value nearest neighbor classification algorithm to determine at least one set of strings with the same orientation.

[0054] If the orientation of the photovoltaic power station to be diagnosed is unknown, a threshold nearest neighbor classification algorithm is used to cluster the start and stop times of each string to determine at least one set of strings with the same orientation.

[0055] Specifically, the method for clustering the start and stop times of each string to determine at least one set of strings with the same orientation can be a threshold nearest neighbor classification algorithm or a K-value nearest neighbor classification algorithm.

[0056] If the N types (N>=1) of orientations of the photovoltaic power station to be diagnosed are known, the K-nearest neighbor (KNN) classification algorithm can be used to cluster the start-up and shutdown times of each string. Specifically, this can be done by: determining the start-up and shutdown times of any string corresponding to the known N types of orientations of the photovoltaic power station to be diagnosed; calculating the start-up and shutdown times (t) of the strings to be classified. sta ,t sto The distance between the start and stop times of the string with the known orientation is calculated; the strings are sorted in ascending order of distance; the K points with the smallest distance to the string to be classified are selected; the frequency of the orientation of the first K points is determined; the orientation with the highest frequency among the first K points is returned as the orientation of the string to be classified, and the strings with the desired orientation are grouped into a set of strings with the same orientation.

[0057] If the orientation of the photovoltaic power station to be diagnosed is unknown, the threshold nearest neighbor classification method (i.e., KNN classification algorithm) can be used to cluster the start-up and stop times of each string. Specifically, this can be done as follows: strings with the same start-up and stop times are grouped into a set with the same orientation; the set with the largest number of strings with the same orientation is used as the baseline class, and the start-up and stop times are merged. During merging, strings with start-up and stop times that are earlier or later than a preset time (e.g., the preset time can be 5 minutes) are allowed to be merged into a set with the same orientation; after removing the set with the largest number of strings with the same orientation, the step of merging the start-up and stop times using the set with the largest number of strings with the same orientation as the baseline class is repeated for the remaining strings, and all orientation set types are found in turn (denoted as N classes).

[0058] Optionally, determining inefficient strings based on the reference power generation level and the string current for each of the sets of strings with the same orientation includes:

[0059] For each string in the set of strings with the same orientation, determine the difference sequence between the maximum reference power generation level sampling sequence and the string current sampling sequence of the string on the diagnosis date; the maximum reference power generation level sampling sequence is a sequence composed of the maximum probability power generation current value of the string at each sampling time on the diagnosis date; the string current sampling sequence is a sequence composed of the string current of the string at each sampling time on the diagnosis date.

[0060] If the difference sequence contains a preset number of consecutive sequence points with differences greater than zero, then the string is an inefficient string.

[0061] Specifically, the sampling sequence is based on the maximum baseline power generation level of the string on the diagnosis date. and string current sampling sequence and determine the difference sequence If X m -I m If there are a predetermined number of consecutive sequence points with a difference greater than zero, then the string is an inefficient string.

[0062] The preset number can be determined based on actual needs or experience. For example, a string with three consecutive sequence points with a difference greater than zero is considered an inefficient string. It can also be determined based on the preset time and sampling interval. For example, if the preset time is set to 1 hour and the sampling interval is 10 minutes, then a string with six consecutive sequence points with a difference greater than zero is considered an inefficient string.

[0063] Example 2

[0064] Figure 2 This is a flowchart of a photovoltaic string fault diagnosis method provided in Embodiment 2 of the present invention. This embodiment further refines step S130 of the above embodiment. Figure 2 As shown, the method includes:

[0065] S210. Obtain the string current of the photovoltaic power station to be diagnosed on the diagnosis date.

[0066] S220. Perform spatial analysis on the strings based on the start-stop times corresponding to the string current to identify inefficient strings.

[0067] S230. Determine the set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days based on the string current of the inefficient strings on multiple diagnostic days.

[0068] Among them, the set of inefficient strings in sunny weather can be understood as the set of strings that are inefficient under sunny weather conditions; the set of inefficient strings in non-sunny weather conditions can be understood as the set of strings that are inefficient under non-sunny weather conditions.

[0069] Specifically, based on the string current of each inefficient string on multiple diagnostic days and the weather conditions on the diagnostic days, the inefficient strings are classified into sunny-day inefficient strings or non-sunny-day inefficient strings. Thus, at least one sunny-day inefficient string from the photovoltaic power station to be diagnosed constitutes a sunny-day inefficient string set, and at least one non-sunny-day inefficient string from the photovoltaic power station to be diagnosed constitutes a non-sunny-day inefficient string set.

[0070] S240. Determine the set of inefficient strings for the target fault type based on the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days.

[0071] The target fault types include internal inefficiency faults and external inefficiency faults. The inefficiency strings of internal inefficiency faults and the inefficiency strings of external inefficiency faults have different temporal characteristics. Therefore, the set of inefficiency strings for the target fault type can be determined based on the set of inefficiency strings for sunny days and the set of inefficiency strings for non-sunny days.

[0072] Specifically, the timing characteristics of internal inefficiency faults are as follows: the inefficiency level is less affected by radiation, meaning that the inefficient power generation level is lower than that of normal power generation strings on both sunny and cloudy days, and the internal inefficiency level is relatively stable without abrupt changes. The timing characteristics of foreign object obstruction faults are as follows: the inefficiency level of the affected string is less affected by radiation, meaning that the inefficient power generation level is lower than that of normal power generation strings on both sunny and cloudy days, but the inefficiency level caused by foreign object attachment can have abrupt changes. For example, for strings with bird droppings, there will be abrupt changes in inefficiency depending on the bird's activity patterns; for components with accidentally drifting foreign objects attached, there will be sudden inefficiencies in the string's power generation. The timing characteristics of non-attached object obstruction faults are as follows: components affected by external obstruction (not due to foreign object attachment) are sensitive to radiation; the power generation level on sunny days is significantly lower than that of normal power generation strings, but the power generation level on cloudy days is not significantly different from that of normal power generation strings.

[0073] S250. The target fault type of the inefficient string set is determined as the fault type of the inefficient string in the inefficient string set.

[0074] The technical solution of this invention involves obtaining the string current of the photovoltaic power station to be diagnosed on the diagnosis day; performing spatial analysis on the strings based on the start-up and shutdown times corresponding to the string current to identify inefficient strings; determining a set of inefficient strings for sunny days and a set of inefficient strings for non-sunny days based on the string current of the inefficient strings on multiple diagnosis days; determining a set of inefficient strings with a target fault type based on the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days; identifying the target fault type of the inefficient string set as the fault type of the inefficient strings in the inefficient string set; and performing time-series analysis on the string current of the inefficient strings to determine the fault type of the inefficient strings. This method can diagnose the fault type of photovoltaic strings and provide work guidance for operation and maintenance personnel in the operation and maintenance process of photovoltaic strings.

[0075] Optionally, determining the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days based on the string current of the inefficient strings on multiple diagnostic days includes:

[0076] The inefficient string current time series is determined based on the string current of the inefficient string on multiple diagnostic days.

[0077] The set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days are determined based on the string current time series and the weather conditions on each of the diagnostic days.

[0078] Among them, the inefficient string current time series can be understood as the time series formed by collecting the string current of inefficient strings on multiple diagnostic days.

[0079] Specifically, the string current of the photovoltaic power plant under diagnosis exhibits a certain periodic variation within a single diagnosis day, following natural patterns such as sunrise to sunset or weather conditions. If a string experiences a fault leading to inefficiency, this periodic variation will reflect certain abnormal changes. Furthermore, the abnormal changes in string current exhibited by strings with different fault types differ between sunny and cloudy days. Therefore, it is necessary to collect the string current of inefficient strings over multiple diagnosis days to form a time series of inefficient string currents. Strings exhibiting inefficient power generation characteristics on sunny days are identified as sunny-day inefficient strings; strings exhibiting inefficient power generation characteristics on cloudy days are identified as cloudy-day inefficient strings. It should be noted that an inefficient string can exhibit inefficient power generation characteristics on both sunny and / or cloudy days. Thus, a set of sunny-day inefficient strings is determined based on the sunny-day inefficient strings in the photovoltaic power plant under diagnosis; and a set of cloudy-day inefficient strings is determined based on the cloudy-day inefficient strings in the photovoltaic power plant under diagnosis.

[0080] Optionally, determining the set of strings for the target fault type based on the set of inefficient fault strings for sunny days and the set of inefficient fault strings for non-sunny days includes:

[0081] The intersection of the set of inefficient strings during sunny days and the set of inefficient strings during non-sunny days is determined as the set of internal inefficient faults.

[0082] The set of strings in the set of inefficient strings during sunny days, excluding the set of internal inefficient faults, is determined as the set of inefficient strings with non-attached shading faults.

[0083] The difference set of the inefficient string sets corresponding to two adjacent sunny days is determined as the inefficient string set of the attachment shading fault.

[0084] Specifically, since the main temporal characteristics of internal inefficiency faults are: the inefficiency level is less affected by radiation, meaning that the inefficiency level is lower than that of normal generating strings on both sunny and cloudy days, and the degree of internal inefficiency is relatively stable, the intersection of the set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days is determined as the set of internal inefficiency faults, that is:

[0085] A = M ∩ N;

[0086] Where A is the set of internal inefficient faults, M is the set of inefficient strings on sunny days, and N is the set of inefficient strings on non-sunny days.

[0087] Since the main temporal characteristics of non-attached object shading faults are: components affected by external shading (without foreign objects attached) are sensitive to radiation, resulting in significantly lower power generation levels on sunny days compared to normal power generation strings, but no significant difference on cloudy days compared to normal power generation strings, the set of strings inefficient on sunny days, excluding the aforementioned internal inefficient fault set, is defined as the inefficient string set with non-attached object shading faults.

[0088] B = MA = MM ∩ N;

[0089] Where B is the set of inefficient strings for non-attached object shading faults, M is the set of inefficient strings for sunny days, and N is the set of inefficient strings for non-sunny days.

[0090] Since the main temporal characteristic of the foreign object shading fault is that the inefficiency level of the attached string is less affected by radiation, meaning that the inefficiency level of both sunny and cloudy days is lower than that of the normal generating string, but the inefficiency level caused by foreign object attachment has a sudden change, the difference set of the sets of inefficient strings corresponding to two adjacent sunny days is determined as the set of inefficient strings with foreign object shading fault, that is:

[0091] C = M2 - M1;

[0092] Where C is the set of inefficient strings of attachment occlusion faults, and M1 and M2 are the sets of inefficient strings of sunny days corresponding to two adjacent sunny days.

[0093] Example 3

[0094] Figure 3 This is a schematic diagram of a fault diagnosis device for a photovoltaic string provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0095] The acquisition module is used to acquire the string current of the photovoltaic power station to be diagnosed on the diagnosis date.

[0096] The spatial analysis module is used to perform spatial analysis on the strings based on the start-stop time corresponding to the string current, and to identify inefficient strings.

[0097] The timing analysis module is used to perform timing analysis on the string current of the inefficient string and determine the fault type of the inefficient string.

[0098] Optionally, the time series analysis module includes:

[0099] The first set determination unit is used to determine the set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days based on the string current of the inefficient strings on multiple diagnostic days.

[0100] The second set determination unit is used to determine the set of inefficient strings of the target fault type based on the set of inefficient strings in sunny weather and the set of inefficient strings in non-sunny weather.

[0101] The fault type determination unit is used to determine the target fault type of the inefficient string set as the fault type of the inefficient string in the inefficient string set.

[0102] Optionally, the first set determination unit is specifically used for:

[0103] The inefficient string current time series is determined based on the string current of the inefficient string on multiple diagnostic days.

[0104] The set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days are determined based on the time series of inefficient string currents and the weather conditions on each of the diagnostic days.

[0105] Optionally, the second set-determining unit is specifically used for:

[0106] The intersection of the set of inefficient strings during sunny days and the set of inefficient strings during non-sunny days is determined as the set of internal inefficient faults.

[0107] The set of strings in the set of inefficient strings during sunny days, excluding the set of internal inefficient faults, is determined as the set of inefficient strings with non-attached shading faults.

[0108] The difference set of the inefficient string sets corresponding to two adjacent sunny days is determined as the inefficient string set of the attachment shading fault.

[0109] Optionally, the spatial analysis module includes:

[0110] A start / stop time determination unit is used to determine the start / stop time based on the string current.

[0111] An orientation determination unit is used to perform orientation clustering on each of the strings according to the start and stop times, and determine at least one set of strings with the same orientation.

[0112] The reference power generation level determination unit is used to determine the reference power generation level of each string in the set of strings with the same orientation based on the Gaussian kernel density estimation algorithm and the string current.

[0113] An inefficient string determination unit is used to determine inefficient strings for each string in the set of strings facing the same direction, based on the reference power generation level and the string current.

[0114] Optionally, the orientation determining unit is specifically used for:

[0115] If the orientation of the photovoltaic power station to be diagnosed is known, the start-up and shutdown times of each string are clustered using the K-value nearest neighbor classification algorithm to determine at least one set of strings with the same orientation.

[0116] If the orientation of the photovoltaic power station to be diagnosed is unknown, a threshold nearest neighbor classification algorithm is used to cluster the start and stop times of each string to determine at least one set of strings with the same orientation.

[0117] Optionally, the inefficient string determination unit is specifically used for:

[0118] For each string in the set of strings with the same orientation, determine the difference sequence between the maximum reference power generation level sampling sequence and the string current sampling sequence of the string on the diagnosis date; the maximum reference power generation level sampling sequence is a sequence composed of the maximum probability power generation current value of the string at each sampling time on the diagnosis date; the string current sampling sequence is a sequence composed of the string current of the string at each sampling time on the diagnosis date.

[0119] If the difference sequence contains a preset number of consecutive sequence points with differences greater than zero, then the string is an inefficient string.

[0120] The photovoltaic string fault diagnosis device provided in the embodiments of the present invention can execute the photovoltaic string fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0121] Example 4

[0122] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0123] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as fault diagnosis methods for photovoltaic strings.

[0126] In some embodiments, the photovoltaic string fault diagnosis method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the photovoltaic string fault diagnosis method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the photovoltaic string fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0131] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0132] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0133] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0134] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for fault diagnosis of photovoltaic strings, characterized in that, include: Obtain the string current of the photovoltaic power station to be diagnosed on the diagnosis date; Based on the start-stop time corresponding to the string current, spatial analysis is performed on the string to identify inefficient strings; Time-series analysis is performed on the string current of the inefficient string to determine the fault type of the inefficient string; Time-series analysis is performed on the string current of the inefficient string to determine the fault type of the inefficient string, including: The set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days are determined based on the string current of the inefficient strings on multiple diagnostic days. The set of inefficient strings for the target fault type is determined based on the intersection of the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days; the target fault type includes: internal inefficient faults and non-attached object occlusion faults. The target fault type of the inefficient string set is determined as the fault type of the inefficient string in the inefficient string set.

2. The method according to claim 1, characterized in that, The step of determining the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days based on the string current of the inefficient strings on multiple diagnostic days includes: The inefficient string current time series is determined based on the string current of the inefficient string on multiple diagnostic days. The set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days are determined based on the time series of inefficient string currents and the weather conditions on each of the diagnostic days.

3. The method according to claim 1, characterized in that, The step of determining the set of strings for the target fault type based on the intersection of the set of inefficient strings for sunny days and the set of inefficient strings for non-sunny days includes: The intersection of the set of inefficient strings during sunny days and the set of inefficient strings during non-sunny days is determined as the set of internal inefficient faults. The set of strings in the set of inefficient strings under sunny conditions, excluding the set of internal inefficient faults, is identified as the set of inefficient strings with non-attached object occlusion faults.

4. The method according to claim 1, characterized in that, Performing timing analysis on the string current of the inefficient string to determine the fault type of the inefficient string also includes: The difference set of the inefficient string sets corresponding to two adjacent sunny days is determined as the inefficient string set of the attachment shading fault.

5. The method according to claim 1, characterized in that, The step of performing spatial analysis on the strings based on the start-stop times corresponding to the string current to identify inefficient strings includes: The start-up and stop times are determined based on the string current. Based on the start and stop times, each string is clustered by orientation to determine at least one set of strings with the same orientation. Based on the Gaussian kernel density estimation algorithm, the reference power generation level corresponding to each string in the set of strings with the same orientation is determined according to the string current. For each string in the set of strings with the same orientation, inefficient strings are determined based on the reference power generation level and the string current.

6. The method according to claim 5, characterized in that, The step of clustering each string according to its orientation based on the start and stop times to determine at least one set of strings with the same orientation includes: If the orientation of the photovoltaic power station to be diagnosed is known, the start-up and shutdown times of each string are clustered using the K-value nearest neighbor classification algorithm to determine at least one set of strings with the same orientation. If the orientation of the photovoltaic power station to be diagnosed is unknown, a threshold nearest neighbor classification algorithm is used to cluster the start and stop times of each string to determine at least one set of strings with the same orientation.

7. The method according to claim 5, characterized in that, The step of determining inefficient strings for each of the aforementioned sets of strings facing the same direction, based on the benchmark power generation level and the string current, includes: For each string in the set of strings with the same orientation, determine the difference sequence between the maximum reference power generation level sampling sequence and the string current sampling sequence of the string on the diagnosis date; the maximum reference power generation level sampling sequence is a sequence composed of the maximum probability power generation current value of the string at each sampling time on the diagnosis date; the string current sampling sequence is a sequence composed of the string current of the string at each sampling time on the diagnosis date. If the difference sequence contains a preset number of consecutive sequence points with differences greater than zero, then the string is an inefficient string.

8. A fault diagnosis device for photovoltaic strings, characterized in that, include: The acquisition module is used to acquire the string current of the photovoltaic power station to be diagnosed on the diagnosis date. The spatial analysis module is used to perform spatial analysis on the strings based on the start-stop time corresponding to the string current, and to identify inefficient strings. The timing analysis module is used to perform timing analysis on the string current of the inefficient string and determine the fault type of the inefficient string. The time series analysis module includes: The first set determination unit is used to determine the set of inefficient strings on sunny days and the set of inefficient strings on non-sunny days based on the string current of the inefficient strings on multiple diagnostic days. The second set determination unit is used to determine the set of inefficient strings of the target fault type based on the intersection of the set of inefficient strings in sunny weather and the set of inefficient strings in non-sunny weather; the target fault type includes: internal inefficient fault and non-attached object occlusion fault. The fault type determination unit is used to determine the fault type of the inefficient string set as the fault type of the inefficient string in the inefficient string set.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fault diagnosis method for the photovoltaic string according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the fault diagnosis method for the photovoltaic string according to any one of claims 1-7.

Images