A Fault Detection System for Complex Terrain Photovoltaic Arrays Based on Machine Learning

Abstract

The present invention discloses a complex terrain photovoltaic array fault detection system based on machine learning. The detection system groups and detects faults in multiple sub-arrays in the photovoltaic array through a grouping module and an analysis module. The grouping module divides sub-arrays with similar environmental conditions into the same group based on the geographical location, terrain features, and power generation trends of each sub-array to form multiple array groups. The grouping module uses machine learning algorithms to train a grouping model, thereby achieving dynamic and accurate grouping. Each array group applies adapted fault detection parameters to monitor the array group in real time. Among them, the grouping module includes a Party A information unit and a Party B information unit, which store the geographical and installation information of the sub-arrays, as well as real-time power generation data, to synthesize environmental and power generation conditions.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy applications, and more particularly, relates to a complex terrain photovoltaic array fault detection system based on machine learning. Background Art

[0002] With the popularization of photovoltaic power generation technology, more and more large-scale photovoltaic arrays are installed on complex terrains, such as mountains, hills, and building roofs. However, the differences in geographical location, orientation, slope, and shading conditions brought about by complex terrains significantly affect the power generation efficiency of photovoltaic panels, posing challenges to traditional fault detection systems. In such scenarios, the output characteristics of photovoltaic panels are no longer uniform. Therefore, if fixed detection criteria are adopted, it is very likely to result in misjudgment or missed judgment. In addition, with the expansion of the scale of photovoltaic power generation systems, traditional methods relying on manual detection or single criteria are difficult to meet the requirements of efficient and accurate fault detection. The fault detection system based on machine learning can dynamically adjust the detection criteria according to the geographical and power generation characteristics of each sub-array. By grouping and fault detecting complex terrain photovoltaic arrays through machine learning, not only the accuracy of fault detection is improved, but also the maintenance cost can be reduced, realizing intelligent and automated management of photovoltaic arrays, providing technical support for the popularization and application of photovoltaic power generation systems in complex scenarios.

[0003] Referring to relevant disclosed technologies, the technical solution with the publication number CN116388669A proposes a method for detecting foreign objects on photovoltaic panels based on the Swin Transformer algorithm, which identifies foreign objects on photovoltaic panels through a high-definition camera, calculates their positions and pollution degrees, and thus makes corresponding countermeasures. The technical solution with the publication number WO2015070482A1 proposes a low-voltage ride-through detection system for large-scale photovoltaic power plants in high-altitude areas, which can continuously detect large-scale photovoltaic power plants by using mobile detection equipment carried in containers. The technical solution with the publication number US20130285670A1 proposes a photovoltaic fault detection system, which can determine the positions of specific modules with faults in a photovoltaic array by connecting multiple detectors to the output end of the photovoltaic system.

[0004] The above technical solutions all propose various detection technical solutions for photovoltaic systems. However, for the scene complexity of photovoltaic systems in complex terrains, the accuracy and detection efficiency of using a single detection algorithm for large-scale faults still need to be improved.

[0005] The foregoing discussion of the background art is only intended to facilitate the understanding of the present invention. This discussion does not recognize or admit any part of the common general knowledge in the materials mentioned. Summary of the Invention

[0006] The object of the present invention is to provide a complex terrain photovoltaic array fault detection system based on machine learning. The detection system groups and detects multiple sub-arrays in the photovoltaic array through a grouping module and an analysis module. The grouping module divides sub-arrays with similar environmental conditions into the same group based on the geographical location, terrain features, and power generation trends of each sub-array, so as to form multiple array groups. The grouping module uses machine learning algorithms to train the grouping model, thereby achieving dynamic and accurate grouping. Each array group applies appropriate fault detection parameters to monitor the array group in real time. Among them, the grouping module includes a Party A information unit and a Party B information unit, which store the geographical and installation information of the sub-arrays and real-time power generation data respectively to integrate the environment and power generation conditions.

[0007] The present invention adopts the following technical solutions: A complex terrain photovoltaic array fault detection system based on machine learning, the detection system is configured to connect to an existing photovoltaic power generation system and group and detect multiple sub-arrays according to the power generation data of multiple sub-arrays in the photovoltaic array to form multiple array groups, and use corresponding fault detection models for each array group for fault detection; the detection system includes:

[0008] A grouping module, configured to group multiple sub-arrays in the photovoltaic power generation system based on the following two conditions to form one or more of the above-mentioned array groups:

[0009] (1) The geographical location and terrain features of each photovoltaic module in each sub-array;

[0010] (2) The power generation trend of each sub-array in the same period of the real-time past;

[0011] An analysis module, configured to use a fault detection program to perform fault detection on one or more of the above-mentioned array groups to determine whether there is an abnormality in the working state of each array group;

[0012] Among them, the grouping module applies machine learning algorithms to train the grouping model, and applies the grouping model to group multiple sub-arrays to establish multiple array groups.

[0013] Preferably, the grouping module includes a Party A information unit; the Party A information unit includes:

[0014] A geographical data storage component, configured to store the geographical location data of each photovoltaic module;

[0015] An installation data storage component, configured to store the installation parameter data of each photovoltaic module;

[0016] An environmental data acquisition component, configured to acquire real-time environmental data.

[0017] Preferably, the grouping module further includes a B information unit; the B information unit includes:

[0018] A power generation data acquisition component configured to acquire the power generation data of each of the sub-arrays; the power generation data includes at least the daily power generation amount, and the average output power and average output voltage based on time series.

[0019] A power generation data storage component configured to store the historical power generation data of each of the sub-arrays.

[0020] Preferably, the grouping module further includes a grouping unit; the grouping unit is configured to train the grouping model based on the latest information data provided by the A information unit and the B information unit.

[0021] Preferably, the grouping module includes dissolving the established array groups and regrouping them at a subsequent stage.

[0022] Preferably, the grouping module includes using a clustering algorithm to perform the following grouping steps to group multiple sub-arrays:

[0023] S100: Preprocess the information data of each sub-array;

[0024] S200: Randomly select sub-arrays for grouping to form initial array groups and initialize the clustering centers;

[0025] S300: Calculate the similarity between each photovoltaic sub-array and each clustering center;

[0026] S400: Assign each sub-array to the array group belonging to the nearest clustering center according to the minimum distance principle;

[0027] S500: Update the clustering centers according to the photovoltaic sub-arrays within each array group;

[0028] S600: Repeat steps S300 to S500 until the change in the clustering centers is less than a preset threshold.

[0029] The beneficial effects achieved by the present invention are:

[0030] 1. The detection system of the present technical solution performs dynamic grouping based on multi-dimensional data such as geographical location and power generation trend. This system can adjust the detection criteria for complex terrain conditions, reduce misjudgment and missed judgment, and improve the accuracy of fault detection; in complex terrain scenarios, the system can flexibly adapt to geographical and environmental differences and achieve accurate analysis of the sub-array status.

[0031] 2. The detection system of this technical solution utilizes machine learning algorithms to automatically update the weights of each feature in the grouping model when the environment changes or the system conditions are altered. When there are, for example, weather changes or local occlusions, the system can adaptively adjust the grouping to maintain the detection efficiency.

[0032] 3. The detection system of this technical solution reduces the dependence on manual inspections by using automation technology, significantly reducing the maintenance cost and being able to adapt to the fault detection work of large-scale photovoltaic systems in complex terrain applications.

[0033] 4. Each working part in the detection system of this technical solution adopts a modular design. The system's maintenance and upgrade can be achieved by separately optimizing and replacing the working modules, reducing the subsequent usage cost and upgrade cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention can be further understood from the following description in conjunction with the drawings. The components in the drawings are not necessarily drawn to scale, but the emphasis is placed on showing the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0035] Explanation of the reference numerals in the drawings: 1 - Photovoltaic power generation system; 11 - Photovoltaic panel; 12 - Photovoltaic sub-array; 13 - Photovoltaic array; 14 - Inverter; 15 - Connector; 16 - Grouping module; 18 - Analysis module; 21 - Main line of the sub-array; 31 - Left laying surface; 32 - Right laying surface; 500 - Computing architecture; 502 - Bus; 504 - Processor; 506 - Main memory; 508 - Read-only memory; 510 - Storage device; 512 - Display; 514 - Input device; 516 - Cursor control device; 518 - Network device;

[0036] Figure 1 It is a layout schematic diagram of the detection system described in the embodiment of the present invention;

[0037] Figure 2 It is an architecture schematic diagram of the detection system described in the embodiment of the present invention;

[0038] Figure 3 It is a layout schematic diagram of the photovoltaic array in complex terrain in the embodiment of the present invention;

[0039] Figure 4 It is a comparison chart of the detection accuracy rate after adopting the present detection system in the embodiment of the present invention;

[0040] Figure 5 It is an architecture schematic diagram of the computer system adopted in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to make the object, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. For those skilled in the art, after referring to the following detailed description, other systems, methods, and / or features of this embodiment will become obvious. It is intended that all such additional systems, methods, features, and advantages be included within this specification, be included within the scope of the present invention, and be protected by the appended claims. Additional features of the disclosed embodiments are described in the following detailed description and will be obvious from the following detailed description.

[0042] In the drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the drawings. This is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only for illustrative purposes and cannot be understood as a limitation of this patent. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0043] Embodiment 1: Exemplarily, as shown in the appendix Figure 1 shown, an exemplary complex terrain photovoltaic array fault detection system based on machine learning is proposed. The detection system is configured to be connected to an existing photovoltaic power generation system 1 and perform grouped detection on multiple sub-arrays according to the power generation data of multiple photovoltaic sub-arrays in the photovoltaic power generation system to form multiple array groups, and perform fault detection on each array group using a corresponding fault detection model; the detection system includes:

[0044] A grouping module 16, configured to group multiple sub-arrays in the photovoltaic power generation system based on the following two conditions to form one or more of the above array groups:

[0045] (3) The geographical location and terrain characteristics of each photovoltaic module in each sub-array;

[0046] (4) The power generation trend of each sub-array in the same period in real time in the past;

[0047] An analysis module 18, configured to perform fault detection on one or more of the above array groups using a fault detection program to determine whether there is an abnormality in the working state of each array group;

[0048] Among them, the grouping module 16 trains a grouping model by applying a machine learning algorithm, and groups the multiple sub-arrays by applying the grouping model to establish multiple array groups.

[0049] Preferably, the grouping module 16 includes a first information unit; the first information unit includes:

[0050] A geographic data storage component configured to store geographic location data of each photovoltaic module;

[0051] An installation data storage component configured to store installation parameter data of each photovoltaic module;

[0052] An environmental data acquisition component configured to acquire real-time environmental data.

[0053] Preferably, the grouping module 16 further includes a second information unit; the second information unit includes:

[0054] A power generation data acquisition component configured to acquire power generation data of each sub-array; the power generation data at least includes daily power generation, as well as average output power and average output voltage based on time series;

[0055] A power generation data storage component configured to store historical power generation data of each sub-array.

[0056] Preferably, the grouping module 16 further includes a grouping unit; the grouping unit is configured to train the grouping model based on the latest information data provided by the first information unit and the second information unit.

[0057] Preferably, the grouping module includes dissolving the established array groups and regrouping them at a subsequent stage.

[0058] Preferably, the grouping module 16 includes using a clustering algorithm to perform the following grouping steps to group multiple sub-arrays:

[0059] S100: Preprocess the information data of each sub-array;

[0060] S200: Randomly select sub-arrays for grouping to form initial array groups and initialize the clustering centers;

[0061] S300: Calculate the similarity between each photovoltaic sub-array and each clustering center;

[0062] S400: Assign each sub-array to the array group belonging to the nearest clustering center according to the minimum distance principle;

[0063] S500: Update the clustering centers according to the photovoltaic sub-arrays within each array group;

[0064] S600: Repeat steps S300 to S500 until the change in the clustering center is less than a preset threshold.

[0065] As shown in the appendix Figure 2 illustrates a schematic layout of the detection system; among them, the photovoltaic power generation system 1 is a device that generates electrical energy using solar light energy; the smallest independent unit of the photovoltaic power generation system is a single photovoltaic panel 11, and multiple photovoltaic panels 11 can be assembled into a photovoltaic sub-array 12; two or more groups of the photovoltaic sub-arrays 12 are combined to form a photovoltaic array 13; multiple photovoltaic arrays 13 can be combined to form an overall photovoltaic power generation system; the photovoltaic power generation system in this technical solution not only refers to a photovoltaic power station installed on the ground, but also refers to various types of photovoltaic power generation systems installed on building roofs, water surfaces, mountains, hillsides and other complex terrains, such as building integrated photovoltaic systems (BIPV).

[0066] Furthermore, in an exemplary embodiment, two or more photovoltaic panels 11 are connected in series to form a photovoltaic sub-array 12; in the case of large-scale solar power generation, dozens to hundreds or more of the photovoltaic sub-arrays 12 can be set; after multiple photovoltaic sub-arrays 12 are connected by a sub-array main line 21 connector 15, they are then connected to an inverter 14 in a circuit to transmit the generated power to the inverter 14 through a 6-channel or 12-channel line, and the inverter 14 is used to convert the direct current generated by the photovoltaic panels into alternating current such as 220V to provide to the electrical load;

[0067] In a preferred embodiment, the sub-array main line 21 of each photovoltaic sub-array 12 is further connected to a grouping module 16 through a branch circuit, and the grouping module 16 performs the grouping and detection steps in this detection system.

[0068] Furthermore, as shown in the appendix Figure 3 illustrates an implementation method of dynamic grouping in an embodiment of a photovoltaic array with two slopes; this method may be an abstraction of an implementation scenario on a hillside or a roof, and is only used as an example here for illustration, not as a restrictive implementation means of this technical solution.

[0069] Optionally, a photovoltaic sub-array can be defined as formed by multiple photovoltaic modules in a single row. For example, a photovoltaic sub-array can be formed by 4 photovoltaic modules of 1×4, or can be in the form of 1×6 or 1×8, etc.; in more definitions of photovoltaic sub-arrays, it can be formed by, for example, 2×2, 2×4, 3×3, 3×4, 4×4, etc. to define a photovoltaic sub-array; this definition method can be defined by technicians according to the geographical environment, lighting environment or line conditions when applying this technical solution, rather than a limitation of this technical solution.

[0070] Further, as shown in the appendix Figure 3 , it has a left laying surface 31 and a right laying surface 32; there is an included angle between the two laying surfaces, such that the orientations of the photovoltaic modules on the two laying surfaces are also correspondingly different; 3 sub-arrays are provided on both laying surfaces, namely 31a, 31b, and 31c on the left laying surface 31; and 32a, 32b, and 32c on the right laying surface 32.

[0071] When the sun 34 is in the position as shown in the appendix Figure 3 , that is, on the side of the left laying surface 31, the left laying surface 31 can obtain relatively good illumination; although during laying, pre-calculation can be performed to set the orientation angles of the respective sub-arrays on the right laying surface 32 as much as possible according to the running trajectory of the sun 34 in order to obtain the maximum sunlight conditions, however, due to the actual complex terrain or the limitation of the laying ground, the right laying surface 32 can never provide the same light-receiving conditions as the left laying surface 31;

[0072] In the working condition as shown in the appendix Figure 3 , the three sub-arrays 31a, 31b, and 31c on the left laying surface 31 all have relatively similar illumination working conditions. At this time, the angles at which the three sub-arrays receive sunlight are all relatively small and are relatively close to each other. Therefore, they can be grouped into the same array group.

[0073] On the other hand, since the left laying surface 31 itself has a relatively large included angle with the current sunlight irradiation, the included angles between the three sub-arrays 32a, 32b, and 32c above it and the sunlight irradiation are also relatively large, and the difference in the included angle between each of the three sub-arrays 32a, 32b, and 32c and the sunlight irradiation is also relatively large. Therefore, it is not suitable to group these three sub-arrays into the same array group.

[0074] The above description only abstractly describes an application scenario of a simplified complex terrain. In actual implementation scenarios, there may be more complex terrain manifestations and more complex grouping strategies may be adopted.

[0075] Embodiment 2: This embodiment should be understood as including at least all the features of any one of the foregoing embodiments and being further improved on this basis;

[0076] Preferably, the first information unit is used to collect and record information of fixed dimensions of the photovoltaic module, such as the geographical location of the photovoltaic module, such as the horizontal height, slope, orientation, etc.; and the installation parameters of the photovoltaic module, such as the tilt angle, array position; this information is basically fixed when the photovoltaic module is installed;

[0077] Preferably, the B information unit is used to collect and record real-time variable information, belonging to variable dimensions; including real-time environmental data, such as illuminance, wind speed, air temperature, etc.; and power generation data of the photovoltaic module, such as daily power generation, average output power, historical power generation data, etc.; environmental data can affect the power generation data of the photovoltaic module, and at the same time, the production process of the photovoltaic module itself, the aging speed over time and the changes caused by aging are also different, so they all belong to the information of variable dimensions;

[0078] Further, in a preferred embodiment, the grouping module performs clustering analysis on multiple sub-arrays based on the above fixed dimension information and variable dimension information based on a clustering algorithm.

[0079] In a preferred embodiment, the clustering analysis can be performed in the following steps:

[0080] S100: Preprocess the information data of each sub-array; specifically, it includes:

[0081] Normalization processing. In order to ensure that data of different dimensions have the same magnitude, first perform normalization processing on all input data so that the numerical range of each parameter of the sub-array falls between [0, 1].

[0082] Feature weighting. For each parameter in the A information unit and the B information unit, corresponding weights W i and U j can be preset, where i is a positive integer; W i is the weight corresponding to the i-th parameter in the A information unit; U j is the weight corresponding to the j-th parameter in the B information unit; the weight value of each parameter can be optimized and set by machine learning according to topographical conditions or the laying design of the photovoltaic system.

[0083] Preferably, collect a large amount of experimental data or geographical feature data (such as location, orientation) and power generation feature data (such as real-time output power, historical power generation) in actual applications for initial model training; use these data to perform preliminary training on the model, set the initial weights of each feature pair, and then evaluate the performance based on the current grouping results and the fault detection accuracy rate.

[0084] Preferably, the machine learning algorithm can adopt Grid Search or Bayesian Optimization to optimize the weight combination through experiments; substitute different weight combinations into the model with the goal of maximizing the fault detection accuracy rate or minimizing the false alarm rate.

[0085] Preferably, the optimal weight combination is used to update the grouping model to ensure automatic adaptation to the differences in geography and power generation characteristics under dynamic terrain conditions, thereby optimizing the weight values of each feature.

[0086] S200: Initialize the clustering centers, randomly select K initial clustering centers from the input data to represent the initial array groups; the initial array groups are denoted as G1, G2, ……, G K ;

[0087] Since the information of the initial grouping is uncertain, the algorithm randomly selects K sub-arrays from the photovoltaic sub-arrays as the initial clustering centers; this random selection is to provide a preliminary grouping reference point in the data space, and each clustering center contains two parts of information, namely fixed-dimension information and variable-dimension information.

[0088] S300: Calculate the similarity between each photovoltaic sub-array and each clustering center G1, G2, ……, G K ; The weighted Euclidean distance is adopted, combining the fixed-dimension information and the variable-dimension information, and the following calculation formula is used for calculation:

[0089]

[0090] In the above formula, x p,i is the feature of the i-th fixed dimension of the p-th sub-array; y p,j is the feature of the j-th variable dimension of the p-th sub-array; G k,i and G k,j are respectively the feature of the i-th fixed dimension and the feature of the j-th variable dimension of the k-th clustering center.

[0091] S400: Assign the sub-arrays to the clusters, that is, according to the similarity calculated in S300, assign each sub-array to the array group belonging to the nearest clustering center G according to the principle of the minimum distance, where the distance refers to the Euclidean distance.

[0092] S500: Update the clustering centers based on the photovoltaic sub-arrays within each array group; the new clustering center is the weighted average of all the sub-arrays within the group, that is:

[0093]

[0094] In the above formula, │num k │ is the number of sub-arrays in the k-th array group.

[0095] S600: Repeat steps S300 to S500 until the change in the clustering centers is less than the preset threshold ε, that is:

[0096] ‖C k ′ - C k ‖ < ε;

[0097] In the above formula, C k ′ represents the k-th clustering center in the current iteration, and C k represents the k-th clustering center in the previous iteration; ‖C k ′ - C k ‖ represents the modulus of the two; the threshold ε is specifically set by relevant technical personnel based on requirements such as the number of sub-arrays, system computing power, or detection accuracy.

[0098] Finally, after outputting the grouping result, the divided array group is used as the input for the next fault detection.

[0099] In a preferred embodiment, after obtaining multiple array groups, the detection criteria for each array group vary due to differences in their respective positions and environments; under complex terrain conditions, the following parameters can be preferably used to achieve more efficient fault detection, and the detection criteria can be adaptively adjusted according to specific conditions within the group;

[0100] Intra-group reference power generation parameters: Based on differences in geographical location, slope, orientation, etc. of each group, specific benchmarks are set for parameters such as power generation, output power, and output voltage; the detection benchmark for each group is set according to its daily power generation level and typical power generation data under similar environmental conditions; during detection, if the sub-arrays within a certain group deviate from the set benchmark, it may indicate a fault.

[0101] Environmental response parameters: Due to different geographical locations, the responses of each group to light, wind speed, and temperature are also different; real-time monitoring of the environmental response of each group (such as the immediate impact of light intensity and temperature changes on power generation) can help identify abnormal responses; for example, when the light intensity is the same, if the output of the sub-arrays in a certain group is low, it may be caused by occlusion or equipment failure.

[0102] Power generation trend comparison parameters: Analyze the short-term and long-term power generation trends of the sub-arrays in each group, and compare the current real-time data with historical data; this can detect gradually accumulating power generation decline or abnormal fluctuations (such as continuous power generation decline in a certain group).

[0103] Intra-group relative balance parameters: Within each array group, when the sub-arrays that make up the array group are the same, the relative differences in output power and output voltage of the array group at different time sequences can be compared; this relative detection is based on the sameness of the sub-arrays within the group, avoiding the influence of errors caused by different geographical locations. If the output of a certain sub-array within the group is significantly different from that of the sub-arrays at other times, it can be marked as abnormal for further detection.

[0104] As shown in the appendix Figure 4As shown, in the experimental photovoltaic power generation system, a large photovoltaic power generation system is set up, and each photovoltaic sub-array in the photovoltaic system is in different positions and lighting conditions, and an experiment is carried out for 480 hours. By generating controllable fault phenomena in the photovoltaic power generation system, the performance of this detection system is detected. By comparing the fault detection rates with the old detection system, the accuracy rate has been significantly improved.

[0105] Embodiment 3: This embodiment should be understood as including at least all the features of any one of the foregoing embodiments, and further improved on this basis;

[0106] Exemplarily, as shown in the appendix Figure 5 illustrate the implementation manner of the computer system 500 adopted by the analysis module in the detection system; the computer system 500 can be applied to the data storage, operation and result output processes of each working module in the identification and judgment system;

[0107] Exemplarily, the computer system 500 includes a bus 502 or other communication mechanisms for transmitting information, and one or more processors 504 coupled to the bus 502 for processing information; the processor 504 can be, for example, one or more general microprocessors;

[0108] The computer system 500 also includes a main memory 506, such as a random access memory (RAM), a cache, and / or other dynamic storage devices, which are coupled to the bus 502 for storing information and instructions to be executed by the processor 504; the main memory 506 can also be used to store temporary variables or other intermediate information during the execution of the instructions executed by the processor 504; when these instructions are stored in a storage medium accessible by the processor 504, the computer system 500 is presented as a dedicated machine customized to execute the operations specified in the instructions;

[0109] The computer system 500 may also include a read-only memory (ROM) 508 or other static storage devices coupled to the bus 502 for storing static information and instructions of the processor 504; a storage device 510 such as a magnetic disk, an optical disk, or a USB drive (flash drive) will be coupled to the bus 502 for storing information and instructions;

[0110] Furthermore, coupled to the bus 502 may also include a display 122 for displaying various information, data, media, etc., and an input device 514 for allowing the user of the computer system 500 to control, manipulate the computer system 500 and / or interact with the computer system 500;

[0111] A preferred way to interact with the management system can be through a cursor control device 516, such as a computer mouse or a similar control / navigation mechanism;

[0112] Further, computer system 500 may also include a network device 518 coupled to bus 502; wherein the network device 518 may include components such as a wired network card, a wireless network card, a switching chip, a router, a switch, etc.;

[0113] Generally, terms such as "engine", "component", "system", "database", etc. as used herein may refer to logic embodied in hardware or firmware, or to a collection of software instructions, which may have entry and exit points and are written in a programming language such as Java, C, or C++; software components may be compiled and linked into an executable program, installed in a dynamic link library, or may be written in an interpreted programming language (such as BASIC, Perl, or Python); it should be understood that software components may be called from other components or from themselves, and / or may be called in response to detected events or interrupts;

[0114] Software components configured to execute on a computing device may be provided on a computer-readable medium, such as a compact disc, a digital video disc, a flash drive, a magnetic disk, or any other tangible medium, or as a digital download (and may initially be stored) in a compressed or installable format that requires installation, decompression, or decryption before execution); such software code may be stored, in whole or in part, on the memory device of the executing computing device for execution by the computing device; software instructions may be embedded in firmware, such as an EPROM; it should also be understood that hardware components may be composed of connected logic units (such as gates and flip-flops), and / or may be composed of programmable units (such as programmable gate arrays or processors);

[0115] Computer system 500 includes custom hardwired logic, one or more ASICs or FPGAs, firmware, and / or program logic that may be used to implement the techniques described herein, and the program logic combined with the computer system causes computer system 500 to be a dedicated computing device;

[0116] According to one or more embodiments, the techniques herein are performed by computer system 500 in response to one or more sequences of one or more instructions contained in main memory 506 being executed by processor 504; such instructions may be read into main memory 506 from another storage medium, such as storage device 510; the execution of the instruction sequence contained in main memory 506 causes processor 504 to perform the processing steps described herein; in alternative embodiments, hardwired circuitry may be used in place of or in combination with software instructions;

[0117] As used herein, the term "non-transitory medium" and like terms refer to any medium that stores data and / or instructions that cause a machine to operate in a particular manner; such non-transitory media can include non-volatile media and / or volatile media; non-volatile media includes, for example, optical discs or magnetic disks such as storage device 510; volatile media includes dynamic memory such as main memory 506;

[0118] Common forms of non-transitory media include, for example, floppy disks, hard disks, solid state drives, magnetic tape, or any other magnetic data storage media, CD-ROMs, any other optical data storage media, any physical media with a hole pattern, RAM, PROM, and EPROM, FLASH-EPROM, NVRAM, any other memory chip or cartridge, and network versions thereof;

[0119] Non-transient media is different from transmission media, but can be used in combination with transmission media; transmission media participates in the transfer of information between non-transient media; for example, transmission media includes coaxial cables, copper wire, and optical fiber, including the wires that make up bus 502; transmission media can also take the form of acoustic waves or light waves, such as radio waves and infrared data communication.

[0120] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the present invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may appropriately omit, substitute, or add various processes or components. For example, in alternative configurations, the methods may be performed in a different order than described, and / or various components may be added, omitted, and / or combined. Moreover, the features described with respect to certain configurations may be combined in various other configurations, such as different aspects and elements of the configurations may be combined in a similar manner. Additionally, as technology evolves, the elements therein may be updated, i.e., many elements are examples and do not limit the scope of the present disclosure or claims.

[0121] Specific details are given in the specification to provide a thorough understanding of the exemplary configurations including the implementation. However, the configurations may be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail to avoid obscuring the configurations. The description only provides example configurations and does not limit the scope, applicability, or configurations of the claims. Instead, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made to the function and arrangement of the elements without departing from the spirit or scope of the present disclosure.

[0122] In summary, it is intended that the above detailed description be regarded as illustrative rather than restrictive, and it should be understood that the above embodiments are to be construed as merely illustrative of the present invention and not as limiting the scope of protection of the present invention. After reading the content described in the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A complex terrain photovoltaic array fault detection system based on machine learning, characterized in that, The detection system is configured to connect to an existing photovoltaic power generation system and perform grouped detection on multiple sub-arrays in the photovoltaic array according to the power generation data of the multiple sub-arrays, so as to form multiple array groups, and perform fault detection on each array group using a corresponding fault detection model; the detection system includes: a grouping module configured to group multiple sub-arrays in the photovoltaic power generation system based on the following two conditions to form one or more of the above-mentioned array groups: (1) The geographical location and terrain features of each photovoltaic module in each sub-array; (2) The power generation trend of each sub-array in the same period of the real-time past; The grouping module includes a first information unit and a second information unit; the first information unit is used to collect and record the fixed dimension information of the photovoltaic module, and the second information unit is used to collect and record the real-time variable dimension information; the fixed dimension information includes the horizontal height, slope, orientation of the photovoltaic module, as well as the tilt angle and array position of the photovoltaic module; the variable dimension information includes illuminance, wind speed, air temperature, as well as the daily power generation, average output power, and historical power generation data of the photovoltaic module; An analysis module, configured to perform fault detection on one or more of the above-mentioned array groups by using a fault detection program to determine whether there is an abnormality in the working state of each array group; wherein, the analysis module trains a grouping model by applying a machine learning algorithm, and applies the grouping model to group multiple sub-arrays to establish multiple array groups; the grouping module performs clustering analysis on multiple sub-arrays based on the above fixed dimension information and variable dimension information based on a clustering algorithm; the clustering analysis adopts the following steps: S100: Perform normalization preprocessing on the information data of each sub-array: feature weighting, for each parameter in the A information unit and the B information unit, a corresponding weight w i and u j is given in advance, where i is a positive integer; w i is the weight corresponding to the i-th parameter in the A information unit; u j is the weight corresponding to the j-th parameter in the B information unit; S200: Initialize the clustering center, randomly select K initial clustering centers from the input data to represent the initial array groups; the initial array groups are represented as G1, G2,..., G K ; S300: Calculate the similarity D K between each photovoltaic sub-array and each clustering center G1, G2,..., G pk ; Adopt the weighted Euclidean distance, combine the fixed dimension information and the variable dimension information, and calculate by using the following calculation formula: ； In the above formula, x p,i is the feature of the i-th fixed dimension of the p-th sub-array; y p,j is the feature of the j-th variable dimension of the p-th sub-array; G k,i and G k,j are the features of the i-th fixed dimension and the j-th variable dimension of the k-th cluster center respectively; S400: Assign sub-arrays to clusters. According to the similarity calculated in S300, each sub-array is assigned to the array group to which the nearest cluster center G belongs according to the minimum distance principle; S500: Update the cluster center according to the photovoltaic sub-arrays within each array group ; The new cluster center is the weighted average of all sub-arrays within the group, that is: ; │num k │ is the number of sub-arrays in the k-th array group; S600: Repeat steps S300 to S500 until the change in the cluster center is less than the preset threshold ε.

2. The detection system according to claim 1, wherein, The grouping module includes a first information unit; the first information unit includes: A geographical data storage component configured to store the geographical location data of each photovoltaic module; An installation data storage component configured to store the installation parameter data of each photovoltaic module; An environmental data acquisition component configured to acquire real-time environmental data.

3. The detection system according to claim 2, characterized in that, The grouping module further includes a second information unit; the second information unit includes: A power generation data acquisition component configured to acquire the power generation data of each sub-array; the power generation data at least includes the daily power generation, as well as the average output power and average output voltage based on time series; A power generation data storage component configured to store the historical power generation data of each sub-array.

4. The detection system according to claim 3, characterized in that, The grouping module further includes a grouping unit; the grouping unit is configured to train the grouping model based on the latest information data provided by the first information unit and the second information unit.

5. The detection system according to claim 4, wherein, The grouping module includes dissolving the established array groups and regrouping them in subsequent stages.

6. The detection system according to claim 5, characterized in that, The grouping module includes using a clustering algorithm to perform the following grouping steps to group multiple sub-arrays: S100: Preprocess the information data of each sub-array; S200: Randomly select sub-arrays for grouping to form initial array groups and initialize the clustering centers; S300: Calculate the similarity between each photovoltaic sub-array and each clustering center; S400: Assign each sub-array to the array group to which the nearest clustering center belongs according to the minimum distance principle; S500: Update the clustering centers according to the photovoltaic sub-arrays within each array group; S600: Repeat steps S300 to S500 until the change in the clustering centers is less than a preset threshold.

Images