Photovoltaic panel array fault diagnosis method and system, electronic equipment and program product

Abstract

The invention discloses a fault diagnosis method and device for a photovoltaic panel array, electronic equipment and a program product. The method comprises the following steps: acquiring voltages and currents of a plurality of photovoltaic panel groups in a photovoltaic panel array; comparing the voltages and the currents of the plurality of photovoltaic panel groups, and determining an abnormal photovoltaic panel group in the plurality of photovoltaic panel groups; determining an IV curve of an abnormal photovoltaic panel in the abnormal photovoltaic panel group; based on the IV curve, determining the fault type of the abnormal photovoltaic panel through a multi-layer sensor artificial neural network model; and according to the fault type of the abnormal photovoltaic panel, adaptively recommending a maintenance scheme for the fault type. Through the mode of obtaining the electrical data of the photovoltaic panel array in groups, the cost is reduced, the abnormal photovoltaic panel is positioned based on the electrical data, the data volume detected by the neural network model is reduced, and the efficiency of the whole fault detection process is improved.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic system fault diagnosis, and in particular to a photovoltaic panel array fault diagnosis method, system, electronic equipment and program product. Background Art

[0002] Photovoltaic power generation is valued around the world as a convenient, environmentally friendly and low-cost clean energy. Photovoltaic power generation technology has also moved from a period of rapid development to a mature stage, and its application scenarios and implementation methods have become increasingly diverse. This has also brought challenges to the fault diagnosis of photovoltaic components in photovoltaic power generation systems, and the requirements for photovoltaic system fault diagnosis technology are becoming increasingly higher. However, the existing photovoltaic system fault diagnosis technology has a high detection cost and cannot achieve high-efficiency and high-precision detection at the same time.

[0003] Therefore, how to reduce costs while ensuring the efficiency and accuracy of photovoltaic system fault diagnosis technology is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a photovoltaic panel array fault diagnosis method, system, electronic device and program product, which detects photovoltaic array faults by acquiring electrical data of the photovoltaic panel array in groups and combining it with a high-precision artificial neural network-based detection method, and intelligently recommends maintenance plans, thereby achieving low-cost, efficient and high-precision photovoltaic array fault diagnosis.

[0005] In a first aspect, an embodiment of the present application provides a photovoltaic panel array fault diagnosis method, comprising: obtaining voltages and currents of multiple photovoltaic panel groups in a photovoltaic panel array, wherein each photovoltaic panel group includes at least one photovoltaic panel; comparing the voltages and currents of the multiple photovoltaic panel groups to determine an abnormal photovoltaic panel group among the multiple photovoltaic panel groups; determining an IV curve of an abnormal photovoltaic panel in the abnormal photovoltaic panel group; based on the IV curve, determining a fault type of an abnormal photovoltaic panel in the abnormal photovoltaic panel group through a multilayer perceptron artificial neural network model; and adaptively recommending a maintenance plan for the fault type according to the fault type of the abnormal photovoltaic panel group.

[0006] In certain embodiments of the present application, multiple photovoltaic panel groups include multiple parallel branches connected in series, each parallel branch includes at least two photovoltaic panel groups connected in parallel, each parallel branch is connected in parallel to a voltage sensor, and each photovoltaic panel group is connected in series to a current sensor, and the voltage and current of multiple photovoltaic panel groups in the photovoltaic panel array are obtained, including: using the voltage sensor of each parallel branch to measure the voltage of each photovoltaic panel group on the parallel branch; using the current sensor connected to the photovoltaic panel group to measure the current of the photovoltaic panel group.

[0007] In certain embodiments of the present application, the voltages and currents of multiple photovoltaic panel groups are compared to determine the abnormal photovoltaic panel group among the multiple photovoltaic panel groups, including: comparing the voltages measured by voltage sensors of multiple parallel branches to determine the parallel branches where the abnormal photovoltaic panel group exists; comparing the currents of each photovoltaic panel group in the parallel branches where the abnormal photovoltaic panel group exists to determine the abnormal photovoltaic group.

[0008] In certain embodiments of the present application, at least one photovoltaic panel includes multiple photovoltaic panels, and the IV curve of each photovoltaic panel in the abnormal photovoltaic panel group is determined, including: for each photovoltaic panel in the abnormal photovoltaic panel group, shutting down the other multiple photovoltaic panels in the abnormal photovoltaic panel group, measuring the open circuit voltage and short circuit current of the photovoltaic panel; comparing the open circuit voltage and short circuit current of each photovoltaic panel in the abnormal photovoltaic panel group to determine the abnormal photovoltaic panel; based on a single diode model, generating the IV curve of the abnormal photovoltaic panel according to the open circuit voltage and short circuit current of the abnormal photovoltaic panel.

[0009] In certain embodiments of the present application, based on the IV curve, the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group is determined by a multilayer perceptron artificial neural network model, including: obtaining the current IV curve, temperature and light irradiance of the abnormal photovoltaic panel in the abnormal photovoltaic panel group; preprocessing the IV curve, temperature and light irradiance to obtain a vector matrix of the abnormal photovoltaic panel, the vector matrix is ​​used to characterize the IV curve, temperature and light irradiance of the abnormal photovoltaic panel; inputting the vector matrix into the trained multilayer perceptron artificial neural network model to determine the fault type of the abnormal photovoltaic panel.

[0010] In certain embodiments of the present application, it also includes generating IV curves under different fault types based on a single diode model according to the measured short-circuit current and open-circuit voltage of a sample photovoltaic panel; generating training samples based on the IV curves under different fault types and corresponding environmental information, wherein the environmental information includes light amplitude and temperature; and training a multilayer perceptron artificial neural network model based on the training samples.

[0011] In certain embodiments of the present application, based on the fault type of the abnormal photovoltaic panel, a maintenance plan for the fault type is adaptively recommended, including: obtaining the fault type of the abnormal photovoltaic panel; determining the maintenance entity based on the fault type of the abnormal photovoltaic panel, wherein the maintenance entity includes at least one of a drone, an inspection robot, and a maintenance personnel; matching the corresponding maintenance plan from the maintenance information database based on the fault type of the abnormal photovoltaic panel and the maintenance entity.

[0012] In certain embodiments of the present application, a corresponding maintenance plan is matched from a maintenance information database according to the fault type and maintenance entity of the abnormal photovoltaic panel, including: collecting historical maintenance data of the maintenance entity for different types of faults; scoring the maintenance capability of the maintenance entity for different types of faults based on the historical maintenance data; and determining the assigned maintenance entity based on the score and the fault type.

[0013] In a second aspect, an embodiment of the present application provides a photovoltaic panel array fault diagnosis device, comprising: a data acquisition module, used to acquire voltages and currents of multiple photovoltaic panel groups in a photovoltaic panel array, wherein each photovoltaic panel group includes at least one photovoltaic panel; an abnormal photovoltaic panel determination module, used to compare the acquired voltages and currents of multiple photovoltaic panel groups, and determine the abnormal photovoltaic panel group among the multiple photovoltaic panel groups, and the abnormal photovoltaic panel determination module is also used to determine the IV curve of each photovoltaic panel in the abnormal photovoltaic panel group; a fault determination module, used to determine the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group based on the IV curve through a multilayer perceptron artificial neural network model; a maintenance plan recommendation module, used to adaptively recommend a maintenance plan for the fault type according to the fault type of the abnormal photovoltaic panel.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the photovoltaic panel array fault diagnosis method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program / instruction, characterized in that when the computer program / instruction processor is executed, it is used to implement the photovoltaic panel array fault diagnosis method described in the first aspect.

[0016] The embodiments of the present application provide a photovoltaic panel array fault diagnosis method, device, electronic device and program product, which reduces the cost of the fault detection process by obtaining the voltage and current of the photovoltaic array in groups, further compares the voltage and current of multiple photovoltaic panels to locate the abnormal photovoltaic panel, and then detects the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group through a high-precision multi-layer perceptron artificial neural network model, reducing the amount of data required to be detected by the artificial neural network model and improving the efficiency of the overall fault detection process. After determining the fault type of the abnormal photovoltaic panel, an intelligent maintenance plan suitable for the fault type is recommended to further improve the efficiency of maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings, in which:

[0018] Figure 1It is a schematic diagram of the structure of a photovoltaic panel array fault diagnosis system provided in some embodiments of the present application.

[0019] Figure 2 It is a flowchart of a photovoltaic panel array fault diagnosis method provided in some embodiments of the present application.

[0020] Figure 3 It is a schematic diagram of the structure of grouping measurement of voltage and current of photovoltaic panels provided in some embodiments of the present application.

[0021] Figure 4 It is an exemplary flow chart of a photovoltaic panel array fault diagnosis method based on a multilayer perceptron artificial neural network model provided in some embodiments of the present application.

[0022] Figure 5 It is a system module diagram of a photovoltaic panel array fault diagnosis device provided in some embodiments of the present application.

[0023] Figure 6 It is a schematic diagram of the structure of an electronic device provided in some embodiments of the present application.

[0024] Figure 7 It is the equivalent circuit diagram of a single diode model in the related art. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] Application Overview

[0027] In the related art, the fault type of the photovoltaic system is generally diagnosed by an electrical detection method or an artificial intelligence neural network method.

[0028] The electrical detection method measures the electrical data of the photovoltaic panel group, such as voltage and current values, and analyzes the difference or change trend between the current actual measured electrical data and the normal electrical data size to identify and locate the faulty photovoltaic panel group. It is highly dependent on the electrical data such as the voltage and current values ​​of the photovoltaic panel group. Therefore, a large number of voltage sensors and current sensors need to be set up, and the detection cost is high. It is not suitable for the detection of large photovoltaic arrays. In addition, the electrical detection method can only detect some simple fault types, and the fault types that can be detected are limited.

[0029] The IV curve is an important characteristic curve in the photovoltaic system. To a certain extent, it can reflect the output characteristics of the photovoltaic unit under different conditions and can solve the problem that the photovoltaic cell (photovoltaic unit) has nonlinear behavior between current and voltage. Therefore, the fault diagnosis method based on the artificial neural network model often realizes the detection of the fault type of the photovoltaic panel group by learning the mapping relationship between the IV curve and the fault type, and the detection accuracy is relatively high. However, the artificial neural network model requires a large number of samples for training, and collecting samples of the IV curves of photovoltaic units with different faults requires a certain amount of time and equipment costs. In addition, for large photovoltaic systems, the number of photovoltaic panels included is huge. If all fault diagnosis methods based on the artificial neural network model are used for fault detection, it will take up huge computing resources and a lot of time, and it will not be able to detect faults in a timely and efficient manner.

[0030] Figure 7 This is the equivalent circuit diagram of a single diode model. Figure 7 As shown, the single diode model is a photovoltaic model, which is modeled by connecting some diodes in series. The diode represents the photovoltaic cells in series. For example, its mathematical expression can be expressed by the following formula:

[0031]

[0032] Where I represents the output current of the photovoltaic unit; V represents the output voltage of the photovoltaic unit; I ph Represents the photocurrent of the photovoltaic cell; I 0 represents the reverse saturation current; q represents the electron charge, which is 1.62×10 -19 C; a is the ideal factor; k is the Boltzmann constant (1.381×10 -23 m 2 ×kg / s 2 ×K); T is the temperature of the photovoltaic cell; R sh is the parallel resistance; R s is the series resistance.

[0033] In response to the above problems, the embodiments of the present application creatively propose a photovoltaic array fault diagnosis method that combines a grouped current and voltage detection method with an artificial neural network-based detection method to achieve low-cost, efficient and high-precision photovoltaic array fault diagnosis.

[0034] Various non-limiting embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0035] Exemplary Photovoltaic Panel Array Fault Diagnostic System

[0036] The present application provides a photovoltaic panel array fault diagnosis system 100, Figure 1This is a schematic diagram of the structure of a photovoltaic panel array fault diagnosis system provided in some embodiments of the present application. Figure 1 As shown, the photovoltaic panel array fault diagnosis system 100 may include a photovoltaic array 110, a sensor assembly 120, a control system 130, a user 140, and a user terminal 150. The photovoltaic panel array 110 may include a plurality of photovoltaic panel groups 111, and the photovoltaic panel group 111 may include at least one photovoltaic panel. It should be noted that the present application does not impose specific restrictions on the number of photovoltaic panels in the photovoltaic panel array and the number of photovoltaic units in the photovoltaic panel.

[0037] exist Figure 1 In the photovoltaic panel array fault system 100 shown, the user 140 can view the fault conditions in the current photovoltaic panel array through the user terminal 150. According to different fault types, the user terminal 150 can click the corresponding selection control to select the corresponding maintenance method.

[0038] In some embodiments, the photovoltaic panel array fault system 100 can adaptively recommend an efficient maintenance solution to the user 140 according to the fault type.

[0039] In some embodiments, the sensor assembly 120 can be used to obtain current, voltage, and temperature data of the photovoltaic panel array as basic data for fault diagnosis.

[0040] In some embodiments, the sensor assembly 120 may include a voltage sensor, a current sensor, a temperature sensor, a photoelectric sensor, and the like.

[0041] The user 140 can interact with the control system 130 through the user terminal 150, so that the user terminal 150 presents the current state of the photovoltaic panel array 110 to view the fault condition of the photovoltaic panel array 110, which may specifically include the number information of the abnormal photovoltaic panel (the photovoltaic panel with a fault) and the corresponding fault type information. Among them, based on the interaction with the user 140, the control system 130 can obtain the sensor data of the photovoltaic panel array 110 through the sensor component 120, and based on the sensor data of the photovoltaic panel array, determine the fault condition in the photovoltaic panel array 110 through the fault diagnosis algorithm in the control system 130, including determining the abnormal photovoltaic panel in the photovoltaic panel array and the fault type of the abnormal photovoltaic panel. For more information about the control system 130 determining the fault type of the photovoltaic panel, please refer to Figure 2-Figure 4 and its related description.

[0042] In some embodiments, the control system 130 may include a processor 131, a memory 132, and a network 133. Among them, the processor 131 can process data and / or information obtained from other devices or system components. The processor can execute program instructions based on these data, information and / or processing results to perform one or more functions described in this application. In some embodiments, the processor 131 may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). As an example only, the processor 131 may include a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), etc. or any combination thereof.

[0043] The memory 132 may be used to store data and / or instructions. The memory 132 may include one or more storage components, each of which may be an independent device or a part of another device. In some embodiments, the memory 132 may include a random access memory (RAM), a read-only memory (ROM), a mass storage device, or the like, or any combination thereof. Exemplarily, the mass storage device may include a magnetic disk, an optical disk, a solid-state disk, or the like.

[0044] In some embodiments, the memory 132 may be configured to store a computer program related to the photovoltaic panel array fault diagnosis method shown in the present application and data required for the implementation of the photovoltaic panel array fault diagnosis method. When the computer program is executed (such as called by the processor 131), the photovoltaic panel array fault diagnosis method shown in the embodiment of the present application may be implemented.

[0045] The network 133 can connect the components of the system and / or connect the system with external resources. The network 133 allows the components to communicate with each other and with other parts outside the system, and promotes the exchange of data and / or information. In some embodiments, the network 133 can be any one or more of a wired network or a wireless network. For example, the network 133 can include a cable network, an optical fiber network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), etc. or any combination thereof. The network connection between the various parts can be in one of the above-mentioned ways, or in multiple ways.

[0046] In the present application, the user 140 may be an operator of the user terminal 150. Generally, the user 140 may be a maintenance person or a management person of a photovoltaic power station.

[0047] The user terminal 150 refers to one or more terminal devices or software used by the user. In some embodiments, the user terminal 150 can be one or any combination of other devices with input and / or output functions such as a mobile device, a tablet computer, a laptop computer, a desktop computer, etc.

[0048] Exemplary Photovoltaic Panel Array Fault Diagnosis Method

[0049] Corresponding to the above system, the present application provides a photovoltaic panel array fault diagnosis method for the above system, Figure 2 Shown is a flow chart of a photovoltaic panel array fault diagnosis method provided in some embodiments of the present application.

[0050] In some embodiments, Figure 2 The exemplary process shown may be executed by processor 131 .

[0051] like Figure 2 As shown, the method may include the following steps:

[0052] S210, obtaining voltages and currents of multiple photovoltaic panel groups in a photovoltaic panel array.

[0053] Considering that in actual applications, the number of photovoltaic panels included in a large-scale photovoltaic system is huge, which can reach tens of thousands or even hundreds of thousands, the number of sensors that need to be installed is also very large, and the cost increases accordingly. In order to reduce the cost of obtaining electrical data, this application obtains the voltage and current of multiple photovoltaic panel groups in a photovoltaic array, wherein each photovoltaic panel group includes at least one photovoltaic panel. Specifically, Figure 3 As shown, the photovoltaic panel array may include a plurality of parallel branches connected in series, each parallel branch may further include at least two photovoltaic panel groups connected in parallel, each parallel branch is connected in parallel to a voltage sensor, and each photovoltaic panel group is connected in series to a current sensor. The voltage sensor of each parallel branch may be used to measure the voltage of each photovoltaic panel group on the parallel branch, and the current sensor connected to the photovoltaic panel group may be used to measure the current of the photovoltaic panel group, that is, the voltage and current of the entire photovoltaic panel array may be obtained in a grouped manner to reduce costs.

[0054] In some embodiments, the number of parallel branches in the photovoltaic panel can be determined according to the arrangement of the photovoltaic panels in the photovoltaic panel array, and the number of photovoltaic panels in the photovoltaic panel group can be further determined according to the number of photovoltaic panels in the parallel branches. Exemplarily, the photovoltaic panel array includes 6 parallel branches (111a-111f), and 3 photovoltaic panels in the parallel branches are grouped together, that is, the photovoltaic panel group includes 3 photovoltaic panels. The fewer the number of photovoltaic panels included in the photovoltaic panel group, the higher the detection accuracy. The number of parallel branches included in the photovoltaic panel and the number of photovoltaic panels in the photovoltaic panel group can be adjusted according to actual conditions to balance the detection cost and detection accuracy. The number of parallel branches and the number of photovoltaic panels in the photovoltaic panel group are not specifically limited here.

[0055] S220 , comparing the acquired voltages and currents of the multiple photovoltaic panel groups, and determining an abnormal photovoltaic panel group among the multiple photovoltaic panel groups.

[0056] The abnormal photovoltaic panel group may be a photovoltaic panel group including a faulty photovoltaic panel.

[0057] After obtaining the voltages and currents of multiple photovoltaic panel groups through S210, the voltages measured by the voltage sensors of different parallel branches (111a-111f) can be compared to determine the line position of the abnormal photovoltaic panel, that is, the parallel branch where the abnormal photovoltaic panel is located, and then the group where the abnormal photovoltaic panel is located, that is, the abnormal photovoltaic panel group, can be determined by comparing the currents of each photovoltaic panel group in the parallel branch where the abnormal photovoltaic panel is located, so as to locate the abnormal photovoltaic panel group. For example, when the output voltage of the photovoltaic panel of the parallel branch i is U i , while the output voltages of the photovoltaic panels in other parallel branches are all U, and U i <U, it is determined that there is an abnormal photovoltaic panel in the photovoltaic panels of the parallel branch i, and the currents of the photovoltaic panels in the parallel branch i are further compared. When the output current of the photovoltaic panels of the ath group in the parallel branch i is I ia , while the currents of the other photovoltaic panels in the parallel branch i are all I, and I ia <I, it is determined that the photovoltaic panels in the ath group in the parallel branch i are abnormal, that is, an abnormal photovoltaic panel group. By predetermining the abnormal photovoltaic panel group, the amount of data to be processed in the subsequent fault detection process is reduced, and the efficiency of the overall fault detection process is improved.

[0058] In some embodiments, a collection period for current and voltage data can be set to collect the current and voltage of the photovoltaic panel array at fixed periodic time intervals. Exemplarily, the collection period can be 1 hour. Every hour, the current current and voltage of the photovoltaic panel array are collected, and the electrical data of the current photovoltaic panel array is updated to promptly detect abnormal photovoltaic panels.

[0059] S230: Determine the IV curve of the abnormal photovoltaic panel in the abnormal photovoltaic panel group.

[0060] In some embodiments, when the photovoltaic panel group includes multiple photovoltaic panels, that is, at least one photovoltaic panel is a plurality of photovoltaic panels, the open circuit voltage and short circuit current of each photovoltaic panel in the abnormal photovoltaic panel can be measured in sequence. Exemplarily, the photovoltaic panels in the abnormal photovoltaic panel group can be used as photovoltaic panels to be tested in sequence, and the other photovoltaic panels in the abnormal photovoltaic group except the photovoltaic panel to be tested are shut down to measure the open circuit voltage and short circuit current of the photovoltaic panel to be tested. The open circuit voltage and short circuit current of different photovoltaic panels in the abnormal photovoltaic panel group are compared. If there is a photovoltaic panel whose open circuit voltage and short circuit current are significantly different from the open circuit voltage and short circuit current of other photovoltaic panels in the abnormal photovoltaic group, for example, less than the open circuit voltage and short circuit current of other photovoltaic panels in the abnormal photovoltaic group, the photovoltaic panel is regarded as an abnormal photovoltaic panel in the abnormal photovoltaic group. Further based on the single diode model, the IV curve of the abnormal photovoltaic panel is generated according to the measured open circuit voltage and short circuit current of the abnormal photovoltaic panel.

[0061] S240: Based on the IV curve, determine the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group through a multi-layer perceptron artificial neural network model.

[0062] In order to ensure the accuracy of fault detection, the present application determines the fault type of the abnormal photovoltaic panel group through a multilayer perceptron artificial neural network model with high detection accuracy. In some embodiments, the characteristics of the IV curve of the abnormal photovoltaic panel in the abnormal photovoltaic panel group can be extracted through a multilayer perceptron artificial neural network to determine the fault type corresponding to the abnormal photovoltaic panel in the abnormal photovoltaic panel group. The specific fault detection process can be found in Figure 4 and related descriptions.

[0063] S250: According to the fault type of the abnormal photovoltaic panel, adaptively recommend a maintenance plan for the fault type.

[0064] In some embodiments, in order to enable the failure of the photovoltaic panel group to be solved more quickly and efficiently, and to reduce the energy loss in the photoelectric conversion process caused by the photovoltaic panel failure, an efficient maintenance plan for the current fault type can be adaptively recommended according to the fault type of the abnormal photovoltaic panel group. For example, the fault entity suitable for solving the fault type can be determined according to the fault type of the photovoltaic panel group, wherein the fault entity can include at least one of a drone, a patrol robot and a maintenance personnel, and then further determined according to the fault entity and the fault type of the abnormal photovoltaic panel group. The corresponding maintenance plan. For example, if the fault type is an external fault, such as dust accumulation, the corresponding maintenance entity can be a drone, and the specific maintenance plan can be that the drone directly assigned near the corresponding photovoltaic panel group sprays a cleaning fluid on the abnormal (faulty) part of the photovoltaic panel group to clean the fault, so that the fault can be cleaned without manual on-site cleaning; if the fault type is an internal fault such as a short circuit of the bypass diode, aging, damage of the photovoltaic panel group, etc., it can be further determined whether the fault type is within the range that the patrol robot can repair. If it is within the maintenance range of the patrol robot, the patrol robot can be directly dispatched to repair the fault part. If it is not within the maintenance range of the patrol robot, the maintenance personnel are dispatched to the site for maintenance. In addition, if the fault is caused by environmental factors, such as shadow obstruction, etc., it can be determined whether to conduct manual intervention based on the actual impact on the photovoltaic panel group, and the fault can be repaired with an efficient maintenance plan to improve the efficiency of fault repair.

[0065] In some embodiments, the information of maintenance personnel and data corresponding to the fault types that they are good at repairing can be collected to generate a maintenance information table and build a corresponding maintenance information database. After obtaining the fault type of the photovoltaic panel group, it is directly matched with the fault type in the maintenance information table in the database, the information of the corresponding maintenance personnel is determined, and the corresponding maintenance plan is generated.

[0066] In some embodiments, historical maintenance data of maintenance personnel for different types of faults can be collected, and the maintenance personnel's maintenance capabilities for different types of faults can be scored based on the historical maintenance data. The assigned maintenance personnel can be determined based on the score and the fault type. When assigning maintenance personnel according to the fault type of the photovoltaic panel group, maintenance personnel with high scores can be given priority for maintenance.

[0067] Therefore, based on the aforementioned photovoltaic array fault diagnosis method, the voltages and currents of multiple photovoltaic panel groups of photovoltaic panels are obtained in groups, which reduces the cost of obtaining electrical data, and further locates the abnormal photovoltaic panel group by comparing the voltages and currents of multiple photovoltaic panel groups obtained. Then, the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic group is detected by a multi-layer perceptron artificial neural network model with higher detection accuracy, which reduces the amount of data detected by the artificial neural network model, improves the efficiency of the overall fault detection process, and achieves the goal of reducing costs, improving the efficiency of fault detection, and ensuring the accuracy of fault detection.

[0068] Exemplary photovoltaic panel array fault diagnosis method based on multilayer perceptron artificial neural network model

[0069] Refer to the following Figure 4 The process of PV panel group fault type based on multi-layer perceptron artificial neural network model is further described in detail.

[0070] Figure 4 An exemplary flow chart of a photovoltaic panel array fault diagnosis method based on a multi-layer perceptron artificial neural network model is provided.

[0071] In some embodiments, Figure 4 The exemplary process shown may be executed by processor 131 .

[0072] like Figure 4 As shown, the process may specifically include the following contents.

[0073] S310, obtaining the current IV curve, temperature and light irradiance of the abnormal photovoltaic panel in the abnormal photovoltaic panel group.

[0074] The IV curve of the photovoltaic panel can characterize the current behavior characteristics of the photovoltaic panel group and is used to analyze the operating status of the photovoltaic panel group. Because the IV curve of the photovoltaic panel group will change under different environmental conditions, it is necessary to obtain the current environmental information (light amplitude and temperature) at the same time. Specifically, the key point information of the IV curve (short-circuit current I sc , open circuit voltage V oc , maximum power point MPP, etc.) and environmental information to determine the current operating status of the photovoltaic panel group to determine whether there is a fault in the photovoltaic panel group.

[0075] In some embodiments, the IV curve of the photovoltaic panel in the abnormal photovoltaic group can be generated according to a photovoltaic model, such as a single diode model. Specifically, the key parameters of the photovoltaic panel can be determined first, including the short-circuit current I sc , open circuit voltage V oc The key parameters can be obtained from the photovoltaic module manufacturer or through relevant experiments. The series resistance R of the photovoltaic panel is further calculated based on the key parameters of the photovoltaic panel. s And the parallel resistor Rsh , for example, in the short-circuit state, the output voltage of the photovoltaic panel is 0, which can be calculated according to the formula Get the series resistance R s ; In the open circuit state, the output current of the photovoltaic panel is zero, and the voltage passes through the parallel resistor R sh , can be obtained by the formula Get the parallel resistance R sh . Further, according to the obtained series resistance R of the photovoltaic panel s And the parallel resistor R sh , short circuit current I sc , open circuit voltage V oc , based on a single diode model, the IV curve of the photovoltaic panel is simulated and generated through a simulation platform (such as Matlab).

[0076] In some embodiments, the IV curve of an abnormal photovoltaic panel can be generated by a photovoltaic model, etc., or the IV curve of the photovoltaic panel can be directly obtained by a photovoltaic IV curve tester. The present application does not specifically limit the method for obtaining the IV curve.

[0077] S320 , pre-processing the current IV curve and light irradiance of the abnormal photovoltaic panel to obtain a vector matrix of the abnormal photovoltaic panel group.

[0078] The vector matrix can be used to characterize the IV curve characteristic data, temperature and light irradiance of abnormal photovoltaic panels.

[0079] In some embodiments, the characteristic matrix may specifically include the short-circuit current I sc , open circuit voltage V oc , parallel resistance R sh , series resistance R s , temperature T and light amplitude G and other data.

[0080] S330, inputting the vector matrix into the trained multi-layer perceptron artificial neural network model to determine the fault type of the abnormal photovoltaic panel group.

[0081] In some embodiments, a multi-layer perceptron neural network model can be trained to learn the mapping relationship between the IV curve characteristics of the photovoltaic panel group and the fault type to detect the fault type. For example, aging or damage of the photovoltaic panel group will cause the series resistance R s Increase; hard shadow or short circuit of bypass diode will cause voltage reduction; dust accumulation and aging on the surface of photovoltaic panel group will cause current increase; partial shading or damage of photovoltaic panel group will cause inflection point of IV curve; damage or partial shading of photovoltaic panel group will also cause parallel resistance R sh By combining the trends of IV curve changes caused by the above-mentioned different faults, the characteristics of the IV curve corresponding to different faults can be obtained.

[0082] In some embodiments, training samples can be generated based on the single diode model to construct a sample library. For example, the operation data of the photovoltaic panel group under different fault types can be obtained, such as the short-circuit current I sc , open circuit voltage V oc , calculate the corresponding parallel resistance R according to the operating data of the photovoltaic panel sh , series resistance R s , reverse saturation current I o , combined with environmental information such as light amplitude and temperature, the IV curve of the photovoltaic panel under different fault types is generated through the single diode model to generate training samples. The specific process of generating the IV curve of the photovoltaic panel can refer to the relevant description in S320, which will not be repeated here.

[0083] Exemplary Devices

[0084] Combination of the above Figures 1 to 4 , describes the method embodiment of the present application in detail, and the device embodiment of the present application is described in detail below. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so the part not described in detail can refer to the previous method embodiment.

[0085] The present application also provides a photovoltaic panel array fault diagnosis device, including a module for implementing the photovoltaic panel array fault diagnosis method provided by the present application. Figure 5 As shown, the figure is a system module diagram of a photovoltaic panel array fault diagnosis device 500 provided in some embodiments of the present application. The photovoltaic panel array fault diagnosis device 500 provided in the present application may include a data acquisition module 510, an abnormal photovoltaic panel determination module 520, a fault determination module 530 and a maintenance plan recommendation module 540.

[0086] The data acquisition module 510 can acquire the voltage and current of a plurality of photovoltaic panel groups in the photovoltaic panel array, wherein the plurality of photovoltaic panel groups include at least one photovoltaic panel.

[0087] The abnormal photovoltaic panel determination module 520 may be used to compare the acquired voltages and currents of the plurality of photovoltaic panel groups, and determine an abnormal photovoltaic panel group among the plurality of photovoltaic panel groups.

[0088] The fault determination module 530 can determine the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group based on the IV curve through a multi-layer perceptron artificial neural network model.

[0089] The maintenance plan recommendation module 540 can be used to adaptively recommend a maintenance plan for the fault type according to the fault type of the abnormal photovoltaic panel.

[0090] The abnormal photovoltaic panel determination module 520 is further used to determine the IV curve of the abnormal photovoltaic panel in the abnormal photovoltaic panel group.

[0091] For the specific definition of the photovoltaic panel array fault diagnosis device, please refer to the definition of the photovoltaic panel array fault diagnosis method mentioned above, which will not be repeated here. Each module in the above-mentioned photovoltaic panel array fault diagnosis device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0092] Exemplary electronic devices and program products

[0093] The present application also provides an electronic device, such as Figure 6 The electronic device 600 provided in the present application includes a memory 610, a processor 620, and an input / output interface 630. The memory 610, the processor 620, and the input / output interface 630 are connected through an internal connection path, the memory 610 is used to store instructions, and the processor 620 is used to execute the instructions stored in the memory 610 to control the input / output interface 630 to receive input data and information, and output data such as operation results.

[0094] It should be understood that in the embodiment of the present application, the processor 620 can adopt a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs to implement the technical solution provided in the embodiment of the present application.

[0095] The memory 610 may include a read-only memory and a random access memory, and provides instructions and data to the processor 620. A portion of the processor 620 may also include a nonvolatile random access memory. For example, the processor 620 may also store information on the device type.

[0096] In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 620 or the instruction in the form of software. The photovoltaic panel array fault diagnosis method disclosed in the embodiment of the present application can be directly embodied as a hardware processor execution, or it can be completed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 610, and the processor 620 reads the information in the memory 610 and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here. The present application also provides a computer program product, including a computer program / instruction. When the computer program / instruction processor in the computer program product provided by the present application is executed, the photovoltaic panel array fault diagnosis method provided by the present application can be implemented.

[0097] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, and will not be described one by one here.

[0098] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0099] It should be noted that in the apparatus, equipment and method of the present application, each module or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present application. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present application. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the above-mentioned aspects, but to the widest scope consistent with the principles disclosed herein and novel features.

[0100] The above description is intended to illustrate and describe the technical solution of the present application. In addition, this description is not intended to limit the embodiments of the present application to the scope of the above disclosed forms. Although multiple exemplary aspects and embodiments have been discussed in the above content, those skilled in the art can easily obtain other variations, modifications, changes, additions and sub-combinations based on the above content.

[0101] It should be noted that, in the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0102] The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A photovoltaic panel array fault diagnosis method, characterized in that: include: Acquire voltages and currents of a plurality of photovoltaic panel groups in a photovoltaic panel array, wherein each photovoltaic panel group includes at least one photovoltaic panel; comparing the voltages and currents of the plurality of photovoltaic panel groups, and determining an abnormal photovoltaic panel group among the plurality of photovoltaic panel groups; Determining an IV curve of an abnormal photovoltaic panel in the abnormal photovoltaic panel group; Based on the IV curve, determining the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group through a multi-layer perceptron artificial neural network model; According to the fault type of the abnormal photovoltaic panel, a maintenance plan for the fault type is adaptively recommended.

2. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: The plurality of photovoltaic panel groups include a plurality of parallel branches connected in series, each parallel branch includes at least two photovoltaic panel groups connected in parallel, each parallel branch is connected in parallel with a voltage sensor, and each photovoltaic panel group is connected in series with a current sensor, Wherein, obtaining the voltage and current of a plurality of photovoltaic panel groups in the photovoltaic panel array includes: Using a voltage sensor of each parallel branch to measure the voltage of each photovoltaic panel group on the parallel branch; The current sensor connected to the photovoltaic panel group is used to measure the current of the photovoltaic panel group. The step of comparing the voltages and currents of the plurality of photovoltaic panel groups to determine an abnormal photovoltaic panel group among the plurality of photovoltaic panel groups includes: Comparing the voltages measured by the voltage sensors of the plurality of parallel branches, determining the parallel branch with abnormal photovoltaic panels; The currents of the photovoltaic panel groups in the parallel branch where the abnormal photovoltaic panel group exists are compared to determine the abnormal photovoltaic group.

3. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: The at least one photovoltaic panel includes a plurality of photovoltaic panels, and the determining of the IV curve of the abnormal photovoltaic panel in the abnormal photovoltaic panel group includes: For each photovoltaic panel in the abnormal photovoltaic panel group, shut down the other multiple photovoltaic panels in the abnormal photovoltaic panel group. measuring the open circuit voltage and short circuit current of the photovoltaic panel; Compare the open circuit voltage and short circuit current of each photovoltaic panel in the abnormal photovoltaic panel group to determine the abnormal photovoltaic panel; Based on a single diode model, an IV curve of the abnormal photovoltaic panel is generated according to the open circuit voltage and the short circuit current of the abnormal photovoltaic panel.

4. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: The method of determining the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group based on the IV curve by using a multi-layer perceptron artificial neural network model includes: Obtaining the current IV curve, temperature and light irradiance of the abnormal photovoltaic panel in the abnormal photovoltaic panel group; Preprocessing the IV curve, temperature and light irradiance to obtain a vector matrix of the abnormal photovoltaic panel, wherein the vector matrix is ​​used to characterize the IV curve, temperature and light irradiance of the abnormal photovoltaic panel; The vector matrix is ​​input into a trained multi-layer perceptron artificial neural network model to determine the fault type of the abnormal photovoltaic panel.

5. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: Also includes: Based on the single diode model, IV curves under different fault types are generated according to the measured short-circuit current and open-circuit voltage of the sample photovoltaic panel; Generate training samples based on the IV curves under the different fault types and corresponding environmental information, wherein the environmental information includes light amplitude and temperature; The multi-layer perceptron artificial neural network model is trained based on the training samples.

6. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: The method of adaptively recommending a maintenance plan for the fault type according to the fault type of the abnormal photovoltaic panel includes: Obtaining the fault type of the abnormal photovoltaic panel; Determining a maintenance entity according to the fault type of the abnormal photovoltaic panel, wherein the maintenance entity includes at least one of a drone, an inspection robot, and a maintenance person; According to the fault type of the abnormal photovoltaic panel and the maintenance entity, a corresponding maintenance plan is matched from a maintenance information database.

7. The photovoltaic panel array fault diagnosis method according to claim 1, characterized in that: The matching of a corresponding maintenance plan from a maintenance information database according to the fault type of the abnormal photovoltaic panel and the maintenance entity includes: Collecting historical maintenance data of different types of faults by the maintenance entity; Scoring the maintenance capability of the maintenance entity for different fault types according to the historical maintenance data; An assigned maintenance entity is determined according to the score and the fault type.

8. A photovoltaic panel array fault diagnosis device, characterized in that: include: A data acquisition module, used to acquire voltage and current of a plurality of photovoltaic panel groups in a photovoltaic panel array, wherein each photovoltaic panel group includes at least one photovoltaic panel; an abnormal photovoltaic panel determination module, used for comparing the acquired voltages and currents of the plurality of photovoltaic panel groups, determining an abnormal photovoltaic panel group among the plurality of photovoltaic panel groups, and the abnormal photovoltaic panel determination module is further used for determining an IV curve of an abnormal photovoltaic panel in the abnormal photovoltaic panel group; A fault determination module, used for determining the fault type of the abnormal photovoltaic panel in the abnormal photovoltaic panel group through a multi-layer perceptron artificial neural network model based on the IV curve; The maintenance plan recommendation module is used to adaptively recommend a maintenance plan for the fault type according to the fault type of the abnormal photovoltaic panel.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the photovoltaic panel array fault diagnosis method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction processor is executed, it is used to implement the photovoltaic panel array fault diagnosis method according to any one of claims 1-7.

Images