Method and device for determining fault cause of photovoltaic module, storage medium and electronic device

Abstract

The invention discloses a photovoltaic module fault cause determination method and device, a storage medium and an electronic device, and the method comprises the steps: obtaining the operation data of a photovoltaic module in the operation process, and the operation data at least comprise one of the first operation data of a photovoltaic array and the second operation data of a boost converter, third operating data of the inverter; inputting the operation data into a fault detection model to obtain a fault reason output by the fault detection model, the fault detection model being obtained by training with historical operation data as an input sample and historical fault reasons as output samples, the model parameters of the fault detection model are obtained through optimization based on a golden eagle optimization algorithm. By adopting the technical scheme, the technical problem that the fault reason of the photovoltaic module cannot be comprehensively and accurately judged is solved, and the accuracy and comprehensiveness of the fault reason of the photovoltaic module are improved.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic module fault detection, and more specifically, to a method and device for determining the cause of photovoltaic module failure, a storage medium, and an electronic device. Background Art

[0002] With the rapid development of photovoltaic technology, photovoltaic power generation systems have become more and more popular due to their high production efficiency. However, if the photovoltaic components of the photovoltaic power generation system fail, it will also affect the system performance. Therefore, timely detection of faults is a key issue to be solved in photovoltaic power generation systems.

[0003] There are currently a variety of fault detection methods. For example, infrared thermal imaging technology can quickly and directly identify faulty modules, because when the photovoltaic array is blocked or short-circuited, the inside of the faulty module will continue to heat up, resulting in a significant temperature gradient. In addition, the fault detection method based on timing voltage and current can achieve fault diagnosis of the photovoltaic array by adding a fault detection module to the DC combiner box. However, the existing technical solutions mainly rely on visual technology to detect the surface of the photovoltaic panel, and do not detect or predict the possible faults of the photovoltaic system, and cannot comprehensively and accurately determine the cause of the fault. Therefore, a more comprehensive method is needed to detect faults in photovoltaic systems.

[0004] With regard to the technical problem in the related technologies that the cause of failure of photovoltaic modules cannot be fully and accurately determined, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a method and device for determining the cause of a photovoltaic module failure, a storage medium, and an electronic device, so as to at least solve the technical problem that the cause of a photovoltaic module failure cannot be fully and accurately determined.

[0007] According to one aspect of an embodiment of the present application, a method for determining the cause of a photovoltaic component failure is provided, comprising: obtaining operating data of the photovoltaic component during operation, wherein the operating data includes at least one of the following: first operating data of the photovoltaic array, second operating data of the boost converter, and third operating data of the inverter; inputting the operating data into a fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained using historical operating data as input samples and historical fault causes as output samples, and model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm.

[0008] In an exemplary embodiment, the operating data includes at least the first operating data, and the operating data is input into a fault detection model to obtain a fault cause output by the fault detection model, including: determining a first voltage value of the photovoltaic array from the first operating data; when it is determined that the first voltage value does not belong to a first voltage range, inputting the first voltage value into the fault detection model to obtain a first fault cause output by the fault detection model, wherein the first fault cause includes at least one of the following: a shading fault cause, an open circuit fault cause, and a short circuit fault cause.

[0009] In an exemplary embodiment, the operating data also includes the second operating data, and the operating data is input into a fault detection model to obtain a fault cause output by the fault detection model, including: when it is determined that the first voltage value belongs to a first voltage range, determining the second voltage value of the boost converter from the second operating data; when it is determined that there is no voltage tolerance for the second voltage value, inputting the second voltage value into the fault detection model to obtain a second fault cause output by the fault detection model, wherein the second fault cause includes at least one of the following: source fluctuation and inductor failure, capacitor failure and duty cycle change.

[0010] In an exemplary embodiment, the operating data also includes the third operating data, and the operating data is input into a fault detection model to obtain a fault cause output by the fault detection model, including: when it is determined that the second voltage value has a voltage tolerance, determining the third voltage value of the inverter from the third operating data; when it is determined that the third voltage value does not have a voltage tolerance, inputting the third voltage value into the fault detection model to obtain a third fault cause output by the fault detection model, wherein the third fault cause includes at least one of the following: a short circuit fault or a switch fault, a source fluctuation of the input and power supply voltages.

[0011] In an exemplary embodiment, the method further includes: when it is determined that the first voltage value belongs to a first voltage range, if it is determined that the second voltage value has a voltage tolerance and the third voltage value has a voltage tolerance, then determining that the photovoltaic component has no fault during operation.

[0012] In an exemplary embodiment, during the training process of the fault detection model, the method further includes: using the following formula to express the model parameters optimized based on the Golden Eagle optimization algorithm:

[0013]

[0014] Where ΔX Irepresents the change in the position of Golden Eagle I between the tth iteration and the t+1th iteration, P A represents the attack coefficient at iteration t, P C represents the cruise coefficient at iteration t, and are all random vectors with a value range of [0, 1]. represents the attack vector of Golden Eagle I, Indicates the stopping point where Golden Eagle I stops iterating. and They respectively represent the Euclidean norm of the Golden Eagle I cruise attack vector.

[0015] According to another aspect of an embodiment of the present application, a device for determining the cause of a photovoltaic component failure is also provided, including: an acquisition module for acquiring operating data of the photovoltaic component during operation, wherein the operating data includes at least one of the following: first operating data of the photovoltaic array, second operating data of the boost converter, and third operating data of the inverter; an acquisition module for inputting the operating data into a fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained using historical operating data as input samples and historical fault causes as output samples, and model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm.

[0016] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for determining the cause of photovoltaic component failure when running.

[0017] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the cause of failure of the photovoltaic component through the computer program.

[0018] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0019] Through the present application, the operating data of the photovoltaic component during operation, including the first operating data of the photovoltaic array, the second operating data of the boost converter, and the third operating data of the inverter, are obtained; then the operating data is input into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operating data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm. It can be seen that the present application proposes a fault detection model based on an artificial neural network and the Golden Eagle optimization algorithm for detecting photovoltaic system faults, which not only solves the technical problem that the cause of photovoltaic component failure cannot be fully and accurately determined, but also improves the accuracy and comprehensiveness of the cause of photovoltaic component failure, thereby improving the system performance of the photovoltaic system based on photovoltaic components. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining a photovoltaic module failure cause according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of a method for determining the cause of a photovoltaic module failure according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of the structure of a deep neural network according to an embodiment of the present application;

[0025] Figure 4 is a schematic diagram of a process of fault classification and detection according to an embodiment of the present application;

[0026] Figure 5 It is a structural block diagram of a device for determining the cause of a photovoltaic component failure according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for determining the cause of a photovoltaic module failure according to an embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, MCU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the cause of photovoltaic module failure in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] In this embodiment, a method for determining the cause of a photovoltaic module failure is provided. Figure 2 is a flow chart of a method for determining the cause of a photovoltaic module failure according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0033] Step S202: Acquiring operation data of the photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of the photovoltaic array, second operation data of the boost converter, and third operation data of the inverter;

[0034] The first operation data may include, for example, the voltage of the photovoltaic array, the temperature of the photovoltaic array, the irradiance of the photovoltaic array, etc. The second operation data may include, for example, the voltage of the boost converter, etc. The third operation data may include, for example, the voltage of the inverter, etc.

[0035] Step S204: input the operating data into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained using historical operating data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle Optimization (GEO) algorithm.

[0036] Through the above steps, the operation data of the photovoltaic component during operation, including the first operation data of the photovoltaic array, the second operation data of the boost converter, and the third operation data of the inverter, are obtained; then the operation data is input into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operation data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm. It can be seen that the present application proposes a fault detection model based on an artificial neural network and the Golden Eagle optimization algorithm for detecting photovoltaic system faults, which not only solves the technical problem that the cause of photovoltaic component failure cannot be comprehensively and accurately determined, but also improves the accuracy and comprehensiveness of the cause of photovoltaic component failure, thereby improving the system performance of photovoltaic systems based on photovoltaic components.

[0037] The above fault detection model can be implemented using a deep neural network (DNN) model. A deep neural network is a multi-layer unsupervised neural network. Figure 3 As shown in the figure, DNN inputs the data of the input layer into multiple hidden layers for processing in sequence, and finally the output layer outputs the result. Among them, each layer of DNN can use the output features of the previous layer as the input of the next layer for feature learning. After layer-by-layer feature mapping, the features of the existing spatial samples are mapped to another feature space, so as to learn better feature expressions for the existing input.

[0038] Deep neural networks have multiple nonlinear mapping feature transformations and can fit highly complex functions. Deep neural networks have the following advantages: (1) They overcome the time-consuming and labor-intensive shortcomings of manually designing features; (2) They obtain primary features of each layer through layer-by-layer data pre-training; (3) Distributed data learning is more effective (exponentially); (4) Compared with shallow modeling methods, deep modeling can more meticulously and efficiently represent actual complex nonlinear problems.

[0039] In the present application, the training process can be implemented according to the following steps: forward propagation (FP), back-propagation (BP), and weight gradient calculation (WG).

[0040] In this embodiment, the training data is first sent to the DNN in batches, and forward calculation is performed layer by layer in the DNN until the output layer. Then the current output of the DNN is compared with the true label, and the loss value is calculated using the loss function (LF).

[0041] Among them, common loss functions include mean square error (MSE), cross entropy (CE), etc.

[0042] It should be noted that, for the sake of convenience, BP and WG are collectively referred to as the reverse process and weight update (WeightUpdate, WU).

[0043] The reverse process is to calculate the gradient of the loss function with respect to the weights of each layer layer by layer according to the chain rule. BP and WG are two calculation branches of the reverse process, which are used to calculate the gradient of the loss function with respect to the activation value. Finally, the weights are updated according to the weight gradients obtained in the reverse process.

[0044] In an exemplary embodiment, the operating data includes at least the first operating data. The technical solution for inputting the operating data into the fault detection model in step S204 to obtain the fault cause output by the fault detection model specifically includes: determining a first voltage value of the photovoltaic array from the first operating data; when it is determined that the first voltage value does not belong to the first voltage range, inputting the first voltage value into the fault detection model to obtain the first fault cause output by the fault detection model, wherein the first fault cause includes at least one of the following: shading fault cause, open circuit fault cause, and short circuit fault cause.

[0045] It should be noted that in this embodiment, the shading failure may be caused by natural obstructions, artificial obstructions, dirt accumulation on the surface of the module, snow, ice, bird excrement, etc. These obstructions may affect the light transmittance and reduce the light radiation on the surface of the module. In severe cases, hot spot effects may be formed locally on the module, affecting the power generation efficiency and service life of the photovoltaic module, and even causing partial burning of the module, forming permanent damage such as dark spots, which may bring safety hazards.

[0046] There are historical operating data corresponding to the cause of the shading fault for training the fault detection model, including historical voltage values ​​of the photovoltaic array that do not belong to the first voltage range.

[0047] For the cause of the open circuit fault, there is historical operating data used to train the fault detection model, including historical voltage values ​​of the photovoltaic array that do not belong to the first voltage range and do not belong to the irradiance voltage range. The irradiance voltage range represents the voltage range corresponding to a certain irradiance. For example, for 300W / m 2 ~1000W / m 2 The corresponding voltage can be set to 30V~36V.

[0048] For the cause of the short circuit fault, there is corresponding historical operation data used to train the fault detection model, including historical voltage values ​​of the photovoltaic array that do not belong to the first voltage range, and the historical voltage value causes the current to increase when it decreases.

[0049] In an exemplary embodiment, the operating data also includes the second operating data, and other implementation schemes are further proposed for inputting the operating data into a fault detection model to obtain the fault cause output by the fault detection model, specifically including: when it is determined that the first voltage value belongs to the first voltage range, determining the second voltage value of the boost converter from the second operating data; when it is determined that there is no voltage tolerance for the second voltage value, inputting the second voltage value into the fault detection model to obtain the second fault cause output by the fault detection model, wherein the second fault cause includes at least one of the following: source fluctuation and inductor failure, capacitor failure and duty cycle change.

[0050] Among them, for the causes of source fluctuations and inductor failure, there are corresponding historical operating data used to train the fault detection model, including historical voltage values ​​of the boost converter without voltage tolerance and the filtering rate of the boost converter that is less than a preset range.

[0051] In response to the causes of capacitor failure and duty cycle variation, there is historical operating data used to train the fault detection model, including historical voltage values ​​of the boost converter where there is no voltage tolerance and is greater than a preset tolerance range.

[0052] In an exemplary embodiment, the operating data also includes the third operating data. The technical solution for inputting the operating data into a fault detection model to obtain the fault cause output by the fault detection model may also include: when it is determined that the second voltage value has a voltage tolerance, determining the third voltage value of the inverter from the third operating data; when it is determined that the third voltage value does not have a voltage tolerance, inputting the third voltage value into the fault detection model to obtain the third fault cause output by the fault detection model, wherein the third fault cause includes at least one of the following: a short circuit fault or a switch fault, a source fluctuation of the input and power supply voltages.

[0053] For the causes of source fluctuations in input and power voltages, there are corresponding historical operating data used to train the fault detection model, including historical voltage values ​​of inverters that do not have voltage tolerance and do not belong to a preset range.

[0054] According to the causes of the short circuit fault or the switch fault, there is corresponding historical operation data used to train the fault detection model, including historical voltage values ​​of the inverter that do not have a voltage tolerance and are greater than a preset value.

[0055] In an exemplary embodiment, further, the following implementation steps are proposed: when it is determined that the first voltage value belongs to a first voltage range, if it is determined that the second voltage value has a voltage tolerance, and the third voltage value has a voltage tolerance, it is determined that the photovoltaic component has no fault during operation.

[0056] In an exemplary embodiment, during the training process of the fault detection model, the following formula may be used to represent the model parameters obtained by optimizing the Golden Eagle optimization algorithm:

[0057]

[0058] Where ΔX I represents the change in the position of Golden Eagle I between the tth iteration and the t+1th iteration, P A represents the attack coefficient at iteration t, P C represents the cruise coefficient at iteration t, and are all random vectors with a value range of [0, 1]. represents the attack vector of Golden Eagle I, Indicates the stopping point where Golden Eagle I stops iterating. and They respectively represent the Euclidean norm of the Golden Eagle I cruise attack vector.

[0059] In this embodiment, GEO is used to provide an effective optimization technology for DNN training, which reduces the training time and improves the accuracy of the model.

[0060] The principle of the Golden Eagle Optimization Algorithm relies on the spiral motion of the Golden Eagle. For example, each Golden Eagle will use the best cruise route to find food before attacking its prey. In each attack cycle, the Golden Eagle uses its prey model and strong memory skills to select a target from its memory and update it when it finds a better solution during the cruise and attack process. In GEO, the prey selection strategy is crucial.

[0061] In the attack of the golden eagle, an attack vector is used to represent the position relationship between the current position of the golden eagle and the position of the prey in memory. The attack vector is designed to guide the golden eagle to the position with the most prey.

[0062] The cruise vector is used to represent the speed of the golden eagle compared to the speed of its prey.

[0063] Optionally, in one embodiment, the principle of using GEO algorithm to optimize DNN model parameters during training is described. The attack vector of the Golden Eagle is represented by the following formula:

[0064] in, As the best location ever visited by Golden Eagle F, This is the attack vector of Golden Eagle I. As the current location of Golden Eagle I.

[0065] Next, consider is the position of Golden Eagle I as any point on the hyperplane, and considering This attack vector is used as the hyperplane normal to obtain the hyperplane cruise vector of the Golden Eagle I. After multiple rounds of iterations, the destination is determined by the calculated cruise vector of the Golden Eagle I.

[0066] where the angle vector is perpendicular to the circular cruise vector. This vector is placed in the tangent hyperplane and is calculated in n dimensions.

[0067] The golden eagle uses the vector and the attack action to reach the target position to attack the prey. To describe this step, the t iterations of the golden eagle I are as follows:

[0068]

[0069] Where ΔX I represents the change in the position of Golden Eagle I between the tth iteration and the t+1th iteration, P A represents the attack coefficient at iteration t, P C represents the cruise coefficient at iteration t, and are all random vectors with a value range of [0, 1]. represents the attack vector of Golden Eagle I, Indicates the stopping point where Golden Eagle I stops iterating. and They respectively represent the Euclidean norm of the Golden Eagle I cruise attack vector.

[0070]

[0071] Among them, t represents the current iteration number, T represents the current iteration and the maximum iteration number, and They are the cruise vector (P c )’s initial and final values. Accordingly, the proposed algorithm and is the attack vector (P A )’s initial and final values.

[0072] Fault prediction and detection of photovoltaic systems is achieved by combining deep neural networks and the Golden Eagle optimization algorithm. On the one hand, historical photovoltaic system data can be used through DNN to predict future system behavior, and on the other hand, GEO is used to optimize the parameters of the DNN model to improve accuracy. This combination improves the accuracy of fault prediction, detection capabilities, and overall system performance by reducing downtime, improving reliability, and facilitating targeted maintenance.

[0073] Obviously, the embodiments described above are only some embodiments of the present application, not all embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:

[0074] In an optional embodiment, the present application Figure 4 The principle of fault classification based on the input real-time operation data is explained. Figure 4 As shown, after the DNN parameters are optimized by using the GEO algorithm to obtain a trained DNN model, the real-time PV array voltage, temperature, irradiance, boost converter voltage, and inverter voltage are input into the trained DNN model, and then the PV array failure cause, inverter failure cause, and DC-DC boost converter failure cause are determined in turn.

[0075] Among them, in the judgment process, on the photovoltaic array side, if the photovoltaic array fails, the fault causes include shading, open circuit, and short circuit. If the photovoltaic array does not fail, the DC-DC boost converter is detected in the next stage. Assuming that the DC-DC boost converter fails, the fault causes include source fluctuation and inductor failure, capacitor failure, and duty cycle change.

[0076] Assuming that there is no fault in the photovoltaic array and the DC-DC boost converter, the inverter is detected. If the inverter fails, the cause of the fault is a short circuit fault or a switch fault, or a source fluctuation of the input and power supply voltage.

[0077] If no fault is detected after the above judgment, the inverter, DC-DC boost converter and PV array are all normal, and there is no fault in the three independent systems, and the overall working condition of the PV system is good.

[0078] It should be noted that the method proposed in this application is the joint execution of deep neural network (DNN) and Golden Eagle Optimization (GEO). The use of GEO provides an effective optimization technology for DNN training, while also reducing the training time. It has the advantages of data screening within the model, layered troubleshooting, and improving the accuracy of fault classification, thereby improving the accuracy of the model.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0080] In this embodiment, a device for determining the cause of a photovoltaic module failure is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0081] Figure 5 : is a structural block diagram of a device for determining the cause of a photovoltaic module failure according to an embodiment of the present application, the device comprising:

[0082] An acquisition module 52 is used to acquire operation data of the photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of the photovoltaic array, second operation data of the boost converter, and third operation data of the inverter;

[0083] Obtaining module 54, used for inputting the operation data into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operation data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm.

[0084] Through the above-mentioned device, the operating data of the photovoltaic component during operation, including the first operating data of the photovoltaic array, the second operating data of the boost converter, and the third operating data of the inverter, are obtained; then the operating data is input into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operating data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm. It can be seen that the present application proposes a fault detection model based on an artificial neural network and the Golden Eagle optimization algorithm for detecting photovoltaic system faults, which not only solves the technical problem that the cause of photovoltaic component failure cannot be comprehensively and accurately determined, but also improves the accuracy and comprehensiveness of the cause of photovoltaic component failure, thereby improving the system performance of the photovoltaic system based on photovoltaic components.

[0085] In an exemplary embodiment, the operating data includes at least the first operating data, and the obtaining module 54 is further used to: determine a first voltage value of the photovoltaic array from the first operating data; when it is determined that the first voltage value does not belong to the first voltage range, input the first voltage value into the fault detection model to obtain a first fault cause output by the fault detection model, wherein the first fault cause includes at least one of the following: a shading fault cause, an open circuit fault cause, and a short circuit fault cause.

[0086] In an exemplary embodiment, the operating data also includes the second operating data, and the obtaining module 54 is further used to: when it is determined that the first voltage value belongs to the first voltage range, determine the second voltage value of the boost converter from the second operating data; when it is determined that there is no voltage tolerance in the second voltage value, input the second voltage value into the fault detection model to obtain the second fault cause output by the fault detection model, wherein the second fault cause includes at least one of the following: source fluctuation and inductor failure, capacitor failure and duty cycle change.

[0087] In an exemplary embodiment, the operating data also includes the third operating data, and the obtaining module 54 is further used to: when it is determined that the second voltage value has a voltage tolerance, determine the third voltage value of the inverter from the third operating data; when it is determined that the third voltage value does not have a voltage tolerance, input the third voltage value into the fault detection model to obtain a third fault cause output by the fault detection model, wherein the third fault cause includes at least one of the following: a short circuit fault or a switch fault, a source fluctuation of the input and power supply voltage.

[0088] In an exemplary embodiment, the device for determining the cause of failure of a photovoltaic component also includes a determination module for determining that, when it is determined that the first voltage value belongs to a first voltage range, if it is determined that the second voltage value has a voltage tolerance, and if the third voltage value has a voltage tolerance, then determining that no failure has occurred in the photovoltaic component during operation.

[0089] In an exemplary embodiment, during the training process of the fault detection model, the obtaining module 54 is further used to: use the following formula to express the model parameters obtained by the optimization based on the Golden Eagle optimization algorithm:

[0090]

[0091] Where ΔX I represents the change in the position of Golden Eagle I between the tth iteration and the t+1th iteration, P A represents the attack coefficient at iteration t, P C represents the cruise coefficient at iteration t, and are all random vectors with a value range of [0, 1]. represents the attack vector of Golden Eagle I, Indicates the stopping point where Golden Eagle I stops iterating. and They respectively represent the Euclidean norm of the Golden Eagle I cruise attack vector.

[0092] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0093] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0094] S1, obtaining operation data of a photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of a photovoltaic array, second operation data of a boost converter, and third operation data of an inverter;

[0095] S2, inputting the operation data into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operation data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle Optimization Algorithm.

[0096] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0097] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0098] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0099] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0100] S1, obtaining operation data of a photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of a photovoltaic array, second operation data of a boost converter, and third operation data of an inverter;

[0101] S2, inputting the operation data into the fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained with historical operation data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle Optimization Algorithm.

[0102] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0103] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0104] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0105] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0106] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0107] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0108] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining the cause of a photovoltaic module failure, characterized in that: include: Acquiring operation data of the photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of the photovoltaic array, second operation data of the boost converter, and third operation data of the inverter; The operation data is input into a fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained using historical operation data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm.

2. The method according to claim 1, characterized in that The operation data at least includes the first operation data, and the operation data is input into a fault detection model to obtain a fault cause output by the fault detection model, including: determining a first voltage value of the photovoltaic array from the first operating data; When it is determined that the first voltage value does not belong to the first voltage range, the first voltage value is input into the fault detection model to obtain the first fault cause output by the fault detection model, wherein the first fault cause includes at least one of the following: shading fault cause, open circuit fault cause, and short circuit fault cause.

3. The method according to claim 2, characterized in that The operation data also includes the second operation data, and the operation data is input into the fault detection model to obtain the fault cause output by the fault detection model, including: determining a second voltage value of the boost converter from the second operating data when it is determined that the first voltage value belongs to a first voltage range; When it is determined that there is no voltage tolerance for the second voltage value, the second voltage value is input into a fault detection model to obtain a second fault cause output by the fault detection model, wherein the second fault cause includes at least one of the following: source fluctuation and inductor failure, capacitor failure and duty cycle change.

4. The method according to claim 3, characterized in that The operation data further includes the third operation data, and the operation data is input into the fault detection model to obtain the fault cause output by the fault detection model, including: In a case where it is determined that the second voltage value has a voltage tolerance, determining a third voltage value of the inverter from the third operating data; When it is determined that there is no voltage tolerance for the third voltage value, the third voltage value is input into the fault detection model to obtain a third fault cause output by the fault detection model, wherein the third fault cause includes at least one of the following: a short circuit fault or a switch fault, a source fluctuation of the input and power supply voltage.

5. The method according to claim 4, characterized in that The method further comprises: In the case where it is determined that the first voltage value belongs to the first voltage range, if it is determined that the second voltage value has a voltage tolerance and the third voltage value has a voltage tolerance, it is determined that the photovoltaic assembly has no fault during operation.

6. The method according to claim 5, characterized in that During the training process of the fault detection model, the method further includes: The following formula is used to express the model parameters optimized based on the Golden Eagle optimization algorithm: Where ΔX I represents the change in the position of Golden Eagle I between the tth iteration and the t+1th iteration, P A represents the attack coefficient at iteration t, P C represents the cruise coefficient at iteration t, and are all random vectors with a value range of [0, 1]. represents the attack vector of Golden Eagle I, Indicates the stopping point where Golden Eagle I stops iterating. and They respectively represent the Euclidean norm of the Golden Eagle I cruise attack vector.

7. A device for determining the cause of a photovoltaic module failure, characterized in that: include: An acquisition module, used for acquiring operation data of the photovoltaic assembly during operation, wherein the operation data includes at least one of the following: first operation data of the photovoltaic array, second operation data of the boost converter, and third operation data of the inverter; A module is obtained, which is used to input the operating data into a fault detection model to obtain the fault cause output by the fault detection model, wherein the fault detection model is trained using historical operating data as input samples and historical fault causes as output samples, and the model parameters of the fault detection model are optimized based on the Golden Eagle optimization algorithm.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images