Arc detection method and device for photovoltaic system and photovoltaic system

Abstract

The present application discloses an arc detection method, device and photovoltaic system for a photovoltaic system, and belongs to the technical field of photovoltaic systems. The arc detection method for the photovoltaic system comprises: performing a fast Fourier transform on the sampled values ​​of the output sampling signal of the photovoltaic system to obtain the amplitude information and phase information of the output sampling signal; converting the amplitude information and the phase information into a target classification image; inputting the target classification image into a detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal; wherein the detection model is trained using a sample classification image as a sample and a sample arc detection result as a sample label. The arc detection method for the photovoltaic system of the present application can improve the noise adaptability and scene adaptability of arc detection, and improve the accuracy of arc detection, and reduce false detection and missed detection.

Description

Technical Field

[0001] The present application belongs to the technical field of photovoltaic systems, and in particular, relates to an arc detection method and device for a photovoltaic system, and a photovoltaic system. Background Art

[0002] In the process of DC arc detection, it is easy to make false detections when the output current noise of the photovoltaic system is large, and it is easy to miss detections when the current is long and the cable is large. In the related art, noise data and arc data are mainly collected, and the extracted features are classified by artificial intelligence algorithms or manually extracting data-related features to determine the arc detection results. However, in the above method, information will be lost in the process of extracting features, and it is difficult to extract comprehensive data features. The noise adaptability and scene adaptability of the algorithm detection are low, resulting in low detection accuracy. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes an arc detection method, device and photovoltaic system for a photovoltaic system, which improves the noise adaptability and scene adaptability of arc detection, improves the accuracy of arc detection, and reduces false detection and missed detection.

[0004] In a first aspect, the present application provides an arc detection method for a photovoltaic system, the method comprising:

[0005] Performing a fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal;

[0006] Converting the amplitude information and the phase information into a target classification image;

[0007] Inputting the target classification image into a detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal;

[0008] in,

[0009] The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

[0010] According to the arc detection method for a photovoltaic system of the present application, by performing a fast Fourier transform on the acquired output sampling signal, amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through a detection model, thereby improving the noise adaptability and scene adaptability of the arc detection, and improving the accuracy of the arc detection, reducing false detections and missed detections.

[0011] According to the arc detection method for a photovoltaic system of the present application, the converting of the amplitude information and the phase information into a target classification image includes:

[0012] Converting the amplitude information into an amplitude-frequency image, and converting the phase information into a phase-frequency image;

[0013] The amplitude-frequency image and the phase-frequency image are spliced ​​to obtain the target classification image.

[0014] According to the arc detection method for a photovoltaic system of the present application, the amplitude-frequency image is used to characterize the change of the amplitude of the output sampling signal over time, and the phase-frequency image is used to characterize the change of the phase of the output sampling signal over time; the splicing of the amplitude-frequency image and the phase-frequency image to obtain the target classification image includes at least one of the following methods:

[0015] The edge of the target image on the X-axis side is spliced ​​with the edge of another image other than the target image away from the X-axis side to obtain the target classification image; the target image is any one of the amplitude-frequency image and the phase-frequency image; the X-axis is the coordinate axis corresponding to the time information;

[0016] The edge of the target image on the Y-axis side is spliced ​​with the edge of another image other than the target image away from the Y-axis side to obtain the target classification image; the Y-axis is the coordinate axis corresponding to the amplitude information or the phase information;

[0017] splicing the edge of the target image away from the X-axis side with the edge of another image other than the target image on the X-axis side to obtain the target classification image;

[0018] The edge of the target image away from the Y-axis side is spliced ​​with the edge of another image other than the target image on the Y-axis side to obtain the target classification image.

[0019] According to the arc detection method for a photovoltaic system of the present application, the step of inputting the target classification image into a detection model to obtain the arc detection result output by the detection model includes:

[0020] The target classification image is input into the detection model to obtain the noise category corresponding to the non-arc signal output by the detection model.

[0021] According to the arc detection method for a photovoltaic system of the present application, the step of inputting the target classification image into a detection model to obtain the arc detection result output by the detection model includes:

[0022] Inputting the target classification image into the detection model to obtain a self-detection signal output by the detection model;

[0023] in,

[0024] The detection model is trained using sample classification images as samples and sample self-detection signals as sample labels.

[0025] According to the arc detection method for a photovoltaic system of the present application, the detection model includes at least two output layers.

[0026] In a second aspect, the present application provides an arc detection device for a photovoltaic system, the device comprising:

[0027] A first processing module is used to perform a fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal;

[0028] A second processing module, used for converting the amplitude information and the phase information into a target classification image;

[0029] A third processing module is used to input the target classification image into a detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal;

[0030] in,

[0031] The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

[0032] According to the arc detection device of the photovoltaic system of the present application, by performing fast Fourier transform on the acquired output sampling signal, amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through the detection model, thereby improving the noise adaptability and scene adaptability of the arc detection, and improving the accuracy of the arc detection, reducing false detections and missed detections.

[0033] In a third aspect, the present application provides a photovoltaic system, comprising:

[0034] at least one solar panel;

[0035] The photovoltaic system performs arc detection based on the arc detection method for the photovoltaic system as described in the first aspect.

[0036] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the arc detection method for a photovoltaic system as described in the first aspect above is implemented.

[0037] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the arc detection method for a photovoltaic system as described in the first aspect above.

[0038] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0039] By performing fast Fourier transform on the acquired output sampling signal, the amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through the detection model, thereby improving the noise adaptability and scene adaptability of arc detection, and improving the accuracy of arc detection, reducing false detection and missed detection.

[0040] Furthermore, by further analyzing the amplitude information and phase information when it is determined that there is a non-arc signal in the output sampling signal, the non-arc signal is divided into noise signals containing multiple categories to distinguish different categories of noise signals in the non-arc signal, thereby improving the tolerance to noise in the arc detection process and improving the arc detection accuracy.

[0041] Furthermore, by performing self-test on the arc detection circuit and outputting a self-test signal to confirm the working status of the arc detection circuit, the underreporting and false alarms caused by arc detection voltage failures can be reduced to improve the accuracy of arc detection. The self-test signal can also promptly remind the operator to inspect the arc detection circuit to reduce unnecessary losses caused by arc detection circuit failures.

[0042] Furthermore, by setting the output layer of the detection model to multiple dimensions, the number of arc detection result categories can be flexibly set based on the actual detection accuracy requirements, and various types of noise signals existing in non-arc signals can be distinguished, providing a variety of usage scenarios and improving user experience.

[0043] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0045] Figure 1 is a flow chart of an arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0046] Figure 2 This is one of the principle schematic diagrams of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0047] Figure 3 This is the second principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0048] Figure 4 This is the third principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0049] Figure 5 This is the fourth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0050] Figure 6 This is the fifth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0051] Figure 7 This is the sixth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0052] Figure 8 This is the seventh principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0053] Fig. 9 This is the eighth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0054] Fig.10 This is the ninth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0055] Fig.11 This is the tenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0056] Fig.12 This is the eleventh principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0057] Fig.13 This is the twelfth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0058] Fig.14 This is the thirteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0059] Fig.15 This is the fourteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0060] Fig.16 This is the fifteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0061] Fig.17 This is the sixteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0062] Fig.18 FIG. 17 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0063] Fig.19 This is the eighteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0064] Fig. 20 This is the nineteenth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0065] Fig.21 This is the twentieth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0066] Fig. 22 This is the twenty-first principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0067] Fig.23 FIG22 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0068] Fig.24 FIG23 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0069] Fig.25 FIG24 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0070] Fig.26 FIG25 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0071] Fig. 27 FIG26 is a schematic diagram of the principle of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0072] Fig.28 This is the twenty-seventh principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0073] Fig.29 This is the twenty-eighth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0074] Fig.30 This is the twenty-ninth principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0075] Fig.31This is the 30th principle schematic diagram of the arc detection method for a photovoltaic system provided in an embodiment of the present application;

[0076] Fig.32 is a schematic structural diagram of an arc detection device for a photovoltaic system provided in an embodiment of the present application;

[0077] Fig.33 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0079] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0080] In combination with the accompanying drawings, the arc detection method for a photovoltaic system, the arc detection device for a photovoltaic system, the photovoltaic system, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail below through specific embodiments and their application scenarios.

[0081] The arc detection method of the photovoltaic system may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0082] The terminal includes but is not limited to portable communication devices such as mobile phones or tablet computers. It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer.

[0083] The terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0084] The embodiment of the present application provides an arc detection method for a photovoltaic system, and the executor of the arc detection method for the photovoltaic system can be the photovoltaic system, or can be an arc detection device of the photovoltaic system arranged on the photovoltaic system, or can also be a server electrically connected to the photovoltaic system (wired or wireless connection), or can also be a user terminal communicatively connected to the photovoltaic system, including but not limited to mobile terminals and non-mobile terminals.

[0085] like Figure 1 As shown, the arc detection method of the photovoltaic system includes: step 110 and step 120.

[0086] Step 110: Perform fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal;

[0087] In this step, the output sampling signal is a signal used to detect whether there is an arc in the photovoltaic system.

[0088] The output sampling signal may include: the output current of the photovoltaic system and the output voltage of the photovoltaic system.

[0089] The sampled value is the actual data of the output sampled signal obtained by sampling.

[0090] The sampled value of the output current of the photovoltaic system can be Figure 2 shown.

[0091] Fast Fourier transform is to convert the sampled values ​​of the output sampled signal into the frequency domain.

[0092] The amplitude information and the phase information are frequency domain related features of the output sampling signal.

[0093] The amplitude information is the amplitude of the output sampling signal in the frequency domain, reflecting the strength of the output sampling signal at each frequency.

[0094] The phase information is the phase information of each frequency component of the output sampling signal in the frequency domain, reflecting the time offset of the output sampling signal at each frequency component. The phase information can be represented by an angle.

[0095] In the actual implementation process, the output sampling signal of the photovoltaic inverter can be collected through current sensors, Hall elements, voltage sensors, and voltage sampling devices.

[0096] Of course, the sampling value of the output sampling signal of the photovoltaic system may also be obtained by any other feasible method, which is not limited in this application.

[0097] After obtaining the sampling value of the output sampling signal, the sampling value can be fast Fourier transformed by the fast Fourier transform algorithm to convert the sampling value to the frequency domain to obtain the amplitude information and phase information of the output sampling signal so as to perform frequency domain analysis on the output sampling signal.

[0098] Fast Fourier transform algorithms include, but are not limited to, Cooley-Tukey algorithm, Radix-2 algorithm, and Radix-4 algorithm.

[0099] In the actual implementation process, a suitable fast Fourier transform algorithm can be selected based on the actual situation of the output sampling signal, and this application does not limit it.

[0100] Step 120, converting the amplitude information and the phase information into a target classification image;

[0101] In this step, the target classification image is an image including amplitude information and phase information of the output sampling signal.

[0102] In the actual implementation process, the amplitude information can be converted into an image including the amplitude information, and the image obtained by the phase information conversion is further added to the image including the amplitude information to obtain the target classification image.

[0103] A canvas can also be divided into two parts equally. In the first part, an image corresponding to the amplitude information is drawn based on the amplitude information, and in the second part, an image corresponding to the phase information is drawn based on the phase information to obtain a target classification image.

[0104] Similarly, an image corresponding to the phase information may be drawn in the first part based on the phase information, and an image corresponding to the phase information may be drawn in the second part based on the amplitude information to obtain a target classification image.

[0105] Step 130: input the target classification image into the detection model to obtain the arc detection result output by the detection model.

[0106] In this step, the detection model is a model for analyzing arc conditions in the output sampling signal.

[0107] The detection model can be an image classification model such as an artificial intelligence model, a machine learning model, a deep learning model, and a neural network model.

[0108] The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

[0109] The sample classification image is an image obtained based on a plurality of historical output sampling signals, including amplitude information and phase information of the historical output sampling signals.

[0110] The sample arc detection result is the actual situation of the existence of arc signals and non-arc signals in the historical output sampling signals corresponding to the sample classification image.

[0111] During the actual execution process, sample classification images of multiple historical output sampling signals can be collected, and sample arc detection results corresponding to each historical output sampling signal can be obtained. The obtained sample classification images and sample arc detection results are used as training sets to train the detection model so that the detection model is suitable for arc detection of output sampling signals.

[0112] The arc detection result is used to characterize at least one of the presence of an arc signal and the presence of a non-arc signal.

[0113] The arc presence signal is used to indicate the presence of arc features in the output sampling signal.

[0114] The presence of the non-arcing signal is used to characterize the presence of noise characteristics in the output sampling signal.

[0115] In some embodiments, the output sampling signal may contain a non-arcing signal.

[0116] In some other embodiments, the output sampling signal may contain a non-arc signal.

[0117] In the actual implementation process, after obtaining the output sampling signal of the photovoltaic system, the sampling value of the output sampling signal can be subjected to a fast Fourier transform to obtain the amplitude information and phase information of the output sampling signal, and the amplitude information and phase information are converted into a visual target classification image. The target classification image is input into the detection model, and the target classification image is analyzed by the detection model to obtain the arc detection result predicted by the detection model to determine whether there is an arc in the output sampling signal.

[0118] During the research and development process, the inventors found that it is easy to misdetect when the output current noise of the photovoltaic system is large, and it is easy to miss detection when the long cable has a large current. In the related art, the noise data and arc data are mainly collected, and the extracted features are classified by artificial intelligence algorithms or manually extracting data-related features to determine the arc detection results. However, in the process of extracting features, the above method will lose information and it is difficult to extract comprehensive data features. The noise adaptability and scene adaptability of the algorithm detection are low, resulting in low detection accuracy.

[0119] The present application samples the output sampling signal of the photovoltaic inverter to obtain the sampling value of the output sampling signal, and performs fast Fourier transform on the sampling value to obtain the amplitude information and phase information of the output sampling signal. The amplitude information and phase information can more comprehensively characterize the data features of the output sampling signal, convert the more comprehensive data features into a target classification image, analyze the target classification image through a detection model, obtain an accurate arc detection result of the output sampling signal, and analyze the output sampling signal in the frequency domain to distinguish between arc signals and non-arc signals, thereby improving the noise adaptability and scene adaptability of arc detection, and improving the accuracy of arc detection, reducing false detections and missed detections.

[0120] According to the arc detection method for a photovoltaic system provided in an embodiment of the present application, by performing a fast Fourier transform on the acquired output sampling signal, amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through a detection model, thereby improving the noise adaptability and scene adaptability of the arc detection, and improving the accuracy of the arc detection, thereby reducing false detections and missed detections.

[0121] In some embodiments, step 120 may further include:

[0122] Convert amplitude information into amplitude-frequency image, and convert phase information into phase-frequency image;

[0123] The amplitude-frequency image and the phase-frequency image are stitched together to obtain the target classification image.

[0124] In this embodiment, the amplitude-frequency image is an image including amplitude information of the output sampling signal.

[0125] The phase-frequency image is an image including the phase information of the output sampling signal.

[0126] The size of the amplitude-frequency image is the same as that of the phase-frequency image.

[0127] In the actual implementation process, after obtaining the amplitude-frequency image and the phase-frequency image, the amplitude-frequency image and the phase-frequency image can be directly spliced ​​to obtain the target classification image.

[0128] According to the arc detection method for a photovoltaic system provided in an embodiment of the present application, by converting amplitude information into an amplitude-frequency image and converting phase information into a phase-frequency image, an image that is easier to observe and analyze can be obtained, and the amplitude-frequency image and the phase-frequency image can be spliced ​​to improve the comprehensiveness of the output sampling signal features contained in the target classification image.

[0129] In some embodiments, the amplitude-frequency image is used to characterize the change of the amplitude of the output sampling signal over time, and the phase-frequency image is used to characterize the change of the phase of the output sampling signal over time; splicing the amplitude-frequency image and the phase-frequency image to obtain the target classification image may include at least one of the following methods:

[0130] The edge of the target image on the X-axis side is spliced ​​with the edge of another image other than the target image and away from the X-axis side to obtain a target classification image; the target image is any image of the amplitude-frequency image and the phase-frequency image; the X-axis is the coordinate axis corresponding to the time information;

[0131] The edge of the target image on the Y axis side is spliced ​​with the edge of another image other than the target image away from the Y axis side to obtain a target classification image; the Y axis is the coordinate axis corresponding to the amplitude information or the phase information;

[0132] The edge of the target image away from the X-axis side is spliced ​​with the edge of another image other than the target image on the X-axis side to obtain a target classification image;

[0133] The edge of the target image away from the Y axis is spliced ​​with the edge of another image on the Y axis except the target image to obtain the target classification image.

[0134] In this embodiment, the target image is any one of an amplitude-frequency image and a phase-frequency image.

[0135] In the case where the target image is an amplitude-frequency image, the other image is a phase-frequency image.

[0136] In the case where the target image is a phase-frequency image, the other image is an amplitude-frequency image.

[0137] The X-axis is the coordinate axis corresponding to the time information.

[0138] The Y-axis is the coordinate axis corresponding to the amplitude information or the phase information.

[0139] The sampling value of the output sampling signal is as follows Figure 2 In the case shown, we can get Figure 3 The amplitude-frequency image shown and Figure 4 The phase-frequency image shown.

[0140] Taking the target image as an amplitude image as an example, the edge of the amplitude-frequency image on the X-axis side and the edge of the phase-frequency image away from the X-axis side can be spliced ​​to obtain the following: Figure 5 The target classification image shown, that is, the amplitude-frequency image is above the phase-frequency image.

[0141] The sampling value of the output sampling signal is as follows Figure 6 In the case shown, we can get Figure 7 The amplitude-frequency image shown and Figure 8 The phase-frequency image shown.

[0142] Taking the target image as a phase-frequency image as an example, the edge of the phase-frequency image on the X-axis side and the edge of the amplitude-frequency image away from the X-axis side can be spliced ​​to obtain the following: Fig. 9 The target classification image shown, that is, the phase-frequency image is above the amplitude-frequency image.

[0143] The sampling value of the output sampling signal is as follows Fig.10 In the case shown, we can get Fig.11 The amplitude-frequency image shown and Fig.12 The phase-frequency image shown.

[0144] Taking the target image as a phase-frequency image as an example, the edge on the Y-axis side of the phase-frequency image and the edge away from the Y-axis side of the amplitude-frequency image can be spliced ​​to obtain the following: Fig.13 The target classification image shown, that is, the amplitude-frequency image is on the left side of the phase-frequency image.

[0145] The sampling value of the output sampling signal is as follows Fig.14 In the case shown, we can get Fig.15 The amplitude-frequency image shown and Fig.16 The phase-frequency image shown.

[0146] Taking the target image as an amplitude-frequency image as an example, the edge of the amplitude-frequency image on the Y axis side and the side away from the Y axis side of the phase-frequency image can be spliced ​​to obtain the following: Fig.17 The target classification image shown, that is, the phase-frequency image is on the left side of the amplitude-frequency image.

[0147] The sampling value of the output sampling signal is as follows Fig.18 In the case shown, we can get Fig.19 The amplitude-frequency image shown and Fig. 20 The phase-frequency image shown.

[0148] Taking the target image as an amplitude-frequency image as an example, the edge of the amplitude-frequency image away from the X-axis side can be spliced ​​with the edge of the phase-frequency image on the X-axis side, and the following is obtained: Fig.23 The target classification image shown.

[0149] That is, based on the edge of the amplitude frequency image in the X-axis direction and the edge of the phase frequency image in the X-axis direction, the image is mirrored and flipped, as shown below: Fig.21 The flipped amplitude-frequency image in the X-axis direction shown in FIG. Fig. 22 The flipped phase-frequency image in the X-axis direction is shown.

[0150] The edge of the flipped amplitude frequency image in the X-axis direction and the edge of the flipped phase frequency image in the X-axis direction away from the X-axis side can be spliced ​​to obtain the following: Fig.23 The target classification image shown, that is, the flipped amplitude-frequency image in the X-axis direction is above the flipped phase-frequency image in the X-axis direction.

[0151] Taking the target image as a phase-frequency image as an example, the edge of the phase-frequency image away from the X-axis side can be spliced ​​with the edge of the amplitude-frequency image on the X-axis side, and the following is obtained: Fig.24 The target classification image shown.

[0152] The edge of the flipped phase-frequency image in the X-axis direction on the X-axis side and the edge of the flipped amplitude-frequency image in the X-axis direction away from the X-axis side can be spliced ​​to obtain the following: Fig.24 The target classification image shown, that is, the flipped phase-frequency image in the X-axis direction is above the flipped amplitude-frequency image in the X-axis direction.

[0153] The sampling value of the output sampling signal is as follows Fig.25 In the case shown, we can get Fig.26 The amplitude-frequency image shown and Fig. 27 The phase-frequency image shown.

[0154] Taking the target image as the amplitude-frequency image and the other image as the phase-frequency image as an example, the amplitude-frequency image and the phase-frequency image can be flipped based on the Y-axis edge of the amplitude-frequency image and the Y-axis edge of the phase-frequency image, respectively, to obtain the following: Fig.28 The Y-axis flipped amplitude-frequency image shown in FIG. Fig.29 The phase-frequency image shown is flipped in the Y-axis direction.

[0155] The edge of the amplitude-frequency image flipped in the Y-axis direction on the X-axis side is spliced ​​with the edge of the phase-frequency image flipped in the Y-axis direction away from the X-axis direction, and the following is obtained: Fig.30 The target classification image shown is Fig.28 Splice in Fig.29 above.

[0156] The edge of the phase-frequency image flipped in the Y-axis direction on the X-axis side is spliced ​​with the edge of the amplitude-frequency image flipped in the Y-axis direction away from the X-axis direction, and the following is obtained: Fig.31 The target classification image shown is Fig.29 Splice in Fig.28 above.

[0157] Taking the target image as an amplitude-frequency image as an example, the edge of the amplitude-frequency image away from the Y-axis side can be spliced ​​with the edge of the phase-frequency image on the Y-axis side to obtain the target classification image, that is, Fig.28 Splice in Fig.29 on the right side.

[0158] Taking the target image as a phase-frequency image as an example, the edge of the phase-frequency image away from the Y-axis side can be spliced ​​with the edge of the amplitude-frequency image on the Y-axis side to obtain the target classification image, that is, Fig.29 Splice in Fig.28 on the right side.

[0159] According to the arc detection method for a photovoltaic system provided in an embodiment of the present application, by using the long side of the amplitude-frequency image and the long side of the phase-frequency image as the splicing side, or using the short side of the amplitude-frequency image and the short side of the phase-frequency image as the splicing side, the amplitude-frequency image and the phase-frequency image are flexibly spliced, and the splicing methods are diverse. Users can choose a suitable splicing method based on actual usage needs to improve user experience.

[0160] In some embodiments, step 130 may further include:

[0161] The target classification image is input into the detection model to obtain the noise category corresponding to the presence of non-arc signals output by the detection model.

[0162] In this embodiment, the noise category is a category obtained by further classifying the non-arc signal based on the difference between the feature of the non-arc signal and the arc signal.

[0163] During the actual execution process, when it is determined that there is a non-arc signal in the output sampling signal, if the difference between the data features corresponding to the non-arc signal and the data features corresponding to the arc signal is large, then it can be determined that the arc detection result is that there is a non-arc signal.

[0164] If the difference between the data features corresponding to the non-arc signal and the data features corresponding to the arc signal is small, then it can be determined that the arc detection result is the existence of a non-arc signal, but it is difficult to distinguish whether there is an arc feature in the non-arc signal. At this time, the non-arc signal can be further subdivided and divided into different categories.

[0165] For example, the presence of a non-arc signal is further divided into the presence of a normal noise signal and the presence of a severe noise signal.

[0166] For another example, the presence of an arc signal is further divided into: the presence of a primary noise signal, the presence of a secondary noise signal, the presence of a tertiary noise signal, and the like.

[0167] During the actual execution process, after the target classification image is input into the detection model, the detection model can further divide the features of the non-arc signal in the target classification image during the analysis of the target classification model, and output the noise category corresponding to the non-arc signal. For example, the noise category corresponding to the non-arc signal is a harsh noise signal.

[0168] According to the arc detection method for a photovoltaic system provided in an embodiment of the present application, by analyzing the amplitude information and phase information in the target classification image, the non-arc signal is divided into noise signals containing multiple categories to distinguish different categories of noise signals in the non-arc signal, thereby improving the tolerance to noise in the arc detection process and improving the arc detection accuracy.

[0169] In some embodiments, after step 120, the method may further include:

[0170] The target classification image is input into the detection model to obtain the self-detection signal output by the detection model.

[0171] In this embodiment, the self-detection signal is a signal obtained by detecting the working state of the arc detection circuit.

[0172] The self-test signal is used to indicate that the arc detection circuit is working normally or abnormally.

[0173] The detection model is trained using sample classification images as samples and sample self-detection signals as sample labels.

[0174] The sample self-check signal is the actual state of the self-check signal in the historical output sampling signal corresponding to the sample classification image.

[0175] In the actual implementation process, multiple different sample classification images can be collected, and sample self-test signals corresponding to the sample classification images can be obtained. The obtained sample classification images and sample self-test signals are used as training sets to train the detection model.

[0176] When there is a certain difference between the data features corresponding to the self-test signal and the data features corresponding to the arc signal, the self-test signal in the output sampling signal can be output as a separate category in the arc detection result by analyzing the target classification image.

[0177] According to the arc detection method for a photovoltaic system provided in an embodiment of the present application, a self-test is performed on the arc detection circuit and a self-test signal is output to confirm the working status of the arc detection circuit, reduce missed alarms and false alarms caused by arc detection voltage failures, and improve the accuracy of arc detection. The self-test signal can also be used to promptly remind the operator to test the arc detection circuit, thereby reducing unnecessary losses caused by arc detection circuit failures.

[0178] In some embodiments, the detection model is a binary classification or multi-classification model.

[0179] In this embodiment, the detection model may be a binary classification model, a ternary classification model, or a multi-class classification model.

[0180] The classification model may be a convolutional neural network structure, or a classification algorithm adjusted on the basis of the convolutional neural network.

[0181] The specific selection of the classification model can be based on user customization or determined based on actual execution conditions, and this application does not limit it.

[0182] For example, the classification model is a LeNet-5 convolutional neural network structure, and the dimension of the output layer of the LeNet-5 convolutional neural network structure can be set to 2, that is, the classification results corresponding to the output layer include: the existence of an arc signal and the existence of a non-arc signal.

[0183] For example, the classification model is a ResNet convolutional neural network structure, and the dimension of the output layer of the ResNet convolutional neural network structure can be set to 3, that is, the classification results corresponding to the output layer include: the presence of an arc signal, the presence of an ordinary noise signal, and the presence of a severe noise signal.

[0184] For another example, the classification model is a MobileViT convolutional neural network structure, and the dimension of the output layer of the MobileViT convolutional neural network structure can be set to 4, that is, the classification results corresponding to the output layer include: the presence of arc signals, self-test signals, the presence of ordinary noise signals, and the presence of severe noise.

[0185] In the actual execution process, based on experience, the sampled values ​​of the acquired output sampling signals can be analyzed to determine whether the arc features and non-arc features are obvious, and to determine the actual dimension of the output layer.

[0186] For example, when the arc features and the non-arc features are obvious, the dimension of the output layer is determined to be 2.

[0187] For another example, when the arc features and non-arc features are not obvious, the dimension of the output layer is determined to be 4.

[0188] According to the arc detection method for photovoltaic systems provided in the embodiments of the present application, by setting the output layer of the detection model to multiple dimensions, the number of arc detection result categories can be flexibly set based on the actual detection accuracy requirements, and various types of noise signals existing in non-arc signals can be distinguished, providing a variety of usage scenarios and improving user experience.

[0189] The arc detection method for a photovoltaic system provided in the embodiment of the present application can be performed by an arc detection device for a photovoltaic system. The arc detection method for a photovoltaic system performed by an arc detection device for a photovoltaic system is used as an example to illustrate the arc detection device for a photovoltaic system provided in the embodiment of the present application.

[0190] An embodiment of the present application also provides an arc detection device for a photovoltaic system.

[0191] like Fig.32 As shown, the arc detection device of the photovoltaic system includes: a first processing module 3210 , a second processing module 3220 and a third processing module 3230 .

[0192] The first processing module 3210 is used to perform a fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal;

[0193] The second processing module 3220 is used to input the target classification image into the detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal;

[0194] The third processing module 3230 is used to input the target classification image into the detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal;

[0195] in,

[0196] The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

[0197] According to the arc detection device for a photovoltaic system provided in an embodiment of the present application, by performing a fast Fourier transform on the acquired output sampling signal, amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through a detection model, thereby improving the noise adaptability and scene adaptability of the arc detection, and improving the accuracy of the arc detection, reducing false detections and missed detections.

[0198] In some embodiments, the second processing module 3220 may also be used to:

[0199] Convert amplitude information into amplitude-frequency image, and convert phase information into phase-frequency image;

[0200] The amplitude-frequency image and the phase-frequency image are stitched together to obtain the target classification image.

[0201] In some embodiments, the amplitude-frequency image is used to characterize the change of the amplitude of the output sampling signal over time, and the phase-frequency image is used to characterize the change of the phase of the output sampling signal over time; the second processing module 3220 can also be used to:

[0202] The edge of the target image on the X-axis side is spliced ​​with the edge of another image other than the target image and away from the X-axis side to obtain a target classification image; the target image is any image of the amplitude-frequency image and the phase-frequency image; the X-axis is the coordinate axis corresponding to the time information;

[0203] The edge of the target image on the Y axis side is spliced ​​with the edge of another image other than the target image away from the Y axis side to obtain a target classification image; the Y axis is the coordinate axis corresponding to the amplitude information or the phase information;

[0204] The edge of the target image away from the X-axis is spliced ​​with the edge of another image other than the target image on the X-axis side to obtain a target classification image;

[0205] The edge of the target image away from the Y axis is spliced ​​with the edge of another image on the Y axis except the target image to obtain the target classification image.

[0206] In some embodiments, the second processing module 3220 may also be used to:

[0207] The target classification image is input into the detection model to obtain the noise category corresponding to the presence of non-arc signals output by the detection model.

[0208] In some embodiments, the second processing module 3220 may also be used to:

[0209] Input the target classification image into the detection model to obtain the self-detection signal output by the detection model;

[0210] in,

[0211] The detection model is trained using sample classification images as samples and sample self-detection signals as sample labels.

[0212] The arc detection device of the photovoltaic system in the embodiment of the present application can be a photovoltaic system, or can be an electronic device connected to the photovoltaic system for communication, or can be a component in the photovoltaic system or electronic device, such as an integrated circuit or chip. The electronic device can be a terminal, or can be other devices other than the terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0213] The arc detection device of the photovoltaic system in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0214] The arc detection device for a photovoltaic system provided in the embodiment of the present application can achieve Figures 1 to 31 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0215] In some embodiments, Fig.33 As shown, an embodiment of the present application further provides an electronic device 3300, including a processor 3301, a memory 3302, and a computer program stored in the memory 3302 and executable on the processor 3301. When the program is executed by the processor 3301, each process of the arc detection method embodiment of the above-mentioned photovoltaic system is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0216] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0217] The embodiment of the present application also provides a photovoltaic system.

[0218] In some embodiments, a photovoltaic system includes: at least one solar panel.

[0219] In this embodiment, during the actual implementation process, output sampling signals of the solar panel, such as output current and output voltage, may be collected.

[0220] The photovoltaic system is detected based on the arc detection result of the photovoltaic system as described in any of the above embodiments.

[0221] According to the photovoltaic system provided in the embodiment of the present application, by performing fast Fourier transform on the acquired output sampling signal, amplitude information and phase information that can more comprehensively characterize the characteristics of the sampling value data are obtained, the amplitude information and phase information are converted into a target classification image, and the arc detection result of the output sampling signal is obtained through the detection model, thereby improving the noise adaptability and scene adaptability of the arc detection, and improving the accuracy of the arc detection, reducing false detections and missed detections.

[0222] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned photovoltaic system arc detection method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0223] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0224] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned arc detection method for the photovoltaic system when executed by a processor.

[0225] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0226] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned photovoltaic system arc detection method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0227] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0228] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0229] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus 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 relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0230] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0231] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0232] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for detecting arc in a photovoltaic system, characterized in that: include: Performing a fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal; Converting the amplitude information and the phase information into a target classification image; Inputting the target classification image into a detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal; in, The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

2. The arc detection method for a photovoltaic system according to claim 1, characterized in that: The converting the amplitude information and the phase information into a target classification image includes: Converting the amplitude information into an amplitude-frequency image, and converting the phase information into a phase-frequency image; The amplitude-frequency image and the phase-frequency image are spliced ​​to obtain the target classification image.

3. The arc detection method of a photovoltaic system according to claim 2, characterized in that: The amplitude-frequency image is used to characterize the change of the amplitude of the output sampling signal over time, and the phase-frequency image is used to characterize the change of the phase of the output sampling signal over time; the splicing of the amplitude-frequency image and the phase-frequency image to obtain the target classification image includes at least one of the following methods: The edge of the target image on the X-axis side is spliced ​​with the edge of another image other than the target image away from the X-axis side to obtain the target classification image; the target image is any one of the amplitude-frequency image and the phase-frequency image; the X-axis is the coordinate axis corresponding to the time information; The edge of the target image on the Y-axis side is spliced ​​with the edge of another image other than the target image away from the Y-axis side to obtain the target classification image; the Y-axis is the coordinate axis corresponding to the amplitude information or the phase information; splicing the edge of the target image away from the X-axis side with the edge of another image other than the target image on the X-axis side to obtain the target classification image; The edge of the target image away from the Y-axis side is spliced ​​with the edge of another image other than the target image on the Y-axis side to obtain the target classification image.

4. The arc detection method for a photovoltaic system according to any one of claims 1 to 3, characterized in that: The step of inputting the target classification image into a detection model to obtain the arc detection result output by the detection model includes: The target classification image is input into the detection model to obtain the noise category corresponding to the non-arc signal output by the detection model.

5. The arc detection method for a photovoltaic system according to any one of claims 1 to 3, characterized in that: After converting the amplitude information and the phase information into a target classification image, the method further includes: Inputting the target classification image into the detection model to obtain a self-detection signal output by the detection model; in, The detection model is trained using sample classification images as samples and sample self-detection signals as sample labels.

6. The arc detection method for a photovoltaic system according to any one of claims 1 to 3, characterized in that: The detection model is a binary classification model or a multi-classification model.

7. An arc detection device for a photovoltaic system, characterized in that: include: A first processing module is used to perform a fast Fourier transform on the sampled value of the output sampled signal of the photovoltaic system to obtain amplitude information and phase information of the output sampled signal; A second processing module, used for converting the amplitude information and the phase information into a target classification image; A third processing module is used to input the target classification image into a detection model to obtain the arc detection result output by the detection model; the arc detection result is used to characterize the existence of an arc signal or a non-arc signal; in, The detection model is trained using sample classification images as samples and sample arc detection results as sample labels.

8. A photovoltaic system, characterized in that: include: at least one solar panel; The photovoltaic system performs arc detection based on the arc detection method for the photovoltaic system according to any one of claims 1 to 6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the arc detection method for the photovoltaic system according to any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the arc detection method for a photovoltaic system as described in any one of claims 1 to 6 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the arc detection method for a photovoltaic system according to any one of claims 1 to 6 is implemented.

Images