Arc discharge detection equipment, detection system, arc discharge detection method and storage medium

Abstract

The invention discloses arc discharge detection equipment, a detection system, an arc discharge detection method and a storage medium, and the equipment comprises a first detection circuit which is connected with a photovoltaic power generation system and is used for carrying out the arc discharge detection of the photovoltaic power generation system; the second detection circuit is connected with the photovoltaic power generation system and is used for carrying out arc discharge detection on the photovoltaic power generation system; the first processing circuit is used for determining whether an arc discharge phenomenon occurs in the photovoltaic power generation system according to a detection result of the first detection circuit and / or a detection result of the second detection circuit; wherein the first detection circuit carries out arc discharge detection based on an AI model, and the second detection circuit carries out arc discharge detection based on arc physical characteristics. According to the scheme, an arc discharge detection mode based on the AI model and an arc discharge detection mode based on the physical characteristics of the arc are effectively combined together, so that the arc discharge can be accurately identified, and the false alarm rate of the arc discharge is greatly reduced.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of electric power technology, and more specifically, to an arc detection device, a detection system, an arc detection method and a storage medium. Background Art

[0002] With the development and widespread application of photovoltaic power generation technology, the market has higher and higher requirements for the safety performance of photovoltaic power generation systems. Since photovoltaic power generation systems may produce arcing, which is easy to cause fire, photovoltaic power generation systems need to have arcing detection functions.

[0003] However, how to improve the accuracy of arc detection and reduce the false alarm rate of arc is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide an arc detection device, a detection system, an arc detection method and a storage medium. The following introduces various aspects of the embodiments of the present application.

[0005] In a first aspect, an arc detection device is provided, comprising a first detection circuit, connected to a photovoltaic power generation system, for performing arc detection on the photovoltaic power generation system; a second detection circuit, connected to the photovoltaic power generation system, for performing arc detection on the photovoltaic power generation system; and a first processing circuit, for determining whether an arc occurs in the photovoltaic power generation system based on a detection result of the first detection circuit and / or a detection result of the second detection circuit; wherein the first detection circuit performs arc detection based on an AI model, and the second detection circuit performs arc detection based on physical characteristics of the arc.

[0006] As a possible implementation manner, the first processing circuit is further used to: if the detection result of the first detection circuit and the detection result of the second detection circuit both indicate that arcing occurs in the photovoltaic power generation system, then determine that arcing occurs in the photovoltaic power generation system.

[0007] As a possible implementation method, the first processing circuit is further used to: if N consecutive detection results output by the first detection circuit all indicate that arcing occurs in the photovoltaic power generation system, then determine that arcing occurs in the photovoltaic power generation system, where N is a positive integer greater than 1.

[0008] As a possible implementation method, the first processing circuit is further used for: if during the i-th detection, the detection result of the second detection circuit indicates that arcing occurs in the photovoltaic power generation system, then determining that the detection result of the second detection circuit is that arcing occurs; if during the M consecutive detection processes after the i-th detection, the detection results of the second detection circuit all indicate that arcing does not occur in the photovoltaic power generation system, then still determining the detection result of the second detection circuit as that arcing occurs; wherein M is a positive integer greater than or equal to 1 and less than a preset threshold.

[0009] As a possible implementation manner, the arc physical characteristics include one or more of the following characteristics of the arc: arc light, arc sound, electromagnetic radiation, current, and voltage.

[0010] As a possible implementation, the first detection circuit includes: a current transformer, used to collect the AC signal output by the photovoltaic power generation system; a first sampling circuit, used to sample the AC signal to obtain a first sampling result; a second processing circuit, used to determine the detection result of the first detection circuit based on the first sampling result, and the second processing circuit and the first processing circuit may be the same or different processing circuits.

[0011] As a possible implementation, the second detection circuit includes: a current sensor, used to collect the current signal output by the photovoltaic power generation system; a second sampling circuit, used to sample the current signal to obtain a second sampling result; a third processing circuit, used to determine the detection result of the second detection circuit based on the second sampling result, and the third processing circuit and the first processing circuit may be the same or different processing circuits.

[0012] In a second aspect, a detection system is provided, comprising a photovoltaic power generation system and an arc detection device as described in the first aspect or any implementation of the first aspect.

[0013] On the third aspect, an arc detection method is proposed, which uses a first detection method to detect arcing in a photovoltaic power generation system; uses a second detection method to detect arcing in a photovoltaic power generation system; determines whether arcing occurs in the photovoltaic power generation system based on the detection result of the first detection method and / or the detection result of the second detection method; wherein the first detection method performs arc detection based on an AI model, and the second detection method performs arc detection based on the physical characteristics of the arc.

[0014] As a possible implementation method, determining whether arcing occurs in the photovoltaic power generation system based on the detection result of the first detection method and / or the detection result of the second detection method includes: if the detection result of the first detection method and the detection result of the second detection method both indicate that arcing occurs in the photovoltaic power generation system, then determining that arcing occurs in the photovoltaic power generation system.

[0015] As a possible implementation method, determining whether arcing occurs in the photovoltaic power generation system based on the detection results of the first detection method and / or the detection results of the second detection method includes: if N consecutive detection results of the first detection method all indicate that arcing occurs in the photovoltaic power generation system, then determining that arcing occurs in the photovoltaic power generation system, where N is a positive integer greater than 1.

[0016] According to a fourth aspect, a computer-readable storage medium is provided, on which an executable code is stored. When the executable code is executed, the method described in the third aspect or any implementation method of the third aspect can be implemented.

[0017] The embodiment of the present application provides an arc detection device, including: a first detection circuit, connected to a photovoltaic power generation system, for detecting arcs in the photovoltaic power generation system; a second detection circuit, connected to the photovoltaic power generation system, for detecting arcs in the photovoltaic power generation system; a first processing circuit, for determining whether an arc occurs in the photovoltaic power generation system based on the detection result of the first detection circuit and / or the detection result of the second detection circuit; wherein the first detection circuit performs arc detection based on an AI model, and the second detection circuit performs arc detection based on the physical characteristics of the arc. This solution effectively combines the arc detection method based on the AI ​​model and the arc detection method based on the physical characteristics of the arc, so that the arc can be accurately identified, greatly reducing the false alarm rate of the arc. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural schematic diagram of an arc detection device provided in one embodiment of the present application.

[0019] Figure 2 It is a schematic diagram of a detection system provided in one embodiment of the present application.

[0020] Figure 3 It is a flowchart of the judgment logic of the arc detection result provided in one embodiment of the present application.

[0021] Figure 4 It is a flowchart of the judgment logic of arc detection results provided by another embodiment of the present application.

[0022] Figure 5 It is a flow chart of an arc detection method provided in one embodiment of the present application.

[0023] Figure 6 It is a structural schematic diagram of an arc detection device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present application, the technical solutions 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 embodiments of a part of the present application, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present application should fall within the scope of protection of the present application.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention; the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance; in addition, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] At present, the research on arc pulling function is mainly divided into the following methods: (1) detection method based on arc light, arc sound, and electromagnetic radiation characteristics; (2) detection method based on arc current and voltage time-frequency domain characteristics; (3) fault detection method based on pattern recognition learning algorithm; (4) fault detection method based on machine learning.

[0028] With the rapid development of technology, more and more companies are using AI models to detect arcs. AI models are highly adaptable and accurate in detection, but they require a large amount of data under different working conditions. At the same time, the customer installation environment is complex and the experimental data collection is different, which will lead to low accuracy of arc detection results and easy to produce false alarms of arcs. According to regulatory requirements, when an arc is detected, the power must be cut off. Under this rule, false alarms of arcs will greatly affect the power generation efficiency and customer experience of photovoltaic power generation systems. For example, if no arc is generated on the photovoltaic cable (also known as PV line) side, the arc detection device reports an incorrect arc detection result, which will seriously affect the normal operation of the photovoltaic power generation system; if an arc is generated on the PV line side, the arc detection device does not report the arc, which will have great safety hazards, such as fires in the photovoltaic power generation system. If the AI ​​model is used alone for arc detection, false alarms are likely to occur, affecting power generation efficiency and customer experience.

[0029] Therefore, how to improve the accuracy of arc detection and reduce the false alarm rate of arc is a technical problem that needs to be solved urgently.

[0030] In response to the above problems, an embodiment of the present application provides an arc detection device, including: a first detection circuit, connected to a photovoltaic power generation system, for detecting arcs in the photovoltaic power generation system; a second detection circuit, connected to the photovoltaic power generation system, for detecting arcs in the photovoltaic power generation system; a first processing circuit, for determining whether an arc occurs in the photovoltaic power generation system based on the detection result of the first detection circuit and / or the detection result of the second detection circuit; wherein the first detection circuit performs arc detection based on an AI model, and the second detection circuit performs arc detection based on the physical characteristics of the arc. This solution effectively combines the arc detection method based on the AI ​​model and the arc detection method based on the physical characteristics of the arc, so that the arc can be accurately identified, greatly reducing the false alarm rate of the arc.

[0031] Figure 1 This is a schematic diagram of the structure of an arc detection device provided in an embodiment of the present application. Figure 1 As shown, the arc detection device 100 includes a first detection circuit 110, a second detection circuit 120 and a first processing circuit 130. It should be understood that the arc detection device 100 is electrically connected to the photovoltaic power generation system 200.

[0032] The first detection circuit 110 is connected to the photovoltaic power generation system 200, and the first detection circuit 110 can be used to perform arc detection on the photovoltaic power generation system 200; wherein, the first detection circuit 110 performs arc detection based on an AI model.

[0033] The second detection circuit 120 is connected to the photovoltaic power generation system 200, and the second detection circuit 120 can be used to perform arc detection on the photovoltaic power generation system 200; wherein, the second detection circuit 120 performs arc detection based on the physical characteristics of the arc.

[0034] In some implementations, the arc physical characteristics include one or more of the following characteristics of the arc: arc light, arc sound, electromagnetic radiation, current, and voltage. It should be understood that the electromagnetic radiation of the arc includes radio frequency interference (RFI) and electromagnetic interference (EMI), etc. The current of the arc refers to the actual current value passing through the arc. The voltage of the arc refers to the voltage required to maintain the arc.

[0035] The first processing circuit 130 is used to determine whether an arcing phenomenon occurs in the photovoltaic power generation system 200 according to the detection result of the first detection circuit 110 and / or the detection result of the second detection circuit 120 .

[0036] It should be noted that the first detection circuit 110, the second detection circuit 120 and the first processing circuit 130 can be integrated together to form an arc detection controller, and the arc detection controller can be a general-purpose processor or a special-purpose processor. For example, the arc detection controller can be a central processing unit (CPU). Alternatively, the arc detection controller can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0037] The foregoing describes that the first processing circuit 130 can determine whether an arcing phenomenon occurs in the photovoltaic power generation system 200 based on different arcing detection results. The following describes in detail the judgment logic of using the first processing circuit 130 to determine whether an arcing phenomenon occurs in the photovoltaic power generation system 200 in combination with specific examples.

[0038] In some implementations, if the detection results of the first detection circuit 110 and the detection results of the second detection circuit 120 both indicate that an arcing phenomenon occurs in the photovoltaic power generation system 200, the first processing circuit 130 can determine that an arcing phenomenon occurs in the photovoltaic power generation system 200. In other words, when the detection results of the first detection circuit 110 and the second detection circuit 120 both indicate that an arcing phenomenon occurs in the photovoltaic power generation system 200, it is not necessary to determine that N consecutive detection results of the first detection circuit 110 all indicate that an arcing phenomenon occurs in the photovoltaic power generation system 200, and it can be determined that an arcing phenomenon occurs in the photovoltaic power generation system 200, thereby improving the efficiency of detecting the arcing phenomenon in the photovoltaic power generation system 200.

[0039] In other implementations, if the detection results of multiple consecutive detections by the first detection circuit 110 all indicate that arcing occurs in the photovoltaic power generation system 200 , the first processing circuit 130 may also determine that arcing occurs in the photovoltaic power generation system 200 .

[0040] As an example, if N consecutive detection results output by the first detection circuit 110 all indicate that arcing occurs in the photovoltaic power generation system 200, the first processing circuit 130 can determine that arcing occurs in the photovoltaic power generation system 200, where N is a positive integer greater than 1, for example, N can be set to 20.

[0041] In some implementations, considering arc detection based on the physical characteristics of the arc, the arc phenomenon can only be detected at the moment of arc occurrence, and the arc will last for a period of time (i.e., the length of time the arc is maintained in the arc state), therefore, when the detection result of the second detection circuit 120 indicates that the photovoltaic power generation system 200 has an arc phenomenon, then during the arc maintenance time, it is determined that the detection result of the second detection circuit 120 indicates that the photovoltaic power generation system 200 has an arc phenomenon, even if the detection result of the second detection circuit 120 indicates that the photovoltaic power generation system 200 has not an arc phenomenon. In other words, if the detection result of the second detection circuit 120 at a certain time indicates that the photovoltaic power generation system 200 has an arc phenomenon, the first processing circuit 130 can determine that the detection result of the second detection circuit 120 is that the arc phenomenon has occurred. Then, the flag indicating the occurrence of arcing in the photovoltaic power generation system 200 will be maintained for a period of time (i.e., the duration of the arcing state). That is, if the second detection circuit 120 shows multiple consecutive detection results indicating that the photovoltaic power generation system 200 has not experienced an arcing phenomenon after a certain detection result indicates that the photovoltaic power generation system 200 has experienced an arcing phenomenon, the present application will still determine the multiple detection results of the second detection circuit 120 as the occurrence of an arcing phenomenon, thereby improving the accuracy of arcing detection based on the second detection circuit 120. The duration corresponding to the multiple consecutive detection results indicating that the photovoltaic power generation system 200 has not experienced an arcing phenomenon is the duration of the arcing state.

[0042] As an example, if the detection result of the second detection circuit 120 indicates that the photovoltaic power generation system 200 has an arcing phenomenon during the i-th detection, the detection result of the second detection circuit 120 is determined to be the occurrence of an arcing phenomenon; if the detection results of the second detection circuit 120 in the M consecutive detection processes after the i-th detection all indicate that the photovoltaic power generation system 200 has not an arcing phenomenon, the detection result of the second detection circuit 120 is still determined to be the occurrence of an arcing phenomenon; wherein i is a positive integer, and M is a positive integer greater than or equal to 1 and less than a preset threshold. For example, if the detection interruption of the second detection circuit 120 is 10ms, then M can be set to 400, that is, the detection result of the second detection circuit 120 detecting that the photovoltaic power generation system 200 has an arcing phenomenon will be maintained for the target duration of 4s (400*10ms).

[0043] It should be noted that if the detection result of the first detection circuit 110 indicates that the photovoltaic power generation system 200 has not experienced arcing, it can be determined that the photovoltaic power generation system 200 has not experienced arcing. If the detection result of the first detection circuit 110 indicates that the photovoltaic power generation system 200 has experienced arcing, and the detection result of the second detection circuit 120 indicates that the photovoltaic power generation system 200 has not experienced arcing, the first processing circuit 130 can determine that the photovoltaic power generation system 200 has not experienced arcing; further, the number of times the first detection circuit 110 detects and indicates that the photovoltaic power generation system 200 has experienced arcing can be further determined. If the N consecutive detection results output by the first detection circuit 110 all indicate that the photovoltaic power generation system 200 has experienced arcing, it can still be determined that the photovoltaic power generation system 200 has experienced arcing, and the machine will be shut down and the arcing will be reported.

[0044] It can be seen that the embodiment of the present application mainly uses the detection method of the first detection circuit 110 (arc detection based on the AI ​​model), and introduces the detection method of the second detection circuit 120 (arc detection based on the physical characteristics of the arc), so as to more accurately and efficiently determine whether an arcing event occurs in the photovoltaic power generation system.

[0045] In some implementations, the first detection circuit 110 includes a current transformer, a first sampling circuit, and a second processing circuit (not shown in the figure). The current transformer is used to collect the AC signal output by the photovoltaic power generation system 200; the first sampling circuit is used to sample the AC signal to obtain a first sampling result; the second processing circuit is used to determine the detection result of the first detection circuit 110 according to the first sampling result. It should be understood that the second processing circuit and the first processing circuit 130 are the same or different processing circuits. In other words, the first processing circuit 130 can be used to determine the detection result of the first detection circuit 110 according to the first sampling result.

[0046] In some implementations, the first sampling circuit may include: a low-frequency filtering circuit, a high-frequency filtering circuit, a notch filter, a voltage follower, and other circuits.

[0047] In some implementations, the photovoltaic power generation system 200 includes a photovoltaic panel, an inverter, and a photovoltaic cable (also called a PV line) disposed between the photovoltaic panel and the inverter. The above-mentioned current transformer can be disposed on the PV line, such as on the positive PV line.

[0048] In some implementations, the second detection circuit 120 includes a current sensor, a second sampling circuit, and a third processing circuit (not shown in the figure). The current sensor is used to collect the current signal output by the photovoltaic power generation system 200 (including the DC signal and AC signal output by the photovoltaic power generation system 200); the second sampling circuit is used to sample the current signal to obtain a second sampling result; the third processing circuit is used to determine the detection result of the second detection circuit 120 according to the second sampling result. It should be understood that the third processing circuit and the first processing circuit 130 are the same or different processing circuits. That is, the first processing circuit 130 can be used to determine the detection result of the second detection circuit 120 according to the second sampling result.

[0049] In some implementations, the second sampling circuit may include: a signal amplification circuit, a voltage follower circuit, and the like.

[0050] In some implementations, the current sensor may be disposed on a PV line, such as a positive PV line.

[0051] In some implementations, the current sensor may be disposed on the PV line close to one side of the photovoltaic panel, and the current transformer may be disposed on the PV line close to one side of the inverter.

[0052] It should be understood that the PV line is mainly a DC signal transmitted from the photovoltaic panel to the inverter, but there will be ripples in the DC signal, and the ripples are AC. The current transformer in this application can filter out the larger DC component and only detect the ripple AC signal, and the current transformer has a low cost. The current sensor in this application can detect both the DC signal and the AC signal on the PV line at the same time, but the current sensor has a high cost.

[0053] In some implementations, the control program in the second processing circuit may include a first interrupt for performing arc detection based on the AI ​​model, and the first interrupt is mainly used to execute the arc detection judgment of the AI ​​model. Accordingly, the current transformer can be configured to collect AC information in the first interrupt.

[0054] In some implementations, the control program in the third processing circuit may include a second interrupt for arc detection based on the arc physical characteristics, and the second interrupt is mainly used to perform arc detection judgment based on the arc physical characteristics. Accordingly, the current sensor may be configured to collect current information for the second interrupt.

[0055] In some implementations, the duration of the first interruption is greater than the duration of the second interruption. For example, the first interruption may be configured as a 100 ms interruption; for example, the second interruption may be configured as a 10 ms interruption.

[0056] It should be noted that the arc detection device in the present application can be used to perform arc detection on a distributed photovoltaic system, that is, the arc detection device can be used to perform arc detection on a distributed photovoltaic inverter.

[0057] An embodiment of the present application also provides a detection system, which includes a photovoltaic power generation system and any arc detection device as mentioned above.

[0058] The following describes the embodiments of the present application in more detail with reference to specific examples. Figures 2 to 4 It is only to help those skilled in the art understand the embodiments of the present application, rather than to limit the embodiments of the present application to the specific values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the examples given, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0059] Figure 2 A schematic diagram of a detection system provided in an embodiment of the present application. Figure 2 The detection system includes an arc detection device 100 and a photovoltaic power generation system 200.

[0060] The arc detection device 100 may include a first detection circuit 110 and a second detection circuit 120. The first detection circuit 110 includes a current transformer, a first sampling circuit and a processor. The internal circuit structure diagram of the first sampling circuit is not shown. The first sampling circuit may include a low-frequency filter circuit, a high-frequency filter circuit, a notch filter, a voltage follower and other circuits; the second detection circuit 120 includes a current sensor, a second sampling circuit and a processor. The internal circuit structure diagram of the second sampling circuit is not shown. The second sampling circuit may include a signal amplification circuit, a voltage follower and other circuits.

[0061] It should be noted that Figure 2 In the example shown, the processor may be used to process the detection results of the first sampling circuit and the second sampling circuit, and the processor may be an embedded controller, such as an STM32 controller.

[0062] The photovoltaic power generation system 200 includes a photovoltaic panel, an inverter, and a photovoltaic cable (also called a PV line) disposed between the photovoltaic panel and the inverter.

[0063] In some implementations, the current sensor may be disposed on the PV line close to one side of the photovoltaic panel, and the current transformer may be disposed on the PV line close to one side of the inverter.

[0064] exist Figure 2 In the example, the current sensor can be used to collect the current signal (including DC signal and AC signal) on the PV line, and then send the PV current signal to the processor through the second sampling circuit. The current sensor can be configured to collect current information with a 10ms interruption; the current transformer can be used to collect the AC signal of the PV line current, and then send the PV AC signal to the processor through the first sampling circuit. The current transformer can be configured to collect AC current information with a 100ms interruption.

[0065] Combine the following Figure 2 and Figure 3 The judgment logic for determining whether an arcing phenomenon occurs in the photovoltaic power generation system based on the first detection circuit is described in detail. Figure 3 The arc detection based on the first detection circuit includes steps S301 to S307.

[0066] In step S301, the collected 4096 PV current information points are sent to the AI ​​model for judgment.

[0067] In step S302, it is determined whether the AI ​​result is arcing, that is, it is determined whether the detection result of arcing detection based on the AI ​​model shows arcing. If it is arcing, jump to step S303, otherwise jump to step S307.

[0068] In step S303, if the AI ​​model determines that the result is arcing, the number of arcing times N1 is set to N1+1. The initial value of the number of arcing times N1 is equal to 0.

[0069] In step S304, it is determined whether the detection result of the arc physical characteristics is arcing, that is, it is determined whether the detection result of arcing detection based on the arc physical characteristics has an arcing phenomenon. If it is arcing, jump to step S306, otherwise jump to step S305.

[0070] In step S305, if the detection result of the arc physical characteristics is that no arcing occurs, it is determined whether the number of arcing times N1 is greater than 20. If N1 is greater than 20, jump to step S306, otherwise jump to step S307.

[0071] In step S306, it is determined that arcing occurs in the photovoltaic power generation system 200, the machine is shut down and the arcing is reported.

[0072] In step S307, the current arc detection is ended.

[0073] according to Figure 3 It can be seen from the example that if the arc detection based on the AI ​​model is an arc, and the arc detection based on the physical characteristics of the arc is also an arc, it is determined that an arc occurs in the photovoltaic power generation system 200, the machine stops and reports the arc.

[0074] If the arc detection based on the AI ​​model is an arc, and the arc detection result based on the physical characteristics of the arc indicates that no arc has occurred, the number of arcs N1 can be further determined. If N1 is greater than 20 times, it can still be determined that the photovoltaic power generation system 200 has an arc, and the machine is shut down and reports the arc. If N1 is less than 20 times, the current detection ends and the next detection continues.

[0075] If the arc detection result based on the AI ​​model indicates that no arc has occurred, the current detection ends and the next detection continues.

[0076] By combining AI model arc detection with arc detection based on the physical characteristics of arc, it is possible to more accurately determine whether an arcing event has occurred in a photovoltaic power generation system.

[0077] Combine the following Figure 2 and Figure 4 The judgment logic for determining whether an arcing phenomenon occurs in the photovoltaic power generation system based on the second detection circuit is described in detail. Figure 4 Taking the current characteristics of the arc as an example, arc detection based on the second detection circuit includes steps S401 to S407.

[0078] In step S401 , the average value of the PV current (ie, the current on the PV line detected by the current sensor) within the 10 ms interruption is calculated and defined as I1.

[0079] In step S402, the difference between the PV current average value I2 in the last 10ms interruption and the PV current average value I1 in the current 10ms interruption is calculated, and the difference △I= I2- I1.

[0080] In step S403, according to the average value I1 of the PV current within the current 10ms interruption, a table is looked up to obtain a threshold current I. The threshold current table is a table obtained based on experiments, and different PV currents correspond to different threshold currents.

[0081] In step S404, it is determined whether ΔI is greater than a threshold current I. If ΔI is greater than the threshold current I, the process goes to step S405; otherwise, the process goes to step S407.

[0082] In step S405, the arc current characteristic flag Flag2 is set to 1, and the target number of times N3 that △I is continuously less than the threshold current I is set to 400. This is equivalent to maintaining the arc current characteristic flag Flag2 for a period of time: 400*10ms=4s. In step S406, I2 is set equal to I1, and the current judgment procedure ends.

[0083] In step S407, when △I is less than the threshold current I, determine whether Flag2 is 1. If so, reduce N3 by one, that is, N3=N3-1; then determine whether N3 is 1. If N3 is equal to 1, set Flag2 to 0 and jump to step S406 to end the program; if N3 is not equal to 1, set I2 to I1 and end the program.

[0084] According to the above content, it can be seen that the embodiment of the present application is mainly based on AI model arc detection, and by introducing arc detection based on the physical characteristics of the arc, it can more accurately determine whether an arc event has occurred in the photovoltaic power generation system. The main judgment logic is: if the AI ​​model judges that the arc is pulled 20 times, it is forcibly determined that an arc event has occurred in the photovoltaic power generation system, the photovoltaic power generation system machine is shut down, and the arc event is reported; when the AI ​​model judges that the arc is pulled less than 20 times, it must be determined that an arc has occurred based on the arc detection judgment condition based on the physical characteristics of the arc. At this time, the machine determines that an arc event has occurred in the photovoltaic power generation system, the photovoltaic power generation system machine is shut down, and the arc event is reported. This greatly reduces the situation of false alarms of arcing, while accurately identifying arcing.

[0085] Combination of the above Figures 1 to 4 The method embodiment of the present application is described in detail. Figure 5 The method embodiment of the present application is described in detail. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so the parts not described in detail can refer to the previous device embodiment.

[0086] Figure 5 This is a flow chart of an arc detection method provided in one embodiment of the present application. Figure 5 The arc detection method includes steps S510 to S530.

[0087] In step S510, arc detection is performed on the photovoltaic power generation system using a first detection method.

[0088] In step S520, arc detection is performed on the photovoltaic power generation system using a second detection method.

[0089] In step S530, it is determined whether arcing occurs in the photovoltaic power generation system according to the detection result of the first detection method and / or the detection result of the second detection method; wherein the first detection method performs arcing detection based on an AI model, and the second detection method performs arcing detection based on the physical characteristics of the arc.

[0090] Optionally, determining whether arcing occurs in the photovoltaic power generation system based on the detection result of the first detection method and / or the detection result of the second detection method includes: if the detection result of the first detection method and the detection result of the second detection method both indicate that arcing occurs in the photovoltaic power generation system, then determining that arcing occurs in the photovoltaic power generation system.

[0091] Optionally, determining whether arcing occurs in the photovoltaic power generation system based on the detection result of the first detection method and / or the detection result of the second detection method includes: if N consecutive detection results of the first detection method all indicate that arcing occurs in the photovoltaic power generation system, then determining that arcing occurs in the photovoltaic power generation system, where N is a positive integer greater than 1.

[0092] Combine the following Figure 6 The present invention introduces an arc detection device 600 in an embodiment of the present application. The arc detection device 600 can be used to implement the method described in the above method embodiment.

[0093] The arc detection device 600 may include one or more processors 610. The processor 610 may support the arc detection device 600 to implement the method described in the above method embodiment.

[0094] The processor 610 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0095] The arc detection device 600 may further include one or more memories 620. The memory 620 stores a program that can be executed by the processor 610 to control the arc detection device 600 to execute the method described in the above method embodiment. The memory 620 may be independent of the processor 610 or integrated in the processor 610.

[0096] The arc detection device 600 may further include a transceiver 630. The processor 610 may communicate with other devices through the transceiver 630. For example, the processor 610 may transmit and receive data with other devices through the transceiver 630.

[0097] The present application also provides a chip in an embodiment, including a processor, which can be used to call and run a computer program from a memory, so that an arc detection device equipped with the chip performs the method described in the above method embodiment. It is understood that the processor can be any type of processor mentioned above. It is understood that the memory can be independent of the chip or integrated in the chip.

[0098] The embodiment of the present application also provides a machine-readable storage medium for storing a program, and the program enables a computer to execute the method in each embodiment of the present application.

[0099] The embodiment of the present application also provides a computer program product. The computer program product includes a program. The program enables a computer to execute the method in each embodiment of the present application.

[0100] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a machine-readable storage medium, or transmitted from one machine-readable storage medium to another machine-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The machine-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0101] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments of the present disclosure can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present disclosure.

[0102] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0105] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An arc detection device, characterized in that: include: A first detection circuit is connected to the photovoltaic power generation system and is used to perform arc detection on the photovoltaic power generation system; A second detection circuit is connected to the photovoltaic power generation system and is used to perform arc detection on the photovoltaic power generation system; a first processing circuit, used for determining whether an arcing phenomenon occurs in the photovoltaic power generation system according to a detection result of the first detection circuit and / or a detection result of the second detection circuit; Among them, the first detection circuit performs arc detection based on the AI ​​model, and the second detection circuit performs arc detection based on the physical characteristics of the arc.

2. The arc detection device according to claim 1, characterized in that: The first processing circuit is further configured to: If the detection result of the first detection circuit and the detection result of the second detection circuit both indicate that arcing occurs in the photovoltaic power generation system, it is determined that arcing occurs in the photovoltaic power generation system.

3. The arc detection device according to claim 1, characterized in that: The first processing circuit is further configured to: If N consecutive detection results output by the first detection circuit all indicate that arcing occurs in the photovoltaic power generation system, it is determined that arcing occurs in the photovoltaic power generation system, where N is a positive integer greater than 1.

4. The arc detection device according to claim 1, characterized in that: The first processing circuit is further configured to: If, during the i-th detection, the detection result of the second detection circuit indicates that an arcing phenomenon occurs in the photovoltaic power generation system, then determining that the detection result of the second detection circuit is that an arcing phenomenon occurs; If, in the M consecutive detection processes after the i-th detection, the detection results of the second detection circuit all indicate that no arcing phenomenon occurs in the photovoltaic power generation system, the detection result of the second detection circuit is still determined as the occurrence of arcing phenomenon; Wherein, M is a positive integer greater than or equal to 1 and less than a preset threshold.

5. The arc detection device according to any one of claims 1 to 4, characterized in that: The arc physical characteristics include one or more of the following characteristics of the arc: arc light, arc sound, electromagnetic radiation, current, and voltage.

6. The arc detection device according to claim 1, characterized in that: The first detection circuit comprises: A current transformer, used for collecting the AC signal output by the photovoltaic power generation system; A first sampling circuit, used for sampling the AC signal to obtain a first sampling result; The second processing circuit is used to determine the detection result of the first detection circuit according to the first sampling result. The second processing circuit and the first processing circuit are the same or different processing circuits.

7. The arc detection device according to claim 1, characterized in that: The second detection circuit comprises: A current sensor, used to collect the current signal output by the photovoltaic power generation system; A second sampling circuit is used to sample the current signal to obtain a second sampling result; The third processing circuit is used to determine the detection result of the second detection circuit according to the second sampling result. The third processing circuit and the first processing circuit are the same or different processing circuits.

8. A detection system, characterized in that: It comprises a photovoltaic power generation system and an arc detection device as claimed in any one of claims 1 to 7.

9. An arc detection method, characterized in that: include: Performing arc detection on the photovoltaic power generation system using the first detection method; Performing arc detection on the photovoltaic power generation system using the second detection method; Determining whether arcing occurs in the photovoltaic power generation system according to the detection result of the first detection method and / or the detection result of the second detection method; Among them, the first detection method performs arc detection based on the AI ​​model, and the second detection method performs arc detection based on the physical characteristics of the arc.

10. The method according to claim 9, characterized in that The determining whether arcing occurs in the photovoltaic power generation system according to the detection result of the first detection method and / or the detection result of the second detection method includes: If the detection result of the first detection method and the detection result of the second detection method both indicate that arcing occurs in the photovoltaic power generation system, it is determined that arcing occurs in the photovoltaic power generation system.

11. The method according to claim 9, characterized in that The determining whether arcing occurs in the photovoltaic power generation system according to the detection result of the first detection method and / or the detection result of the second detection method includes: If N consecutive detection results of the first detection method all indicate that arcing occurs in the photovoltaic power generation system, it is determined that arcing occurs in the photovoltaic power generation system, where N is a positive integer greater than 1.

12. A machine-readable storage medium, characterized in that: A program code is stored thereon, and the program code is used to execute the method according to any one of claims 9 to 11.

Images