Arcing detection method and device, equipment and storage medium

Abstract

The invention discloses an arc discharge detection method and device, equipment and a storage medium, and belongs to the technical field of circuit detection. The method comprises the following steps: acquiring a direct-current component signal of a current signal of a to-be-detected circuit; determining a target current characteristic of the direct-current component signal; determining a target arc discharge judgment model corresponding to the target current feature; acquiring an AC component signal of the current signal; and determining whether arc discharge exists in the circuit to be detected based on the target arc discharge determination model and the AC component signal. According to the invention, arc discharge detection of the circuit can be realized.

Description

Technical Field

[0001] This application relates to the field of circuit testing technology, and in particular to a method, apparatus, device and storage medium for detecting arcing. Background Technology

[0002] With the development of photovoltaic technology, photovoltaic power stations are now widely installed in residential areas, industrial parks, and other locations. Photovoltaic power systems operate at high voltages and have numerous circuit connection points. If a connection point experiences poor contact, arcing can occur. Because photovoltaic power systems operate on direct current without a zero-crossing point, once an arc forms, it is difficult to extinguish on its own and can ignite electrical equipment, causing a fire.

[0003] Therefore, there is an urgent need for a method to detect arcing in circuits, so as to detect arcing early and cut off faulty circuits in time. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for detecting arcing in circuits. The technical solution is as follows:

[0005] Firstly, a method for detecting arcing is provided, the method comprising:

[0006] Acquire the DC component signal of the current signal of the circuit under test;

[0007] Determine the target current characteristics of the DC component signal;

[0008] Determine the target arcing determination model corresponding to the target current characteristics;

[0009] Obtain the AC component signal of the current signal;

[0010] Based on the target arcing determination model and the AC component signal, it is determined whether the circuit to be detected is arcing.

[0011] In one possible implementation, the target current characteristic is the target current magnitude.

[0012] In one possible implementation, the target arc determination model is a clustering model.

[0013] In one possible implementation, the target arcing determination model includes target arcing characteristic data and target normal current characteristic data. The step of determining whether arcing exists in the circuit to be detected based on the target arcing determination model and the AC component signal includes:

[0014] Calculate the first similarity between the AC component signal and the target arcing feature data;

[0015] Calculate the second similarity between the AC component signal and the target normal current characteristic data;

[0016] If the first similarity is greater than the second similarity, then it is determined that the circuit to be detected has arcing.

[0017] If the first similarity is less than the second similarity, then it is determined that the circuit to be detected does not have arcing.

[0018] In one possible implementation, the target arc determination model is a neural network model.

[0019] In one possible implementation, determining whether arcing exists in the circuit to be detected based on the target arcing determination model and the AC component signal includes:

[0020] The AC component signal is input into the target arcing determination model, and the target arcing determination model outputs the arcing existence confidence level.

[0021] If the confidence level of the arcing reaches the first threshold, then it is determined that the circuit under test has arcing.

[0022] If the confidence level of the arcing does not reach the first threshold, then it is determined that the circuit to be tested does not have arcing.

[0023] Secondly, an arc detection device is provided, the device comprising:

[0024] The acquisition module is used to acquire the DC component signal of the current signal of the circuit under test;

[0025] The classification module is used to determine the target current characteristics of the DC component signal and to determine the target arcing determination model corresponding to the target current characteristics.

[0026] The acquisition module is further configured to acquire the AC component signal of the current signal;

[0027] The determination module is used to determine whether arcing exists in the circuit to be detected based on the target arcing determination model and the AC component signal.

[0028] In one possible implementation, the target current characteristic is the target current magnitude.

[0029] In one possible implementation, the target arc determination model is a clustering model.

[0030] In one possible implementation, the target arcing determination model includes target arcing characteristic data and target normal current characteristic data, and the determination module is used for:

[0031] Calculate the first similarity between the AC component signal and the target arcing feature data;

[0032] Calculate the second similarity between the AC component signal and the target normal current characteristic data;

[0033] If the first similarity is greater than the second similarity, then it is determined that the circuit to be detected has arcing.

[0034] If the first similarity is less than the second similarity, then it is determined that the circuit to be detected does not have arcing.

[0035] In one possible implementation, the target arc determination model is a neural network model.

[0036] In one possible implementation, the determination module is configured to:

[0037] The AC component signal is input into the target arcing determination model, and the target arcing determination model outputs the arcing existence confidence level.

[0038] If the confidence level of the arcing reaches the first threshold, then it is determined that the circuit under test has arcing.

[0039] If the confidence level of the arcing does not reach the first threshold, then it is determined that the circuit to be tested does not have arcing.

[0040] Thirdly, an electronic device is provided, the electronic device including a processor and a memory, the memory storing at least one instruction, the instruction being loaded and executed by the processor to perform the operation performed by the arc detection method as described in the first aspect and its possible implementations above.

[0041] Fourthly, a computer-readable storage medium is provided, the storage medium storing at least one instruction, the instruction being loaded and executed by a processor to perform the operations performed by the arc detection method as described in the first aspect and its possible implementations above.

[0042] Fifthly, a computer program product is provided, the computer program product comprising at least one instruction loaded and executed by a processor to perform the operations performed by the arc detection method as described in the first aspect and its possible implementations above.

[0043] The beneficial effects of the technical solution provided in this application are:

[0044] In the technical solution provided in this application, the corresponding target arcing determination model is first selected based on the current characteristics of the DC component signal of the current signal in the circuit to be tested. Since the DC component signal of the current signal in the circuit will have obvious characteristics when arcing occurs, in this solution, by combining the selected target arcing determination model and the AC component signal of the current signal in the circuit to be tested, it is possible to effectively determine whether arcing exists in the circuit to be tested. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of a sampling circuit provided in an embodiment of this application;

[0047] Figure 2 This is a flowchart of a method for detecting arcing provided in an embodiment of this application;

[0048] Figure 3 This is a flowchart of a method for detecting arcing provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram of the structure of an arc detection device provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0051] To facilitate understanding of the embodiments of this application, some terms involved in the embodiments of this application will be explained below.

[0052] I. Arc

[0053] Arcing is a phenomenon that generates high temperature and high energy through electric arc discharge. Its principle involves applying a sufficient voltage between two electrodes, causing electrons to accelerate under the influence of the electric field. When the electrons reach sufficiently high speeds, they collide with atoms or molecules, causing them to lose electrons and form ions. These ions continue to accelerate under the influence of the electric field, eventually forming an electric arc.

[0054] II. Hall Current Sensor

[0055] Hall current sensors are based on the magnetic balance Hall principle. According to the Hall effect principle, when a current is passed through the control current terminal of the Hall element and a magnetic field is applied in the normal direction of the plane of the Hall element, an electric potential will be generated in the direction perpendicular to the current and the magnetic field. This potential is called the Hall potential and its magnitude is proportional to the control current.

[0056] In this embodiment of the application, the Hall current sensor can be installed on the cable of the circuit to be tested to sample the current signal in the circuit.

[0057] III. Low-pass filter

[0058] A low-pass filter is an electronic filter that allows signals below the cutoff frequency to pass through, but blocks signals above the cutoff frequency. In this embodiment, the low-pass filter is used to obtain the DC component signal in a current signal.

[0059] IV. High-pass filter

[0060] A high-pass filter is an electronic filter that allows signals above the cutoff frequency to pass through, but blocks signals below the cutoff frequency. In this embodiment, the high-pass filter is used to obtain the high-frequency AC component signal in a current signal.

[0061] The arc detection method provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0062] The arcing detection method provided in this application can detect DC arcing and can be applied to various power generation systems such as photovoltaic power generation systems, wind power generation systems, and hydropower generation systems. In the power supply circuit of the power generation system, the voltage is high and there are many circuit connection points. If a connection point has poor contact, arcing will occur. Since DC power is transmitted, and DC power does not have a zero crossing point, once arcing is formed, it is difficult to extinguish itself and may ignite electrical equipment, causing a fire.

[0063] The technical solution provided in this application involves using a sampling circuit to acquire the DC component signal and the AC component signal of the current signal in the circuit. Then, based on the target current characteristics of the DC component signal, corresponding target arcing determination reference data is selected. Furthermore, based on the target arcing determination reference data and the AC component signal, it is determined whether arcing exists in the circuit.

[0064] In the technical solutions provided in this application, there can be various sampling circuits for sampling AC component signals and DC component signals. One such sampling circuit is described below:

[0065] See Figure 1The sampling circuit may include a current sensor, a low-pass filter, and a high-pass filter. The current sensor, which can be a Hall effect current sensor, is placed on the circuit to be tested and collects the current signal. The low-pass filter filters the current signal to obtain the lower-frequency DC component. The high-pass filter filters the current signal to obtain the higher-frequency AC component. The cutoff frequency of the low-pass filter is higher than that of the high-pass filter, so the high-pass filter can output the AC component signal with a frequency between the cutoff frequencies of the low-pass and high-pass filters.

[0066] In one possible implementation, the sampling circuit may also include a signal scaling device, which is used to reduce or amplify the AC component signal. Whether to reduce or amplify it depends on the signal amplitude that the device that ultimately analyzes and processes the AC component signal can handle.

[0067] For example, for AC component signals, if the amplitude of the AC component signal output by the high-pass filter is greater than the signal amplitude that the signal analysis and processing equipment can process, a signal amplification device can be set after the high-pass filter. If the amplitude of the AC component signal output by the high-pass filter is less than the signal amplitude that the signal analysis and processing equipment can process, a signal amplification device can be set after the high-pass filter.

[0068] In one possible implementation, the signal analysis and processing device described above can be an electronic device including a processor or a standalone processor. The processor can include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor can be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor can also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor can integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor can also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0069] The arc detection method provided in the embodiments of this application is described below. This method can be implemented using the signal analysis and processing equipment described above. See [link to relevant documentation]. Figure 2 The method may include the following steps:

[0070] Step 201: Obtain the DC component signal of the current signal of the circuit under test.

[0071] In practice, the current sensor in the sampling circuit acquires the current signal from the circuit under test. This current signal is then input to a low-pass filter, which filters out ultra-high frequency AC signals and outputs a DC component signal. This DC component signal is then input to a signal analysis and processing device.

[0072] Step 202: Obtain the AC component signal of the current signal of the circuit under test.

[0073] In implementation, the current sensor in the sampling circuit acquires the current signal from the circuit under test. This current signal is then input to a low-pass filter, which filters out ultra-high frequency AC signals and outputs a DC component signal. Since the low-pass filter only filters out ultra-high frequency interference signals, the DC component signal still contains high-frequency AC components. Therefore, the DC component signal can be input to a high-pass filter, which filters out low-frequency DC signals and outputs a high-frequency AC component signal. This AC component signal is then input to a signal scaling device, which scales the signal. The scaled AC component signal is then input to a signal analysis and processing device.

[0074] Step 203: Determine the target current characteristics of the DC component signal.

[0075] In implementation, the signal analysis and processing equipment can periodically detect both the AC and DC component signals. Specifically, an arc detection cycle can be preset. At the end of each arc detection cycle, the signal analysis and processing equipment can determine the target current characteristics of the DC component signal received during that arc detection cycle, where the target current characteristic can be the current magnitude. For example, the current magnitude of the DC component signal is determined to be 3A (Amperes).

[0076] Step 204: Determine the target arcing judgment model corresponding to the target current characteristics.

[0077] In implementation, the current magnitude can be pre-classified. For example, currents greater than 0A and less than 1A are classified as the first type of current characteristic; currents greater than or equal to 1A and less than 2A are classified as the second type of current characteristic; currents greater than or equal to 3A and less than 4A are classified as the third type of current characteristic, and so on. For each type of current characteristic, a corresponding arcing determination model can be set.

[0078] After determining the magnitude of the DC component signal current, the Nth type of current characteristic to which the DC component signal current magnitude belongs is determined. Then, among the pre-selected stored current characteristics and arcing determination models, the target arcing determination model corresponding to the Nth type of current characteristic is determined.

[0079] For example, such as Figure 3 As shown, firstly, the current magnitude of the DC component signal is determined to be 3A, which belongs to the third type of current characteristic. Then, the target arcing judgment model corresponding to this third type of current characteristic is determined.

[0080] Step 205: Based on the target arcing determination model and the AC component signal, determine whether arcing exists in the circuit.

[0081] In implementation, such as Figure 3As shown, after determining the target arcing determination model corresponding to the third type of current characteristics, the presence of arcing in the circuit can be determined based on the target arcing determination model corresponding to the third type of current characteristics and the AC component signal.

[0082] There are multiple cases for the arc determination model. The following will explain step 205 for each different case.

[0083] Scenario 1:

[0084] The arcing determination model is a clustering model that includes arcing determination reference data. This reference data includes arcing feature data and normal current feature data. For example, the arcing feature data included in the arcing determination model corresponding to the second type of current feature is the AC component signal of the current signal collected when arcing exists in the circuit and the DC component of the current signal is greater than or equal to 1A and less than 2A. The normal current data included in the arcing determination model corresponding to the second type of current feature is the AC component signal of the current signal collected when arcing does not exist in the circuit and the DC component of the current signal is greater than or equal to 1A and less than 2A.

[0085] After determining the target arcing detection model, the model is invoked to execute a clustering algorithm. The AC component signals received during the arcing detection period are clustered into either the target arcing feature data or the target normal current feature data included in the target arcing detection model. If the AC component signals received during the arcing detection period are clustered into the target arcing feature data, then an arcing is determined to exist in the circuit under test. If the AC component signals received during the arcing detection period are clustered into the target normal current feature data, then an arcing is determined to not exist in the circuit under test.

[0086] In one possible implementation, the execution logic of the clustering algorithm can be as follows:

[0087] Calculate the first similarity between the AC component signal received during the arc detection period and the target arc feature data included in the target arc determination reference data, and calculate the second similarity between the AC component signal received during the arc detection period and the target normal current feature data included in the target arc determination reference data. If the first similarity is greater than the second similarity, the AC component signal is clustered into the target arc feature data, determining that arcing exists in the circuit. Conversely, if the first similarity is less than the second similarity, the AC component signal is clustered into the target normal current feature data, determining that arcing does not exist in the circuit under test.

[0088] In this way, each type of current characteristic corresponds to its own arc-breaking judgment reference data. Compared with directly clustering using all the arc-breaking judgment reference data, this scheme uses its own arc-breaking judgment reference data for clustering of each type of current characteristic. This results in a smaller data volume for the clustering algorithm, higher efficiency, and lower computational performance requirements. Experiments have shown that traditional schemes using all the arc-breaking judgment reference data for direct clustering require hundreds of milliseconds (ms) to obtain arc-breaking judgment results, typically between 200 and 300 ms. In contrast, this scheme only requires tens of ms to obtain arc-breaking judgment results, typically between 80 and 90 ms.

[0089] Scenario 2:

[0090] The arcing determination model is a neural network model. For example, the arcing determination model corresponding to the second type of current feature can be trained using samples obtained when arcing exists in the circuit, the magnitude of the DC component of the current signal is greater than or equal to 1A and less than 2A, and the magnitude of the DC component of the current signal is greater than or equal to 1A and less than 2A, respectively.

[0091] After determining the target arc detection model, the AC component signal received during the arc detection period can be input into the target arc detection model, and the target arc detection model will output the judgment result.

[0092] The judgment result can take many forms. Two of them are illustrated below:

[0093] Format 1:

[0094] The determination result indicates a certain level of confidence in the presence of arcing. After obtaining the determination result, it is checked whether the confidence level of arcing presence reaches a first threshold. If the confidence level of arcing presence reaches the first threshold, the circuit under test is determined to meet the arcing presence condition. If the confidence level of arcing presence does not reach the first threshold, the circuit under test is determined not to meet the arcing presence condition. The first threshold can be configured by relevant personnel according to actual needs.

[0095] Form Two:

[0096] The determination result is either 0 or 1. If the determination result is 1, the circuit under test is determined to meet the arcing condition. If the determination result is 0, the circuit under test is determined not to meet the arcing condition.

[0097] It is worth noting that which 1 and 0 represents, indicating whether the circuit under test meets the conditions for arcing, and which represents whether the circuit under test does not meet the conditions for arcing, can be configured according to the actual situation. This application does not limit this.

[0098] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0099] In the technical solution provided in this application, the corresponding target arcing determination model is first selected based on the current characteristics of the DC component signal of the current signal in the circuit to be tested. Since the DC component signal of the current signal in the circuit will have obvious characteristics when arcing occurs, in this solution, by combining the selected target arcing determination model and the AC component signal of the current signal in the circuit to be tested, it is possible to effectively determine whether arcing exists in the circuit to be tested.

[0100] This application also provides an arc detection device, which can be an electronic device, such as... Figure 4 As shown, the device may include an acquisition module 410, a classification module 420, and a determination module 430, wherein:

[0101] The acquisition module 410 is used to acquire the DC component signal of the current signal of the circuit under test;

[0102] The classification module 420 is used to determine the target current characteristics of the DC component signal and to determine the target arcing determination model corresponding to the target current characteristics.

[0103] The acquisition module 410 is also used to acquire the AC component signal of the current signal;

[0104] The determination module 430 is used to determine whether arcing exists in the circuit to be detected based on the target arcing determination model and the AC component signal.

[0105] In one possible implementation, the target current characteristic is the target current magnitude.

[0106] In one possible implementation, the target arc determination model is a clustering model.

[0107] In one possible implementation, the target arcing determination model includes target arcing characteristic data and target normal current characteristic data, and the determination module 430 is used for:

[0108] Calculate the first similarity between the AC component signal and the target arcing feature data;

[0109] Calculate the second similarity between the AC component signal and the target normal current characteristic data;

[0110] If the first similarity is greater than the second similarity, then it is determined that the circuit to be detected has arcing.

[0111] If the first similarity is less than the second similarity, then it is determined that the circuit to be detected does not have arcing.

[0112] In one possible implementation, the target arc determination model is a neural network model.

[0113] In one possible implementation, the determination module 430 is configured to:

[0114] The AC component signal is input into the target arcing determination model, and the target arcing determination model outputs the arcing existence confidence level.

[0115] If the confidence level of the arcing reaches the first threshold, then it is determined that the circuit under test has arcing.

[0116] If the confidence level of the arcing does not reach the first threshold, then it is determined that the circuit to be tested does not have arcing.

[0117] In the technical solution provided in this application, the corresponding target arcing determination model is first selected based on the current characteristics of the DC component signal of the current signal in the circuit to be tested. Since the DC component signal of the current signal in the circuit will have obvious characteristics when arcing occurs, in this solution, by combining the selected target arcing determination model and the AC component signal of the current signal in the circuit to be tested, it is possible to effectively determine whether arcing exists in the circuit to be tested.

[0118] It should be noted that the arc detection device provided in the above embodiments is only illustrated by the division of the functional modules described above. In practical applications, the functions can be assigned to different functional modules as needed, that is, the internal structure of the electronic device can be divided into different functional modules to complete all or part of the functions described above. In addition, the arc detection device and the arc detection method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0119] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 1000 can vary significantly due to differences in configuration or performance. It may include one or more central processing units (CPUs) 1001 and one or more memories 1002. The memories 1002 store at least one instruction, which is loaded and executed by the processors 1001 to implement the arc detection method provided in the various method embodiments described above. Of course, the computing device may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The electronic device may also include other components for implementing device functions, which will not be elaborated upon here.

[0120] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 500, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0121] In an exemplary embodiment, a computer program product is also provided, the computer program product including at least one instruction, which is loaded and executed by a processor to implement the arc detection method as provided in the various method embodiments described above.

[0122] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a processor in a terminal to complete the arc detection method in the above embodiments. This computer-readable storage medium can be non-transitory. For example, the computer-readable storage medium can be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage devices, etc.

[0123] It should be noted that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this application, a first threshold can also be referred to as a second threshold, and similarly, a second threshold can also be referred to as a first threshold.

[0124] Furthermore, it should be noted that all information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals (including but not limited to signals transmitted between the user terminal and other devices) involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the current signals, DC component signals, and AC component signals involved in this application were all obtained under full authorization.

[0125] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0126] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of detecting a drawn arc, characterized by, The method comprises: obtaining a direct current component signal of a current signal of a circuit to be detected; determining a target current feature of the direct current component signal; determining a target arc judgment model corresponding to the target current feature; obtaining an alternating current component signal of the current signal; based on the target arc judgment model and the alternating current component signal, determining whether the circuit to be detected has an arc.

2. The method of claim 1, wherein, The target current feature is a target current size.

3. The method of claim 1, wherein, The target arc judgment model is a clustering model.

4. The method of claim 3, wherein, The target arc judgment model includes target arc feature data and target normal current feature data, and based on the target arc judgment model and the alternating current component signal, determining whether the circuit to be detected has an arc comprises: calculating a first similarity between the alternating current component signal and the target arc feature data; calculating a second similarity between the alternating current component signal and the target normal current feature data; if the first similarity is greater than the second similarity, determining that the circuit to be detected has an arc; if the first similarity is less than the second similarity, determining that the circuit to be detected does not have an arc.

5. The method of claim 1, wherein, The target arc judgment model is a neural network model.

6. The method of claim 5, wherein, Based on the target arc judgment model and the alternating current component signal, determining whether the circuit to be detected has an arc comprises: inputting the alternating current component signal into the target arc judgment model, and the target arc judgment model outputs an arc existence confidence; if the arc existence confidence reaches a first threshold, determining that the circuit to be detected has an arc; if the arc existence confidence does not reach the first threshold, determining that the circuit to be detected does not have an arc.

7. An apparatus for detecting a drawn arc, characterized in that The device comprises: an acquisition module for obtaining a direct current component signal of a current signal of a circuit to be detected; a classification module for determining a target current feature of the direct current component signal and determining a target arc judgment model corresponding to the target current feature; the acquisition module is further configured to obtain an alternating current component signal of the current signal; a judgment module for determining, based on the target arc judgment model and the alternating current component signal, whether the circuit to be detected has an arc.

8. The apparatus of claim 7, wherein, The target current feature is a target current size.

9. The apparatus of claim 7, wherein, The target arc judgment model is a clustering model.

10. An electronic device, comprising: The electronic device comprises a processor and a memory, and the memory stores at least one instruction, which is loaded and executed by the processor to implement the operations performed by the arc detection method of any one of claims 1 to 6.

11. A computer readable storage medium, characterized in that, The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the operations performed by the arc detection method of any one of claims 1 to 6.

Images