Electric arc detection method and device and computer readable storage medium

Abstract

The invention relates to an arc detection method and device and a computer readable storage medium, and the method comprises the steps: carrying out the load recognition of a circuit, and determining the type of a load in the circuit; arc characteristic parameters of each load type are determined based on the load types, and the arc characteristic parameters represent that the change amplitude influenced by the arc is larger than a preset threshold value; determining an arc characteristic value of the arc characteristic parameter according to the arc characteristic parameter; the load types and the electric arc characteristic values serve as input data, an electric arc detection result is obtained through a preset electric arc detection model, if an electric arc exists on a branch where any load type is located, the electric arc detection result is that the electric arc exists in the circuit, and the preset electric arc detection model comprises the threshold range of electric arc characteristic parameters of different load type combinations. According to the invention, the accuracy of arc detection is improved.

Description

Technical Field

[0001] The present application relates to the field of electrical safety, and in particular to an arc detection method, device, and computer-readable storage medium. Background Art

[0002] If an arc fault occurs in a circuit, it may cause serious accidents such as damage to electrical equipment and fire. To avoid accidents, arc detection is required.

[0003] In complex electrical environments, numerous interference signals unrelated to arcs exist. These interference signals can overwhelm the effective arc signatures, reducing arc detection accuracy. Furthermore, related technologies typically capture all arc fault signatures to achieve arc detection. However, the need to calculate numerous arc signatures makes accurate arc detection difficult. Therefore, improving arc detection accuracy has become a pressing issue. Summary of the Invention

[0004] Embodiments of the present application provide an arc detection method, apparatus, and computer-readable storage medium to at least address the problem of low arc detection accuracy in related technologies.

[0005] In a first aspect, an embodiment of the present application provides an arc detection method, characterized by comprising:

[0006] Identify the load of the circuit and determine the type of load in the circuit;

[0007] Determining arc characteristic parameters for each load type based on the load type, wherein the arc characteristic parameters represent that the amplitude of the change affected by the arc is greater than a preset threshold;

[0008] determining an arc characteristic value of the arc characteristic parameter according to the arc characteristic parameter;

[0009] Using the load type and arc characteristic value as input data, the arc detection result is obtained through a preset arc detection model. If there is an arc on the branch where any load type is located, the arc detection result is that there is an arc in the circuit. The preset arc detection model includes the threshold range of the arc characteristic parameters for different load type combinations.

[0010] In one embodiment, determining an arc characteristic value of the arc characteristic parameter according to the arc characteristic parameter includes:

[0011] Obtain the total current waveform in the circuit within a preset time period;

[0012] Based on the total current waveform, an arc characteristic value of each arc characteristic parameter is determined.

[0013] In one embodiment, after determining the arc characteristic parameters of each load type, it further includes:

[0014] Based on all load types, screen the arc characteristic parameters to determine a set of arc characteristic parameters.

[0015] In one embodiment, screening the arc characteristic parameters to determine a set of arc characteristic parameters includes:

[0016] Obtain the arc characteristic parameters of all load types;

[0017] If the arc characteristic parameters of each load type are all different, then use all the arc characteristic parameters as the set of arc characteristic parameters;

[0018] If there are the same arc characteristic parameters among the arc characteristic parameters of the load types, retain the different arc characteristic parameters and one kind of the same arc characteristic parameter, and use the retained arc characteristic parameters as the set of arc characteristic parameters.

[0019] In one embodiment, performing load identification on a circuit to determine the load types in the circuit includes:

[0020] Obtain the total current and total voltage in the circuit;

[0021] Based on the total current and total voltage, perform load identification on the circuit to determine the load types in the circuit.

[0022] In one embodiment, a preset arc detection model includes: a data module and a training module,

[0023] The data module is used to obtain the training data of each load type in a preset training database according to the load type;

[0024] The training module is used to train the training data based on a preset training algorithm until a preset convergence condition is met.

[0025] In a second aspect, an embodiment of the present application provides an arc detection device, which is characterized by including:

[0026] A load identification module, configured to perform load identification on a circuit to determine the load types in the circuit;

[0027] An arc characteristic parameter determination module, configured to determine the arc characteristic parameters of each load type based on the load type, where the arc characteristic parameters characterize that the change amplitude affected by the arc is greater than a preset threshold;

[0028] An arc characteristic value determination module, configured to determine the arc characteristic value of the arc characteristic parameters according to the arc characteristic parameters;

[0029] A detection module is configured to use the load type and the arc characteristic value as input data, and obtain an arc detection result through a preset arc detection model. If there is an arc on any branch where a load type is located, the arc detection result is that there is an arc in the circuit. Among them, the preset arc detection model includes the threshold range of the arc characteristic parameters for different combinations of load types.

[0030] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the arc detection method described in the first aspect above is implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the arc detection method described in the first aspect above is implemented.

[0032] An arc detection method, device, and computer-readable storage medium provided by an embodiment of the present application at least have the following technical effects.

[0033] In the present application, the load in the circuit is identified by load identification of the circuit, and the load types in the circuit are recognized. According to the load types, the arc characteristic parameters of each load type are determined. By determining the arc characteristic parameters according to the load types, the arc characteristic parameters related to the load types are screened out from numerous arc characteristic parameters. Through the relevant arc characteristic parameters, the changes in the arcs generated by this type of load can be more accurately reflected. Based on the determined arc characteristic parameters, the arc characteristic value of the arc characteristic parameter in the circuit is determined, and the arc characteristic value and the load type are used as input data, and are detected through a preset arc detection model including the mapping relationship between the load type and several arc characteristic values, and an arc detection result is obtained. If an arc occurs on any branch where the load type is located, through the mapping relationship in the arc detection model, it is determined that an arc has occurred in the circuit. In the above manner, taking the load type as a judgment condition, the arc characteristic parameters whose change amplitude affected by the arc is greater than the preset threshold are screened out from numerous arc characteristic parameters, reducing the number of arc characteristic parameters, and there is also a mapping relationship between the load type and the arc characteristic value of the arc characteristic parameter in the arc detection model. Using a small number of arc characteristic parameters related to the load type as the conditions for arc detection, and detecting according to the load type and the arc characteristic parameters related to the load type, the influence of irrelevant arc characteristic parameters is reduced, and the arc characteristic parameters used for detection are significantly affected by the arc characteristic change amplitude, which can further improve the accuracy of arc detection.

[0034] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0036] Figure 1 is a flowchart of an arc detection method shown according to an exemplary embodiment;

[0037] Figure 2 is a schematic diagram of a set of charge characteristic parameters shown according to an exemplary embodiment;

[0038] Figure 3 is a schematic diagram of an arc detection method shown according to an exemplary embodiment;

[0039] Figure 4 is a block diagram of an arc detection device shown according to an exemplary embodiment;

[0040] Figure 5 is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0041] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described and explained below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0042] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as insufficient disclosure of the present application.

[0043] References to "embodiments" in this application mean that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0044] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meaning understood by those of ordinary skill in the technical field to which this application belongs. The words "a", "an", "one kind", "the" and the like involved in this application do not indicate a limitation in quantity and can mean singular or plural. The terms "include", "comprise", "have" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products or devices. The words "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0045] In a first aspect, an embodiment of this application provides an arc detection method. Figure 1 It is a flowchart of an arc detection method shown according to an exemplary embodiment, as Figure 1 shown. The arc detection method includes:

[0046] Step S101: Identify the load of the circuit and determine the type of load in the circuit.

[0047] Obtain the total current and total voltage in the circuit, identify the load of the circuit according to the total current and total voltage, and determine the type of load in the circuit. Among them, the output result of load identification is:

[0048] L(t), L(t) ∈ B,

[0049] L(t) is the type of load existing in the current circuit, and B is the complete set of all types of loads.

[0050] For example, B is all known types of loads, including refrigerators, lights, televisions, microwave ovens, and hair dryers. If the current circuit has a range hood and a microwave oven in parallel, the result of load identification is: L(t) is the range hood and the microwave oven.

[0051] The methods of load identification include steady-state identification and transient identification. Among them, the specific method of transient identification includes: obtaining the steady-state total current in the circuit, and when a load is connected or started in the circuit, obtaining the change amount of the steady-state total current in the circuit. Since different types of loads have unique transient characteristics when powered on, time-domain or frequency-domain features are extracted through the current waveform when the load starts, and combined with the load identification algorithm, the identification of the load type is realized.

[0052] Identify the types of loads in the circuit to determine the types of loads existing in the circuit, so as to provide a detection basis for subsequent determination of arc characteristic parameters.

[0053] Step S102: Based on the load types, determine the arc characteristic parameters of each load type, where the arc characteristic parameters characterize that the change amplitude affected by the arc is greater than a preset threshold.

[0054] According to the obtained load types, determine the arc characteristic parameters of each load type. Among them, the determination method is based on prior knowledge, that is, through various methods such as papers and experiments, it is determined that when different load types are affected by an arc, the change amplitude of the arc characteristic parameters is greater than the preset threshold. For each load type, there is at least one arc characteristic parameter. Among them, the arc characteristic parameters include time-domain characteristic parameters and frequency-domain characteristic parameters. The arc characteristic parameters include pulse factor, kurtosis, zero rest time, root mean square, Shannon entropy, fundamental frequency harmonic ratio, third harmonic ratio, and fifth harmonic ratio.

[0055] In one embodiment, a load identification is performed on a circuit, and the result of the load identification is: refrigerator, light bulb, microwave oven, and television. According to the load types in the circuit, through prior knowledge, the arc characteristic parameters of each load type are determined. For example, the arc characteristic parameters of the refrigerator are mean square deviation and pulse factor, the arc characteristic parameters of the microwave oven are Shannon entropy and kurtosis, the arc characteristic parameters of the television are zero rest time and fundamental frequency harmonic ratio, and the arc characteristic parameters of the light bulb are zero rest time.

[0056] Determining the arc characteristic parameters through the load types can screen out the arc characteristic parameters related to the load types from many arc characteristics, and determine that the arc characteristic parameters are closely related to the load types. When an arc exists in the branch where the load type is located, the arc characteristic parameters are affected by the arc and the change amplitude is greater than the preset threshold, so that the generation of the arc can be accurately reflected through the arc characteristic parameters.

[0057] Step S103: determining an arc characteristic value of the arc characteristic parameter according to the arc characteristic parameter.

[0058] After determining the arc characteristic parameters according to the load type, the arc characteristic values of the arc characteristic parameters are determined in the circuit. Based on the arc characteristic parameters of the load type of the current circuit, the set of arc characteristic values is determined:

[0059] C={Q(i),i∈L(t),L(t)∈B}

[0060] Where C is the set of arc eigenvalues, i is the load type, Q(i) is the arc eigenvalue corresponding to load type i, L(t) is the load type in the current circuit, and B is the complete set of all load types.

[0061] In one embodiment, the method for determining the arc characteristic value of the arc characteristic parameter specifically includes:

[0062] Step S131: Obtain the total current waveform in the circuit within a preset time period.

[0063] Obtain the total current waveform of the circuit within a preset duration. The total current waveform is obtained by summing the current waveforms of each branch in the circuit. The total current waveform within the preset duration can be used to calculate arc characteristic parameters.

[0064] Step S132: Determine the arc characteristic value of each arc characteristic parameter based on the total current waveform.

[0065] Based on the total current waveform, the arc characteristic value of each arc characteristic parameter is calculated. The arc characteristic value reflects whether the load type is affected by the arc.

[0066] In one embodiment, there are N types of loads in a circuit. If an arc occurs in a branch where the i-th type of load is located, the branch current waveform of the current branch satisfies the following configuration:

[0067] I i '(t)=F[i,I i (t)]

[0068] Among them, I i '(t) is the branch current waveform that generates the arc, i is the type of load, I i (t) is the branch current, and F[] is the function that characterizes the current waveform generated by the i-th load type.

[0069] When an arc occurs in the i-th type of load, the total current waveform is:

[0070]

[0071] Among them, I 0，i(t) is the total current waveform, I i ’(t) is the branch current waveform that generates the arc, I a (t) is the branch current waveform of other load types.

[0072] Based on the total current waveform I 0，i (t), the arc feature values of each arc feature parameter are calculated. Since an arc is generated in the branch of the i-th type of load, the total current waveform carries the information of the arc. Therefore, the arc feature parameters obtained from the total current waveform also carry the arc information, that is, the arc feature values of the arc feature parameters are abnormal.

[0073] Step S104: Using the load type and the arc feature value as input data, through a preset arc detection model, obtain the arc detection result. If there is an arc on the branch where any load type is located, the arc detection result is that there is an arc in the circuit. Among them, the preset arc detection model includes the threshold range of the arc feature parameters for different combinations of load types.

[0074] Take the recognition result of load recognition in step S101, that is, the load type in the circuit, and the arc feature value obtained in step S103 as input data. Through the preset arc detection model, obtain the arc detection result. The preset arc detection model contains the mapping relationship between the load type and several arc feature values. Based on the mapping relationship, by judging whether there is an abnormality between the input load type and the arc feature value corresponding to each load type, if there is an abnormality, determine whether there is an arc in the circuit.

[0075] Among them, the preset arc detection model includes a data module and a training module. The data module is used to obtain the training data of each type of load in the preset training database according to the load type. The training module is used to train the training data based on the preset training algorithm until the preset convergence condition is met.

[0076] In one embodiment, for any type of load, the preset arc detection model obtains training data from the preset training database in the data module and trains based on the training data. The training data includes the arc feature values when the load type generates an arc and the arc feature values when no arc is generated. In the training module, based on the training data, the preset arc model is trained through a training algorithm until the convergence condition is reached. When it is determined that an arc is generated for the current load type, the threshold range of the load arc feature parameters for the current load type is determined. Through training, it is predicted that the probability of detecting an arc generated by the current load type within this threshold range by the arc detection model is the highest. For example, when the current load type is a light bulb, the arc feature parameter of the light bulb in the preset training database is determined to be the zero rest time, and several arc feature values of several zero rest times are obtained. The arc feature values include the arc feature values when an arc is generated and the arc feature values when no arc is generated. The predictive arc detection model is trained to determine that the probability of detecting an arc is the highest when the zero rest time of the light bulb is within the threshold range of 1 s to 3 s. When the preset arc detection model is trained, the load type and the corresponding current waveform are input, and the preset arc detection model can detect whether an arc is generated in the current circuit according to whether the current real-time arc feature value is within the trained threshold range.

[0077] In another embodiment, during the training process of the preset arc detection model, training is performed for multiple types of loads. Different training data of arc parameters for different load types are obtained from the preset training database according to different load types. And based on the training data, training is carried out through a training algorithm until the convergence condition is reached, and the threshold range of the determined arc feature parameters is obtained. The threshold range represents the highest probability of detecting an arc within the threshold range. For example, the load types include light bulbs, refrigerators, and microwave ovens. The arc feature parameter of the light bulb in the preset training database is determined to be the zero rest time, the arc feature parameters of the refrigerator are the mean square deviation and the pulse factor, and the arc feature parameters of the microwave oven are the Shannon entropy and the kurtosis. The arc feature values corresponding to the arc feature parameters are obtained from the preset training database as training data. Based on the training data, the arc detection model is trained through a training algorithm to determine the threshold ranges of different arc feature parameters.

[0078] It should be noted that since multiple loads are trained simultaneously, the obtained threshold ranges will also vary. For example, when the trained load types are refrigerators and microwave ovens, the first threshold ranges of the mean square deviation, the pulse factor, the Shannon entropy, and the kurtosis are obtained; when the trained load types are refrigerators, microwave ovens, and light bulbs, the second threshold ranges of the mean square deviation, the pulse factor, the Shannon entropy, the kurtosis, and the zero rest time are obtained. There are differences between the first threshold range and the second threshold range of the mean square deviation, the pulse factor, the Shannon entropy, and the kurtosis. The specific differences are determined by the model training process.

[0079] When different load types are input into a preset arc detection model, the preset arc detection model can determine whether there is an arc in the current circuit according to the threshold ranges of arc characteristic parameters for different trained load types.

[0080] It should be noted that the training algorithms include neural networks, convolutional neural networks, clustering algorithms, decision trees, and are not specifically limited, and are selected according to the application scenario.

[0081] The trained preset arc detection model includes load types and mapping relationships. When the load types and arc characteristic values identified in the circuit are input into the preset arc detection model, the preset arc detection model can determine whether there is an arc in the current circuit according to the trained data, and thus output an arc detection result.

[0082] In this application, arc characteristic parameters are determined by load types. The arc characteristic parameters can reflect the situation of load types, that is, if an arc appears in the current load type, the arc characteristic value of the arc characteristic parameters determined by the load type will be abnormal. When an arc occurs in any branch where a load type is located, the branch current waveform of the current branch is an abnormal current waveform. The other branches where load types are located are all in normal operation, and the branch current waveforms are normal current waveforms. The total current waveform is obtained by superimposing all branch current waveforms, and the arc characteristic value obtained from the total current waveform will be an abnormal arc characteristic value. Therefore, when the abnormal arc characteristic value and the load type are input into the preset arc detection model, the preset arc detection model can determine whether an arc is generated in the circuit according to the mapping relationship.

[0083] In addition, after determining the arc characteristic parameters of each load type in step S101, it further includes:

[0084] Based on all load types, screen the arc characteristic parameters to determine a set of arc characteristic parameters. Specifically, it includes the following content: obtain the arc characteristic parameters of all load types; for all arc characteristic parameters, if the arc characteristic parameters of each load type are different, then use all arc characteristic parameters as the set of arc characteristic parameters.

[0085] If there are identical arc characteristic parameters among the arc characteristic parameters of the load types, retain the different arc characteristic parameters and one identical arc characteristic parameter, and use the retained arc characteristic parameters as the set of arc characteristic parameters.

[0086] Figure 2 It is a schematic diagram of a set of charge characteristic parameters shown according to an exemplary embodiment, as Figure 2As shown, the arc characteristic parameters corresponding to load type l include arc characteristic parameter 1, arc characteristic parameter 2, arc characteristic parameter 3, and arc characteristic parameter k; the arc characteristic parameters corresponding to load type j include arc characteristic parameter p, arc characteristic parameter q, and arc characteristic parameter 4; the arc characteristic parameters corresponding to load type i include arc characteristic parameter k, arc characteristic parameter m, arc characteristic parameter p, and arc characteristic parameter 5. Load type i and load type l have the same arc characteristic parameter k, and load type i and load type j have the same arc characteristic parameter p. By retaining the same arc characteristic parameters, the set of arc characteristic parameters is arc characteristic parameter 1, arc characteristic parameter 2, arc characteristic parameter 3, arc characteristic parameter 4, arc characteristic parameter 5, arc characteristic parameter k, arc characteristic parameter p, and arc characteristic parameter m, a total of 8 arc characteristic parameters. If there are no identical arc characteristic parameters among load type l, load type i, and load type j, that is, load type l has 4 arc characteristic parameters, load type i has 4 arc characteristic parameters, and load type j has 3 arc characteristic parameters, then the set of arc characteristic parameters has a total of 11 arc characteristic parameters. In this way, when there are identical arc characteristic parameters among different load types, the arc characteristic parameters to be detected can be reduced, thereby reducing the arc characteristic values to be processed by the arc detection model and improving the efficiency of arc detection.

[0087] Figure 3 is a schematic diagram of an arc detection method shown according to an exemplary embodiment. As Figure 3 shown, in this application, based on the load current and voltage information in the circuit, load identification is performed to determine the load type in the circuit, and the load type is transmitted to the arc detection algorithm. The load current and voltage information in the circuit is transmitted to the arc detection algorithm, and the arc detection algorithm performs arc identification based on the load type and the load current and voltage information to detect whether there is current in the circuit.

[0088] In summary, the load type determines the arc characteristic parameters, which limits the number of arc characteristic parameters, that is, reduces the parameters participating in arc detection, and these arc characteristic parameters are closely related to the load type and can significantly reflect the situation of the load type. Then, the load type and arc characteristic parameters are input into the preset arc detection model, and the preset arc detection model can perform accurate detection based on these few arc characteristic values that are closely related to the load type, thereby solving the problem that when detecting a large number of arc characteristic parameters, it is impossible to capture effective characteristic parameters for arc detection, resulting in a low accuracy of arc detection.

[0089] In a second aspect, an embodiment of the present application provides an arc detection device. Figure 4 is a block diagram of an arc detection device shown according to an exemplary embodiment. As Figure 4As shown in the figure, the arc detection device includes: a load identification module for identifying the load of a circuit to determine the type of load in the circuit;

[0090] An arc feature parameter determination module for determining the arc feature parameters of each type of load based on the type of load, where the arc feature parameters characterize the change amplitude affected by the arc and are greater than a preset threshold;

[0091] An arc feature value determination module for determining the arc feature value of the arc feature parameters according to the arc feature parameters;

[0092] A detection module for using the type of load and the arc feature value as input data, and obtaining an arc detection result through a preset arc detection model. If there is an arc on any branch where a type of load is located, the arc detection result is that there is an arc in the circuit. The preset arc detection model includes a threshold range of arc feature parameters for different combinations of load types.

[0093] In summary, for the arc detection device provided in this application, the application identifies the type of load in the circuit by identifying the load of the circuit. According to the type of load, the arc feature parameters of each type of load are determined. By determining the arc feature parameters according to the type of load, the arc feature parameters related to the type of load are screened out from numerous arc feature parameters. Through the relevant arc feature parameters, the change of the arc generated by this type of load can be more accurately reflected. Based on the determined arc feature parameters, the arc feature value of the arc feature parameters in the circuit is determined, and the arc feature value and the type of load are used as input data to be detected through a preset arc detection model including the mapping relationship between the type of load and several arc feature values, and an arc detection result is obtained. If an arc occurs on any branch where the type of load is located, it is determined that an arc has occurred in the circuit through the mapping relationship in the arc detection model. In the above manner, with the type of load as the judgment condition, the arc feature parameters whose change amplitude affected by the arc is greater than the preset threshold are screened out from numerous arc feature parameters, reducing the number of arc feature parameters. And there is also a mapping relationship between the type of load and the arc feature value of the arc feature parameters in the arc detection model. Using a small number of arc feature parameters related to the type of load as the conditions for arc detection and detecting according to the type of load and the arc feature parameters related to the type of load reduces the influence of irrelevant arc feature parameters and the arc feature parameters used for detection are significantly affected by the arc feature change amplitude, which can further improve the accuracy of arc detection.

[0094] It should be noted that the arc detection device provided in this embodiment is used to implement the above-mentioned implementation manners, and those that have been described will not be repeated. As used above, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the above embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0095] In a third aspect, an embodiment of the present application provides an electronic device, Figure 5 which is a block diagram of an electronic device shown according to an exemplary embodiment. As Figure 5 shown, the electronic device may include a processor 81 and a memory 82 storing computer program instructions.

[0096] Specifically, the above-mentioned processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0097] Among them, the memory 82 may include a mass storage for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, the memory 82 may include removable or non-removable (or fixed) media. In appropriate cases, the memory 82 may be internal or external to the data processing device. In a particular embodiment, the memory 82 is non-volatile memory. In a particular embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable read-only memory (EAROM), or a flash memory, or a combination of two or more of these. In appropriate cases, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended date out dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0098] The memory 82 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81.

[0099] The processor 81 reads and executes the computer program instructions stored in the memory 82 to implement any one of the arc detection methods in the above embodiments.

[0100] In one embodiment, the arc detection device may further include a communication interface 83 and a bus 80. Among them, as Figure 5 shown, the processor 81, the memory 82, and the communication interface 83 are connected through the bus 80 and complete communication with each other.

[0101] The communication interface 83 is used to implement communication between various modules, devices, units, and / or devices in the embodiments of the present application. The communication port 83 can also implement data communication with other components, such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations, etc.

[0102] The bus 80 includes hardware, software, or both, and couples the components of the arc detection device to each other. The bus 80 includes at least one of the following, including but not limited to: Data Bus, Address Bus, Control Bus, Expansion Bus, Local Bus. By way of example and not limitation, the bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. In suitable cases, the bus 80 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0103] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed by a processor, the arc detection method provided in the first aspect is implemented.

[0104] Among them, more specifically, the readable storage medium may include but is not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination of the above.

[0105] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps of implementing the arc detection method provided in the first aspect.

[0106] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, executed as an independent software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0107] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0108] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. An arc detection method, characterized in that, Including: Conduct load identification on the circuit to determine the types of loads in the circuit; Based on the types of loads, determine the arc characteristic parameters for each type of load, where the arc characteristic parameters characterize the change amplitude affected by the arc being greater than a preset threshold; According to the arc characteristic parameters, determine the arc characteristic values of the arc characteristic parameters; Using the types of loads and the arc characteristic values as input data, through a preset arc detection model, obtain an arc detection result. If there is an arc on the branch where any of the types of loads is located, the arc detection result is that there is an arc in the circuit, where the preset arc detection model includes the threshold ranges of the arc characteristic parameters for different combinations of the types of loads.

2. The arc detection method according to claim 1, characterized in that, The step of determining the arc characteristic values of the arc characteristic parameters according to the arc characteristic parameters includes: Within a preset time period, obtain the total current waveform in the circuit; Based on the total current waveform, determine the arc characteristic values of each arc characteristic parameter.

3. The arc detection method according to claim 1, wherein After determining the arc characteristic parameters for each type of load, it further includes: Based on all the types of loads, screen the arc characteristic parameters to determine the set of arc characteristic parameters.

4. The arc detection method according to claim 3, characterized in that The step of screening the arc characteristic parameters to determine the set of arc characteristic parameters includes: Obtain the arc characteristic parameters for all the types of loads; If the arc characteristic parameters for each type of load are all different, then use all the arc characteristic parameters as the set of arc characteristic parameters; If there are identical arc characteristic parameters among the arc characteristic parameters of the types of loads, retain the different arc characteristic parameters and one of the identical arc characteristic parameters, and use the retained arc characteristic parameters as the set of arc characteristic parameters.

5. The arc detection method according to claim 1, characterized in that, The step of conducting load identification on the circuit to determine the types of loads in the circuit includes: Obtain the total current and total voltage in the circuit; Based on the total current and the total voltage, conduct load identification on the circuit to determine the types of loads in the circuit.

6. The arc detection method according to claim 1, characterized in that The preset arc detection model includes: a data module and a training module; The data module is used to obtain the training data for each type of load in a preset training database according to the types of loads; The training module is used to train the training data based on a preset training algorithm until a preset convergence condition is met.

7. An arc detection device, characterized in that, Including: A load identification module, used to conduct load identification on the circuit to determine the types of loads in the circuit; An arc characteristic parameter determination module, used to determine the arc characteristic parameters for each type of load based on the types of loads, where the arc characteristic parameters characterize the change amplitude affected by the arc being greater than a preset threshold; An arc characteristic value determination module, used to determine the arc characteristic values of the arc characteristic parameters according to the arc characteristic parameters; A detection module, used to use the types of loads and the arc characteristic values as input data, through a preset arc detection model, obtain an arc detection result. If there is an arc on the branch where any of the types of loads is located, the arc detection result is that there is an arc in the circuit, where the preset arc detection model includes the threshold ranges of the arc characteristic parameters for different combinations of the types of loads.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the arc detection method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the arc detection method according to any one of claims 1 to 6.

Images