Direct-current arc discrimination method and related device

Abstract

The invention discloses a DC arc discrimination method and a related device, and the method comprises the steps: calculating the characteristics of a preset frequency point of a current signal within a preset time range according to the collected current signal; wherein the current signal is a current signal of each PV string of the inverter; within a preset time range, collection is carried out on a plurality of pre-selected channels, and collection is carried out on each channel for multiple times; direct current arc discrimination is carried out based on the difference between different channels; wherein the difference is the amplitude fluctuation difference between the same frequency point features. According to the method, the characteristics of the current signals of the multiple channels in the preset time range are calculated, direct-current arc judgment is carried out based on the amplitude fluctuation difference between the same frequency point characteristics of different channels, and compared with a traditional method, misjudgment and missed judgment are not likely to happen.

Description

Technical Field

[0001] The present invention relates to a method for discriminating DC arcs and related devices, belonging to the field of DC fault arc detection. Background Art

[0002] With the rapid increase in the global electrification level, the social electricity demand is increasing day by day. Traditional energy sources will cause a series of carbon emission pollution problems, and it is urgent to transform the energy development mode. Photovoltaic power generation has significant advantages such as cleanness and renewability, and has developed rapidly in recent years. However, the relevant safety technologies need to be improved urgently. Faults such as fires caused by DC fault arcs in photovoltaic systems seriously threaten the safe operation of the system.

[0003] Traditional DC fault arc detection devices and methods rely more on low-frequency sampling signals. When a DC fault arc occurs, it is relatively continuous and stable. Therefore, traditional DC arc discrimination methods (specifically time-frequency domain algorithms) basically rely on the magnitude of the frequency domain energy to identify arcs, that is, comparing the energy value with a threshold. However, this strategy is easily affected by different environments, light changes, equipment startup and shutdown, and switching frequency interference, and is prone to false judgments and missed judgments; for example: when there is interference, if the energy increases, a false judgment will occur when the threshold remains unchanged, and vice versa, a missed judgment will occur. Summary of the Invention

[0004] The present invention provides a method for discriminating DC arcs and related devices, which solves the problem of easy false judgment and missed judgment of traditional methods.

[0005] According to one aspect of the present disclosure, a method for discriminating DC arcs is provided, including: Within a preset time range, according to the collected current signal, calculate the characteristics of the preset frequency points of the current signal; wherein, the current signal is the current signal of each PV string of the inverter; within the preset time range, collect for a plurality of preselected channels, and each channel is collected multiple times; Perform DC arc discrimination based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the characteristics of the same frequency point.

[0006] Further, within the preset time range, collecting for a plurality of preselected channels, and each channel is collected multiple times, includes: Within the preset time range, use a polling method to collect for a plurality of preselected channels, and each channel is collected once per round.

[0007] Further, the duration of the preset time range is multiple times the duration of one round of polling.

[0008] Further, performing DC arc discrimination based on the differences between different channels includes: Construct a feature matrix according to the characteristics of each channel; Based on the feature matrix and the neural network, determine the channels that are different from other channels, and use the channels that are different from other channels as the channels with DC arcs.

[0009] According to another aspect of the present disclosure, there is provided a DC arc discrimination device, including: A feature calculation module that, within a preset time range, calculates the features of the preset frequency points of the current signal according to the collected current signal; wherein, the current signal is the current signal of each PV string of the inverter; within the preset time range, multiple preselected channels are collected, and each channel is collected multiple times; A discrimination module that performs DC arc discrimination based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the features of the same frequency point.

[0010] Further, in the feature calculation module, within the preset time range, the multiple preselected channels are collected in a polling manner, and each channel is collected once per round.

[0011] Further, in the feature calculation module, the duration of the preset time range is multiple times the duration of one polling.

[0012] Further, the discrimination module is configured to: construct a feature matrix according to the features of each channel; determine the channels that are different from other channels according to the feature matrix and the neural network, and use the channels that are different from other channels as the channels with DC arcs.

[0013] According to one aspect of the present disclosure, there is provided a computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to execute the DC arc discrimination method.

[0014] According to one aspect of the present disclosure, there is provided a computer device including one or more processors and one or more memories, the one or more programs being stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for executing the DC arc discrimination method.

[0015] The beneficial effects achieved by the present invention: The present invention calculates the features of the current signals of multiple channels within a preset time range, and performs DC arc discrimination based on the amplitude fluctuation difference between the features of the same frequency point of different channels. Compared with the traditional method, it is not easy to misjudge or miss judgment. Description of the Drawings

[0016] Figure 1 It is a flowchart of the DC arc discrimination method; Figure 2 It is a comparison chart of the feature amplitudes of different channels; Figure 3 It is a block diagram of a DC arc discrimination device. Specific implementation manners

[0017] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present disclosure and its application or use. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0018] Unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0019] At the same time, it should be understood that for the convenience of description, the dimensions of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0020] For technologies, methods, and devices known to those of ordinary skill in the relevant art, detailed discussions may not be made, but in appropriate cases, the technologies, methods, and devices should be regarded as part of the specification.

[0021] In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0022] It should be noted that similar symbols and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0023] In order to solve the problems of misjudgment and missed judgment in the DC arc discrimination method, the present disclosure proposes a new DC arc discrimination method. Specifically, the DC arc is discriminated by comparing the amplitude fluctuation differences between the current signal characteristics at the same frequency points of different channels. Compared with the traditional method, it is not easy to misjudge and miss judgment.

[0024] Embodiments of this application provide a DC arc discrimination method based on the differences between the characteristics of current signals of different channels. This DC arc discrimination method can be executed by a discrimination device, which can be a terminal device or a server. Among them, the terminal device can include, but is not limited to, mobile phones, computers, smart wearable devices, smart vehicle-mounted devices, etc., and embodiments of this application do not make limitations; the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, big data, and artificial intelligence platforms, etc., and embodiments of this application do not make limitations. Optionally, this DC arc discrimination method can also be executed collaboratively by multiple electronic devices with computing power. For the convenience of description, subsequent embodiments will be described as being executed by a discrimination device.

[0025] Please refer to Figure 1 , Figure 1 which is a flowchart of a DC arc discrimination method provided by embodiments of this application. This DC arc discrimination method can be executed by a discrimination device, and this DC arc discrimination method can at least include the following steps: Step 1, within a preset time range, calculate the characteristics of the preset frequency points of the current signal according to the collected current signal; where the current signal is the current signal of each PV string of the inverter; within the preset time range, collect for a plurality of preselected channels, and each channel is collected multiple times.

[0026] It should be noted that the number of channels, the number of times each channel is collected, the time range, and the frequency points, etc. can all be adaptively configured.

[0027] Assume that the number of channels is 8, and the number of times each channel is collected is 25 times. When collecting the current signal, if the main chip of the discrimination device supports 8-channel simultaneous collection, then 8-channel current signals can be synchronously collected each time. Considering cost factors, the main chips of many current devices do not support multi-channel simultaneous collection, that is, only one channel can be collected at a time. Therefore, in some embodiments, within the preset time range, the preselected multiple channels are collected in a polling manner, and each channel is collected once per round.

[0028] Still taking 8 channels and each channel being collected 25 times as an example, for Channel 1, collect the current signal and calculate the characteristics of the preset frequency points of the current signal. For example, FFT calculation can be performed to obtain the characteristics of the preset frequency points, and then switch to Channel 1 for the same processing. After collecting one round from Channel 1 to Channel 8, collect Channel 1 again, and a total of 25 rounds are collected.

[0029] It should be noted that, in order to ensure the accuracy of subsequent discrimination, the optimal number of acquisitions for each channel is the same. Therefore, in some embodiments, it is required to be able to poll an integer number of times within a preset time range, that is, the duration of the preset time range is a multiple of the duration of one polling. Taking 25 rounds as an example, assuming that the duration of each feature calculation is 2 ms, the duration of the preset time range can be set to 400 ms.

[0030] Step 2: Perform DC arc discrimination based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the features at the same frequency point.

[0031] It should be noted that when there is no arc, regardless of whether there is interference or not, the feature amplitudes corresponding to the channels do not fluctuate much. For example, Figure 2 the feature amplitude fluctuation of a frequency point in the time domain is less than 1, while for the channels with arcs, the feature amplitudes at the same frequency point have large fluctuations.

[0032] Based on the above analysis, the variance or range can be used to determine the fluctuation of each feature in a channel, so as to screen out the channels with large fluctuations and determine that there is a DC arc in this channel.

[0033] In order to improve the discrimination efficiency, in some embodiments, a neural network can be used for discrimination. Therefore, the process of performing DC arc discrimination based on the differences between the features of different channels can be as follows: 21) Construct a feature matrix according to the features of each channel.

[0034] Taking the 25 rounds within the above 400 ms as an example, assuming there are 50 preset frequency points, the accumulated features can form a 50×200 feature matrix. Among them, 50 represents the number of frequency points, 200 represents the total number of times a certain frequency point polls a certain channel, and the numerical size of the feature matrix represents the size of the frequency domain feature.

[0035] 22) Determine the channels that are different from other channels according to the feature matrix and the neural network, and use the channels that are different from other channels as the channels with DC arcs.

[0036] It should be noted that the neural network here can adopt a one-dimensional convolutional neural network. Before use, it is first trained with training samples. The training samples are the feature matrices composed of the features corresponding to normal channels, that is, the feature matrices composed of both the features corresponding to normal channels and the features corresponding to faulty channels. Input the feature matrix into the one-dimensional convolutional neural network, classify the features in the one-dimensional convolutional neural network, that is, obtain the channels that are different from other channels, and use this channel as the channel with DC arcs. Of course, if there is no difference between all the selected channels, it means that there is no DC arc in the selected channels.

[0037] The above method calculates the characteristics of the current signals of multiple channels within a preset time range, and discriminates direct current arcs based on the amplitude fluctuation differences between the same frequency point characteristics of different channels. Compared with traditional methods, it is not prone to misjudgment and missed judgment.

[0038] See Figure 3 , Figure 3 which is a block diagram of a direct current arc discrimination device provided by an embodiment of the present application. Figure 3 The embodiment of is a virtual device that can be loaded and executed by a computer device, which may include the above discrimination device. Figure 3 The device of may include a feature calculation module and a discrimination module. When used to execute the above direct current arc discrimination method, it can: A feature calculation module, which is used to calculate the characteristics of the preset frequency points of the current signal according to the collected current signal within a preset time range; wherein, the current signal is the current signal of each PV string of the inverter; within the preset time range, multiple preselected channels are collected, and each channel is collected multiple times.

[0039] It should be noted that considering cost factors, the main chips of many current devices do not support multi-channel simultaneous acquisition, that is, only one channel can be acquired at a time. Therefore, in some embodiments, a polling method is used for signal acquisition. Specifically, in the feature calculation module, within a preset time range, a polling method is used to collect multiple preselected channels, and each channel is collected once per round.

[0040] To ensure the accuracy of subsequent discrimination, it is optimal that the number of acquisitions for each channel is the same. Therefore, in some embodiments, in the feature calculation module, it is required that the duration of the preset time range is multiple times the duration of one round of polling.

[0041] A discrimination module, which is used to discriminate direct current arcs based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the same frequency point characteristics.

[0042] It should be noted that when there is no arc occurrence, regardless of whether there is interference or not, the characteristic amplitude corresponding to the channel does not fluctuate much, while for the channel with an arc, the characteristic amplitude corresponding to the channel has a large fluctuation.

[0043] Based on the above analysis, the discrimination module can determine the fluctuation situation of each characteristic in a channel through variance or range, so as to screen out the channels with large fluctuations and determine that there is a direct current arc in the channel.

[0044] To improve the discrimination efficiency, in some embodiments, the discrimination module may use a neural network for discrimination, and is specifically configured to: construct a feature matrix based on the features of each channel; determine the channels that are different from other channels according to the feature matrix and the neural network, and use the channels that are different from other channels as the channels with direct current arcs.

[0045] The above device calculates the features of the current signals of multiple channels within a preset time range, and discriminates direct current arcs based on the amplitude fluctuation differences between the same frequency point features of different channels. Compared with traditional methods, it is not easy to misjudge or miss judgments.

[0046] This application also relates to a computer-readable storage medium. The computer-readable storage medium stores one or more programs. The one or more programs include instructions that, when executed by a computing device, cause the computing device to execute the direct current arc discrimination method.

[0047] This application also relates to a computer device, including one or more processors and one or more memories. The one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors. The one or more programs include instructions for executing the direct current arc discrimination method.

[0048] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0049] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0050] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0052] The above are only embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention pending approval.

Claims

1. A method for discriminating DC arcs, characterized in that, Including: Within a preset time range, calculate the characteristics of the preset frequency points of the current signal according to the collected current signal; wherein, the current signal is the current signal of each PV string of the inverter; within the preset time range, collect for a plurality of preselected channels, and each channel is collected multiple times; Perform DC arc discrimination based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the characteristics of the same frequency point.

2. The method according to claim 1, wherein Within a preset time range, collect for a plurality of preselected channels, and each channel is collected multiple times, including: Within a preset time range, collect for a plurality of preselected channels in a polling manner, and each channel is collected once per round.

3. The method according to claim 2, wherein The duration of the preset time range is multiple times the duration of one polling round.

4. The method according to claim 1, wherein Performing DC arc discrimination based on the differences between different channels, including: Construct a feature matrix according to the characteristics of each channel; According to the feature matrix and the neural network, determine the channels that are different from other channels, and use the channels that are different from other channels as the channels with DC arcs.

5. A DC arc discrimination device, characterized in that, Including: A feature calculation module, within a preset time range, calculate the characteristics of the preset frequency points of the current signal according to the collected current signal; wherein, the current signal is the current signal of each PV string of the inverter; within the preset time range, collect for a plurality of preselected channels, and each channel is collected multiple times; A discrimination module, perform DC arc discrimination based on the differences between different channels; wherein, the difference is the amplitude fluctuation difference between the characteristics of the same frequency point.

6. The device according to claim 5, characterized in that, In the feature calculation module, within a preset time range, collect for a plurality of preselected channels in a polling manner, and each channel is collected once per round.

7. The device according to claim 6, characterized in that, In the feature calculation module, the duration of the preset time range is multiple times the duration of one polling round.

8. The device according to claim 5, characterized in that, The discrimination module is configured to: construct a feature matrix according to the characteristics of each channel; According to the feature matrix and the neural network, determine the channels that are different from other channels, and use the channels that are different from other channels as the channels with DC arcs.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, and the one or more programs include instructions that, when executed by a computing device, cause the computing device to execute the method according to any one of claims 1 to 4.

10. A computer device, characterized in that, Including: One or more processors, and one or more memories, the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to any one of claims 1 to 4.

Images