Method and apparatus for identifying direct-current fault arc, and computer device and storage medium

Abstract

The present application relates to a method and apparatus for identifying a direct-current fault arc, and a computer device, a storage medium and a computer program product. The method comprises: on the basis of a pre-established simulation system, acquiring sample current data, wherein the simulation system is used for simulating a target direct-current power supply and distribution system, and the state of the simulation system comprises the presence of an arc fault; using an association-rule-based data mining algorithm to process the sample current data, so as to obtain a target set, and performing feature extraction on a target item set, so as to obtain a target feature, wherein the target set is a frequent item set of the sample current data; and acquiring target current data, and when the feature of the target current data matches the target feature, determining that the target direct-current power supply and distribution system has a fault arc.

Description

Method and device for identifying direct current fault arc, computer device and storage medium

[0001] Related applications

[0002] The present application claims priority to the Chinese patent application No. 202410677572.7, filed on May 29, 2024, and entitled "Method and device for identifying direct current fault arc, computer device and storage medium", the content of which is hereby incorporated by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of electrical detection, and in particular to a method and device for identifying direct current fault arc, a computer device, a storage medium and a computer program product. BACKGROUND

[0004] To improve the ability of user side of urban power grid to participate in power grid interaction, a light storage flexible technology appears. The technology uses the outer surface of a building to generate photovoltaic power, and stores the generated power in a storage battery. The storage battery and a charging pile near a parking lot are connected to a direct current power distribution network for charging / discharging, so as to realize effective utilization of solar energy and electric vehicle battery resources and flexible power utilization. Therefore, a new type of urban power system based on a direct current power supply and distribution system will develop rapidly in the future.

[0005] However, in the case of long-time high-load operation of the direct current power supply and distribution system, connection loosening or animal scratching of the electrical circuit, etc., problems such as aging of electronic components and electrical circuit insulation layer, reduction of insulation effect, damage of insulation layer or loosening of contact point, etc. may occur, thereby causing a fault arc and threatening the normal operation of the system. The occurrence of the fault arc may burn the circuit and cause an electrical fire accident, which seriously threatens life and property safety.

[0006] At present, whether a fault arc exists is usually determined by analyzing the time-frequency domain characteristics of the loop current. However, when the fault arc occurs, the time-frequency domain characteristics of the loop current are not obvious. In addition, the position where the fault arc occurs may involve different electrode materials, and the time domain and frequency domain characteristics corresponding to different electrode materials are different, which makes it difficult to identify the fault arc. Therefore, there is an urgent need for a method for identifying a direct current fault arc to improve the identification efficiency and accuracy of the direct current fault arc. SUMMARY

[0007] According to various embodiments of the present application, a method and device for identifying a direct current fault arc, a computer device, a computer readable storage medium and a computer program product are provided.

[0008] In a first aspect, the present application provides a method for identifying a direct current fault arc, comprising:

[0009] Obtaining sample current data based on a pre-built simulation system, wherein the simulation system is used to simulate a target direct current power supply and distribution system, the state of the simulation system includes the existence of arc fault, and the sample current data is obtained by sampling the direct current bus current of the simulation system;

[0010] Processing the sample current data by using a data mining algorithm based on association rules to obtain a target set;

[0011] Extracting features from the target item set to obtain a target feature; the target set is a frequent item set of the sample current data;

[0012] Obtaining target current data;

[0013] In the case that the features of the target current data match the target feature, it is determined that the target direct current power supply and distribution system has a fault arc; the target current data is obtained by sampling the direct current bus current of the target direct current power supply and distribution system.

[0014] In one of the embodiments, the processing of the sample current data by using the data mining algorithm based on association rules to obtain a target set comprises:

[0015] Reconstructing a phase space of the sample current data to obtain a first set of target dimensions;

[0016] The feature extraction from the target item set to obtain a target feature comprises:

[0017] Traversing the data in the first set by using the data mining algorithm based on association rules to obtain a second set; the second set is a mapping set associated with the first set;

[0018] In the case that an association evaluation index between the second set and the first set meets a preset numerical range, it is determined that the second set is a target set; wherein the association evaluation index at least includes support, credibility, and positivity;

[0019] Summing the data in the target set by dimension respectively, and then dividing by the target dimension to obtain a target feature.

[0020] In one of the embodiments, the sample current data includes a first sub-sample sequence, and the first sub-sample sequence is obtained by sampling the direct current bus current of the simulation system in the case that the simulation system is in a state of non-existence of arc fault; after the feature extraction from the target item set to obtain a target feature, it comprises:

[0021] Calculating the average value of the first sub-sample sequence to obtain a first average value;

[0022] divide the target feature by the first average value to obtain a normalized target feature.

[0023] In one of the embodiments, the sample current data comprises a second sub-sample sequence, which is obtained by sampling a DC bus current of the simulation system in a case that the simulation system is in an arc fault state; and the calculating the average value of the first sub-sample sequence to obtain a first average value comprises:

[0024] calculating an average value of the second sub-sample sequence to obtain a second average value;

[0025] dividing the second average value by the first average value to obtain a feature evaluation index of the target feature;

[0026] in a case that the feature evaluation index is greater than a preset threshold, determining that the target feature is effective.

[0027] In one of the embodiments, the simulation system comprises a DC simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the DC simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is configured to ignite a fault arc; and the grid-connected inverter is connected in parallel with the resistor and configured to be connected to a power grid.

[0028] In one of the embodiments, an electrode material of the fault arc generator comprises at least one of aluminum, brass, red copper, ductile cast iron, stainless steel, and graphite; the fault arc generator is connected in parallel with a fault switch, and a state of the fault switch comprises closing and opening; in a case that the fault switch is in the open state, the fault arc generator is connected to the simulation system; in a case that the fault switch is in the closed state, the fault arc generator is disconnected from the simulation system; and the obtaining sample current data based on the pre-built simulation system comprises:

[0029] sampling a DC bus current of the simulation system in a first preset time period to obtain a first sub-sample sequence;

[0030] switching an electrode material of the fault arc generator to a target material;

[0031] switching the fault switch to the open state;

[0032] igniting an arc by using the fault arc generator;

[0033] sampling a DC bus current of the simulation system in a second preset time period to obtain a second sub-sample sequence;

[0034] switch the fault switch to a closed state;

[0035] In a third preset time period, a direct current bus current of the simulation system is sampled to obtain a third sub-sample sequence.

[0036] In a second aspect, the application further provides a device for identifying a direct current arc fault, comprising:

[0037] An acquisition module is configured to acquire sample current data based on a simulation system that is pre-built, wherein the simulation system is used to simulate a target direct current power supply and distribution system, the state of the simulation system includes an arc fault, and the sample current data is obtained by sampling a direct current bus current of the simulation system.

[0038] A data mining module is configured to process the sample current data by using a data mining algorithm based on association rules to obtain a target set.

[0039] A feature extraction module is configured to extract features from the target set to obtain a target feature, wherein the target set is a frequent item set of the sample current data.

[0040] A determination module is configured to acquire target current data, and determine that the target direct current power supply and distribution system has an arc fault if a feature of the target current data matches the target feature, wherein the target current data is obtained by sampling a direct current bus current of the target direct current power supply and distribution system.

[0041] In one of the embodiments, the data mining module comprises:

[0042] A phase space reconstruction submodule is configured to reconstruct phase space of the sample current data to obtain a first set of target dimensions.

[0043] The feature extraction module comprises:

[0044] A first determination submodule is configured to traverse data in the first set by using the data mining algorithm based on association rules to obtain a second set, wherein the second set is a mapping set associated with the first set.

[0045] A second determination submodule is configured to determine that the second set is the target set if an association evaluation index between the second set and the first set meets a preset numerical range, wherein the association evaluation index at least includes a support degree, a reliability degree and a positive or negative nature.

[0046] A third determination submodule is configured to sum data in the target set by dimension respectively, and then divide the sum by the target dimension to obtain the target feature.

[0047] In one of the embodiments, the sample current data comprises a first sub-sample sequence, which is obtained by sampling the DC bus current of the simulation system when the simulation system is in the state without arc fault; the device further comprises:

[0048] a first calculation module, configured to calculate the average value of the first sub-sample sequence to obtain a first average value;

[0049] a normalization module, configured to divide the target feature by the first average value to obtain a normalized target feature.

[0050] In one of the embodiments, the sample current data comprises a second sub-sample sequence, which is obtained by sampling the DC bus current of the simulation system when the simulation system is in the state with arc fault; the device further comprises:

[0051] a second calculation module, configured to calculate the average value of the second sub-sample sequence to obtain a second average value;

[0052] a third calculation module, configured to divide the second average value by the first average value to obtain a feature evaluation index of the target feature;

[0053] an effectiveness determination module, configured to determine that the target feature is effective when the feature evaluation index is greater than a preset threshold.

[0054] In one of the embodiments, the simulation system comprises a DC simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the DC simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is configured to ignite a fault arc; the grid-connected inverter is connected in parallel with the resistor and is configured to be connected to a power grid.

[0055] In one of the embodiments, the electrode material of the fault arc generator comprises at least one of the following: aluminum, brass, red copper, ductile cast iron, stainless steel, and graphite; the fault arc generator is connected in parallel with a fault switch, and the state of the fault switch comprises closing and opening; when the fault switch is in the open state, the fault arc generator is connected to the simulation system; when the fault switch is in the closed state, the fault arc generator is disconnected from the simulation system; the acquisition module comprises:

[0056] a first acquisition sub-module, configured to sample the DC bus current of the simulation system in a first preset time period to obtain a first sub-sample sequence;

[0057] a first switching sub-module, configured to switch the electrode material of the fault arc generator to a target material.

[0058] a second switching submodule, configured to switch the fault switch to an open state;

[0059] an arc ignition submodule, configured to ignite an arc by using the fault arc generator;

[0060] a second acquisition submodule, configured to sample a direct-current bus current of the simulation system in a second preset time period to obtain a second sub-sample sequence;

[0061] a third switching submodule, configured to switch the fault switch to a closed state;

[0062] a third acquisition submodule, configured to sample the direct-current bus current of the simulation system in a third preset time period to obtain a third sub-sample sequence.

[0063] In a third aspect, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method in any of the preceding aspects when executing the computer program.

[0064] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the method in any of the preceding aspects when executed by a processor.

[0065] In a fifth aspect, a computer program product is provided, including a computer program, and the computer program implements the steps of the method in any of the preceding aspects when executed by a processor.

[0066] The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the application will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of the disclosed drawings.

[0068] FIG. 1 is a flowchart of a method for identifying a direct-current fault arc in an embodiment;

[0069] FIG. 2 is a flowchart of processing sample current data by using a data mining algorithm based on association rules to obtain a target set, and extracting features of the target item set to obtain target features in an embodiment;

[0070] FIG. 3 is a flowchart of a method for identifying a DC fault arc in another embodiment;

[0071] FIG. 4 is a waveform diagram of sample current data in an embodiment;

[0072] FIG. 5 is a waveform comparison diagram of normalized target features obtained using a correlation rule-based data mining algorithm and using a related technology in an embodiment;

[0073] FIG. 6 is a comparison diagram of index values of feature evaluation indexes obtained using a correlation rule-based data mining algorithm and using a related technology under a resistive load in an embodiment;

[0074] FIG. 7 is a comparison diagram of index values of feature evaluation indexes obtained using a correlation rule-based data mining algorithm and using a related technology under an inverter load in an embodiment;

[0075] FIG. 8 is a circuit topology diagram of a simulation system in an embodiment;

[0076] FIG. 9 is a flowchart of obtaining sample current data based on a pre-built simulation system in an embodiment;

[0077] FIG. 10 is a structural block diagram of an apparatus for identifying a DC fault arc in an embodiment;

[0078] FIG. 11 is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0079] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of the present application.

[0080] In an embodiment, as shown in FIG. 1, a method for identifying a DC fault arc is provided, and the embodiment takes the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction of the terminal and the server. In the embodiment, the method includes the following steps:

[0081] In step S202, sample current data is obtained based on a pre-built simulation system. The simulation system is used to simulate a target DC power supply and distribution system, and the state of the simulation system includes the existence of an arc fault. The sample current data is obtained by sampling the DC bus current of the simulation system.

[0082] The target DC power supply and distribution system can be a subsystem in a power system powered by a DC source such as a photovoltaic array, a battery inside a building, a battery of an electric vehicle, etc. The simulation system is used to simulate the target DC power supply and distribution system, and the simulation system can be built according to the UL1699B standard.

[0083] Exemplarily, the state of the simulation system can be switched, and sample current data is obtained through an inductance sensor located at a DC bus of the simulation system, so that the sample current data includes current data in the state of the fault arc. Here, the frequency of sampling the DC bus current can be determined according to the hardware performance, for example, the sampling frequency can be 1 megahertz (MHz), 100 kilohertz (kHz), 200 kHz, etc.

[0084] In step S204, a data mining algorithm based on association rules is used to process the sample current data to obtain a target set, and a target item set is extracted to obtain a target feature. The target set is a frequent item set of the sample current data.

[0085] Exemplarily, the sample current data can be stored in a storage recorder, and the sample current data can be analyzed based on a MATLAB (MATrix LABoratory) platform. A suitable data mining algorithm can be selected according to the characteristics of the sample current data. For example, the data mining algorithm used for feature extraction of the sample current data can include at least one of the following: Apriori algorithm, FP-Growth (Frequent Pattern Growth) algorithm, classification analysis, clustering analysis, outlier analysis, etc.

[0086] In step S206, target current data is obtained, and in the case that the features of the target current data match the target features, it is determined that the target DC power supply and distribution system has a fault arc. The target current data is obtained by sampling the DC bus current of the target DC power supply and distribution system.

[0087] Exemplarily, the target features under different electrode materials and different circuit topologies can be evaluated, and in the case that the target features are identifiable, a data mining algorithm that determines the target features is used to process the target current data to obtain the features of the target current data. The features of the target current data are matched with the target features to determine whether the target DC power supply and distribution system has a fault arc. For example, the matching can be performed according to the characteristic waveform or the peak value of the normalized feature.

[0088] In the method for identifying the direct current arc fault, the simulation system is built according to the target direct current power supply system, and the sample current data in the arc fault state is obtained by sampling the direct current bus current of the simulation system. Then, the potential law and the correlation of the sample current data are mined by processing the sample current data based on the data mining algorithm of the association rule, and the target feature related to the arc fault state is obtained by extracting the feature of the frequent item set. The target feature is matched with the feature of the direct current bus current of the target direct current power supply system, so that the direct current arc fault in the target direct current power supply system can be effectively identified. The method can adaptively extract the time-frequency domain features of various electrode materials and various circuit topologies, and improve the identification efficiency and accuracy of the direct current arc fault.

[0089] In an exemplary embodiment, as shown in FIG. 2, the step S204 can include:

[0090] In step S2041, the sample current data is reconstructed in phase space to obtain a first set of target dimensions.

[0091] Exemplarily, the first set A of h dimensions can be represented by a first expression. The first expression can include:

[0092] A={I h (t1),I h (t2),…I h (t n )}。

[0093] In step S2042, a data mining algorithm based on the association rule is used to traverse the data in the first set to obtain a second set. The second set is a mapping set associated with the first set.

[0094] Exemplarily, the second set B can be represented by a second expression. The second expression can include:

[0095] B={f h (t1),f h (t2),…f h (t m )}。

[0096] In step S2043, when the association evaluation index between the second set and the first set meets the preset numerical range, the second set is determined as the target set. The association evaluation index at least includes the support, the confidence and the positive and negative.

[0097] Exemplarily, the support S between the second set and the first set can be determined by a first formula. The first formula can include:

[0098] S = sup(A→B) = sup(A∪B) = P(AB).

[0099] The second formula can be used to determine the confidence C between the second set and the first set. The second formula can include:

[0100] C = con(A→B) = P(B|A) = P(AB) / P(A).

[0101] The third formula can be used to determine the positive-negative L between the second set and the first set. The second formula can include:

[0102] Wherein, A→B is a formal description of the association rule between the first set A and the second set B, and P is a probability operator.

[0103] For example, the preset numerical range can be: support S is greater than 0.8, confidence C is greater than 0.8, and positive-negative L is greater than 10. It can be understood that when the association evaluation index between the second set and the first set meets the preset numerical range, the second set and the first set have a strong association relationship.

[0104] In step S2044, the data in the target set is summed up respectively according to the dimension, and then divided by the target dimension to obtain the target feature.

[0105] For example, the target feature can be a time-frequency feature, and the fourth formula can be used to determine the target feature F. The fourth formula can include:

[0106] Wherein, M is the number of elements of the second set B, and H is the embedding dimension.

[0107] In one possible implementation, the parameters involved in the above feature extraction process can be determined according to the characteristics of the sample current data. For example, the embedding dimension H is set to 5, the time window length n is set to 8000, the S initial value is set to 0.8, the C initial value is set to 0.8, and the L initial value is set to 10; the embedding dimension H is set to 5, the time window length n is set to 4000, the S initial value is set to 0.7, the C initial value is set to 0.7, and the L initial value is set to 5.

[0108] The embodiment provides a specific method for extracting sample current data features. By analyzing the relationship between data, the potential operation rule of the data in the system can be obtained, and then the features related to the fault arc state in the system can be extracted.

[0109] In an exemplary embodiment, the sample current data can include a first sub-sample sequence, the first sub-sample sequence being obtained by sampling the DC bus current of the simulation system when the simulation system is in the state of no arc fault, as shown in FIG. 3, and the method for identifying the DC fault arc can further include:

[0110] In step S2051, the average value of the first sub-sample sequence is calculated to obtain a first average value.

[0111] In step S2052, the target feature is divided by the first average value to obtain a normalized target feature.

[0112] Exemplarily, the fifth formula can be used to determine the normalized target feature NF. The fifth formula can include: NF = F / mean[F( / )];

[0113] wherein F is the target feature, F( / ) is the first sub-sample sequence, and mean is an operator for calculating the average value of a time sequence signal.

[0114] Please refer to FIG. 4 and FIG. 5, FIG. 4 is a waveform diagram of sample current data in an embodiment, and FIG. 5 is a waveform comparison diagram of the normalized target feature obtained by using the data mining algorithm based on the association rule and the normalized target feature obtained by using the related technology. In FIG. 4, I is the waveform of the sample current data of the inverter load under the aluminum electrode material, and F0 is the target feature obtained by wavelet transform on I. At this time, the variation of the time domain waveform of the current is not obvious, and the target feature obtained by wavelet transform on I also has no obvious change. That is, the time-frequency domain feature caused by the fault arc under the aluminum electrode material is relatively weak. Therefore, it is difficult to realize the identification of the fault arc by using the related technology. In FIG. 5, NF is the normalized target feature obtained by using the Apriori algorithm under the inverter load and the aluminum electrode material, and NF0 is the normalized target feature obtained by using the wavelet transform method under the inverter load and the aluminum electrode material. It can be understood that the normalized target feature obtained by using the data mining algorithm based on the association rule has higher identification than the normalized target feature obtained by using the related technology.

[0115] In the embodiment, by normalizing the target feature of the sample current data, the effectiveness of the target features extracted by different methods can be more intuitively compared.

[0116] In an exemplary embodiment, the sample current data can include a second sub-sample sequence, the second sub-sample sequence being obtained by sampling the DC bus current of the simulation system when the simulation system is in the state of arc fault, please continue to refer to FIG. 3, and the method for identifying the DC fault arc can further include:

[0117] Step S2053, the average value of the second sub-sample sequence is calculated to obtain a second average value.

[0118] Step S2054, the second average value is divided by the first average value to obtain the feature evaluation index of the target feature.

[0119] Exemplarily, the sixth formula can be used to determine the feature evaluation index Q of the target feature. The sixth formula can include: Q = mean[F( / / )] / mean[F( / )];

[0120] Wherein, F( / ) is the first sub-sample sequence, F( / / ) is the second sub-sample sequence, and mean is an operator for calculating the average value of the time sequence signal. For example, please continue to refer to FIG. 4, under the condition of inverter load and aluminum electrode material, the value of the feature evaluation index obtained by using the Apriori algorithm is 23.16, and the value of the feature evaluation index obtained by using the wavelet transform method is 0.94.

[0121] Step S2055, in the case that the feature evaluation index is greater than a preset threshold, it is determined that the target feature is effective.

[0122] Please refer to FIG. 6 and FIG. 7, FIG. 6 is a comparison diagram of the index values of the feature evaluation indexes obtained by using the data mining algorithm based on the association rule and the related technology under the condition of resistance load in an embodiment, and FIG. 7 is a comparison diagram of the index values of the feature evaluation indexes obtained by using the data mining algorithm based on the association rule and the related technology under the condition of inverter load in an embodiment. Wherein, Q is the index value of the feature evaluation index obtained by using the Apriori algorithm under the condition of multiple electrode materials, and Q0 is the index value of the feature evaluation index obtained by using the wavelet transform method under the condition of multiple electrode materials. It can be understood that the feature evaluation index obtained by using the data mining algorithm based on the association rule has a larger index value compared with the feature evaluation index obtained by using the related technology, that is, the data mining algorithm based on the association rule can better identify the fault arc under the condition of multiple electrode materials. For example, for aluminum, brass and other electrode materials, the related technology is difficult to effectively identify, and the data mining algorithm based on the association rule can realize the identification of the fault arc under the condition of aluminum, brass and other electrode materials; for stainless steel, graphite and other electrode materials, the data mining algorithm based on the association rule can improve the identifiability of the fault arc.

[0123] Further, the data mining algorithm with the largest feature evaluation index Q can be selected as the target processing method under the condition of the current electrode material and the circuit topology, and the target current data is processed by using the target processing method to obtain the feature of the target current data.

[0124] In this embodiment, by determining the effectiveness of the target feature according to the feature evaluation index, the effectiveness of the target feature extracted by different methods can be compared through simple numerical comparison, and the efficiency of determining the optimal feature extraction method is further improved.

[0125] In an exemplary embodiment, the simulation system can include a direct current simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the direct current simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is used to ignite a fault arc; and the grid-connected inverter is connected in parallel with the resistor and is used to connect to a power grid.

[0126] For example, referring to FIG. 8, FIG. 8 is a schematic diagram of a circuit topology of a simulation system according to an embodiment of the present application. The direct current simulation power supply can include a rectifier and a direct current / direct current (DC / DC) converter; the direct current converter can work under any designed volt-ampere characteristic and is used to simulate the output of a photovoltaic array; and the direct current converter can provide a constant voltage mode and a constant current mode. The resistor can be connected in series with a first switch, and the first switch is used to connect the resistor to the simulation system. The grid-connected inverter source can be connected in series with a second switch, and the second switch is used to connect the grid-connected inverter to the simulation system. The arc fault generator (AFG) is located on the direct current bus between the load and the direct current simulation power supply; the arc fault generator has two electrodes (a stationary electrode and a moving electrode), and the moving electrode can ignite a fault arc according to the UL1699B standard by using the draw arc method.

[0127] It should be noted that FIG. 8 takes the simulation system for simulating series arcs as an example, and the simulation system can also be used to simulate parallel arcs. In this case, the circuit topology of the simulation system can be that the arc fault generator is connected in parallel with the load.

[0128] In an exemplary embodiment, the electrode material of the arc fault generator includes at least one of aluminum, brass, red copper, ductile cast iron, stainless steel, and graphite; the arc fault generator is connected in parallel with a fault switch, and the state of the fault switch includes closing and opening; the arc fault generator is connected to the simulation system when the fault switch is in the open state; the arc fault generator is disconnected from the simulation system when the fault switch is in the closed state; and as shown in FIG. 9, the step S202 can include:

[0129] In step S2021, the direct current bus current of the simulation system is sampled in a first preset time period to obtain a first sub-sample sequence.

[0130] In step S2022, the electrode material of the fault arc generator is switched to a target material, the fault switch is switched to an open state, the fault arc generator is used to ignite an arc, and the DC bus current of the simulation system is sampled within a second preset time period to obtain a second sub-sample sequence.

[0131] The target material can be one of aluminum, brass, copper, ductile cast iron, stainless steel, graphite, or other materials that can be used as an electrode. It can be understood that by switching the electrode material of the fault generator, a fault arc under different electrode materials can be triggered, and then the target features of the sample current data under different electrode materials can be extracted.

[0132] In step S2023, the fault switch is switched to a closed state, and the DC bus current of the simulation system is sampled within a third preset time period to obtain a third sub-sample sequence.

[0133] Exemplarily, referring to FIGS. 4 and 8, in the first preset time period (stage I in FIG. 4), the simulation system is in normal operation, and the current value tends to be stable at 15 amperes; the electrode material of the fault arc generator is switched to aluminum, the fault switch is switched to an open state, the fault arc generator is connected to the simulation system to generate a DC fault arc, in the second preset time period (stage II in FIG. 4), the time-domain waveform of the current starts to fluctuate, and the current value decreases as a whole; the fault switch is switched to a closed state, and the fault arc generator is disconnected from the simulation system, in the first preset time period (stage III in FIG. 4), the current value tends to be 0.

[0134] In summary, in the above-mentioned DC fault arc identification method, by building a simulation system according to a target DC power supply system and sampling the DC bus current of the simulation system, sample current data in an arc fault state can be obtained; then, by processing the sample current data based on a correlation rule-based data mining algorithm, the frequent item set of the sample current data can be determined, the potential law and correlation of the sample current data can be mined, and the target features related to the arc fault state can be obtained by feature extraction on the frequent item set; the target features are matched with the features of the DC bus current of the target DC power supply system, and the DC fault arc in the target DC power supply system can be effectively identified. The above-mentioned method can adaptively extract time-frequency domain features under multiple electrode materials and multiple circuit topologies, and improves the identification efficiency and accuracy of the DC fault arc.

[0135] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or stages.

[0136] Based on the same inventive concept, the embodiments of the present application also provide a device for identifying a DC fault arc, which is used to implement the method for identifying a DC fault arc described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more device embodiments for identifying a DC fault arc provided below can refer to the limitations of the method for identifying a DC fault arc described above, which will not be repeated here.

[0137] In an exemplary embodiment, as shown in FIG. 10, a device 300 for identifying a DC fault arc is provided, which includes an acquisition module 301, a feature extraction module 302, and a determination module 303, wherein:

[0138] The acquisition module 301 is configured to acquire sample current data based on a pre-built simulation system. The simulation system is used to simulate a target DC power supply and distribution system, and the state of the simulation system includes the existence of an arc fault. The sample current data is obtained by sampling the DC bus current of the simulation system.

[0139] The feature extraction module 302 is configured to process the sample current data by using a data mining algorithm based on association rules to obtain a target set, and to extract features from the target item set to obtain target features. The target set is a frequent item set of the sample current data.

[0140] The determination module 303 is configured to acquire target current data, and determine that the target DC power supply and distribution system has a fault arc if the features of the target current data match the target features. The target current data is obtained by sampling the DC bus current of the target DC power supply and distribution system.

[0141] In an exemplary embodiment, the feature extraction module 302 described above includes:

[0142] The phase space reconstruction submodule is configured to perform phase space reconstruction on the sample current data to obtain a first set of target dimensions.

[0143] The first determining sub-module is configured to traverse the data in the first set by using a data mining algorithm based on association rules to obtain a second set; the second set is a mapping set associated with the first set.

[0144] The second determining sub-module is configured to determine the second set as a target set when an association evaluation index between the second set and the first set meets a preset numerical range; the association evaluation index at least includes a support degree, a credibility, and a positive or negative nature.

[0145] The third determining sub-module is configured to sum the data in the target set according to dimensions respectively, and then divide by a target dimension number to obtain a target feature.

[0146] In an exemplary embodiment, the sample current data includes a first sub-sample sequence, which is obtained by sampling the direct current bus current of the simulation system when the simulation system is in an arc fault-free state; the direct current fault arc recognition device 300 further includes:

[0147] The first calculating module is configured to calculate the average value of the first sub-sample sequence to obtain a first average value.

[0148] The normalization module is configured to divide the target feature by the first average value to obtain a normalized target feature.

[0149] In an exemplary embodiment, the sample current data includes a second sub-sample sequence, which is obtained by sampling the direct current bus current of the simulation system when the simulation system is in an arc fault state; the direct current fault arc recognition device 300 further includes:

[0150] The second calculating module is configured to calculate the average value of the second sub-sample sequence to obtain a second average value.

[0151] The third calculating module is configured to divide the second average value by the first average value to obtain a feature evaluation index of the target feature.

[0152] The effectiveness determining module is configured to determine that the target feature is effective when the feature evaluation index is greater than a preset threshold.

[0153] In an exemplary embodiment, the simulation system includes a direct current simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the direct current simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is configured to ignite a fault arc; the grid-connected inverter is connected in parallel with the resistor and is configured to be connected to a power grid.

[0154] In an example embodiment, the electrode material of the above-mentioned fault arc generator at least includes at least one of the following: aluminum, brass, red copper, ductile cast iron, stainless steel, graphite; the fault arc generator is connected in parallel with a fault switch, the state of the fault switch includes closing and opening; in the case that the fault switch is in the opening state, the fault arc generator is connected to the simulation system; in the case that the fault switch is in the closing state, the fault arc generator is disconnected from the simulation system; the above-mentioned acquisition module 301 includes:

[0155] A first acquisition submodule is configured to sample the DC bus current of the simulation system in a first preset time period to obtain a first sub-sample sequence.

[0156] A second acquisition submodule is configured to switch the electrode material of the fault arc generator to a target material, switch the fault switch to the opening state, ignite an arc by using the fault arc generator, and sample the DC bus current of the simulation system in a second preset time period to obtain a second sub-sample sequence.

[0157] A third acquisition submodule is configured to switch the fault switch to the closing state, sample the DC bus current of the simulation system in a third preset time period, and obtain a third sub-sample sequence.

[0158] The above-mentioned modules in the recognition device of the DC fault arc can be realized by software, hardware, and combinations thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned modules.

[0159] In an example embodiment, a computer device is provided, which can be a server, and the internal structure diagram thereof can be as shown in FIG. 11. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a recognition method of a DC fault arc.

[0160] Those skilled in the art can understand that the structure shown in FIG. 11 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0162] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0163] In an exemplary embodiment, a computer program product is provided, comprising a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0165] Any combination of the technical features of the above-mentioned embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above-mentioned embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0166] The above-mentioned embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the application. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A method of identifying a direct current fault arc, the method comprising: The method comprises: obtaining sample current data based on a pre-built simulation system; wherein the simulation system is used to simulate a target direct current power supply and distribution system, the state of the simulation system includes the existence of an arc fault, and the sample current data is obtained by sampling the direct current bus current of the simulation system; processing the sample current data by using a data mining algorithm based on association rules to obtain a target set; extracting features from the target item set to obtain a target feature; the target set is a frequent item set of the sample current data; obtaining target current data; in the case that the features of the target current data match the target features, determining that the target direct current power supply and distribution system has a fault arc; the target current data is obtained by sampling the direct current bus current of the target direct current power supply and distribution system.

2. The method of claim 1, wherein, The method comprises: reconstructing the phase space of the sample current data to obtain a first set of target dimensions; The method comprises: traversing the data in the first set by using a data mining algorithm based on association rules to obtain a second set; the second set is a mapping set associated with the first set; in the case that the association evaluation index between the second set and the first set meets the preset numerical range, determining that the second set is the target set; wherein the association evaluation index at least includes support, credibility, and positivity; summing the data in the target set by dimension, and then dividing by the target dimension to obtain the target feature.

3. The method of claim 1, wherein, The sample current data comprises a first sub-sample sequence, which is obtained by sampling the direct current bus current of the simulation system in the case that the simulation system is in a state without an arc fault; The method comprises: calculating the average value of the first sub-sample sequence to obtain a first average value; dividing the target feature by the first average value to obtain a normalized target feature.

4. The method of claim 3, wherein, The sample current data comprises a second sub-sample sequence, which is obtained by sampling the direct current bus current of the simulation system in the case that the simulation system is in a state with an arc fault; The method comprises: calculating the average value of the second sub-sample sequence to obtain a second average value; dividing the second average value by the first average value to obtain a feature evaluation index of the target feature; in the case that the feature evaluation index is greater than a preset threshold, determining that the target feature is valid.

5. The method of claim 1, wherein, The simulation system comprises a direct current simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the direct current simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is used to ignite a fault arc; the grid-connected inverter is connected in parallel with the resistor and is used to connect a power grid.

6. The method of claim 5, wherein, The electrode material of the fault arc generator at least includes at least one of aluminum, brass, red copper, nodular cast iron, stainless steel and graphite; the fault arc generator is connected in parallel with a fault switch, and a state of the fault switch includes closing and opening; in a case where the fault switch is in the opening state, the fault arc generator is connected to the simulation system; in a case where the fault switch is in the closing state, the fault arc generator is disconnected from the simulation system; The simulation system is pre-built, and sample current data is obtained, including: In a first preset time period, the DC bus current of the simulation system is sampled to obtain a first sub-sample sequence; Switching the electrode material of the fault arc generator to a target material; Switching the fault switch to the opening state; Igniting the arc by using the fault arc generator; In a second preset time period, the DC bus current of the simulation system is sampled to obtain a second sub-sample sequence; Switching the fault switch to the closing state; In a third preset time period, the DC bus current of the simulation system is sampled to obtain a third sub-sample sequence.

7. An apparatus for identifying a direct current fault arc, comprising: The device comprises: An acquisition module is configured to obtain sample current data based on a pre-built simulation system; wherein the simulation system is used to simulate a target direct current power supply and distribution system, the state of the simulation system includes an arc fault, and the sample current data is obtained by sampling the DC bus current of the simulation system; A data mining module is configured to process the sample current data by using a data mining algorithm based on association rules to obtain a target set; A feature extraction module is configured to extract features from the target item set to obtain a target feature; the target set is a frequent item set of the sample current data; A determination module is configured to obtain target current data, and determine that the target direct current power supply and distribution system has a fault arc in a case where the features of the target current data match the target features; the target current data is obtained by sampling the DC bus current of the target direct current power supply and distribution system.

8. The apparatus of claim 7, wherein, The data mining module comprises: A phase space reconstruction submodule is configured to reconstruct the phase space of the sample current data to obtain a first set of target dimensions; The feature extraction module comprises: A first determination submodule is configured to traverse the data in the first set by using a data mining algorithm based on association rules to obtain a second set; the second set is a mapping set associated with the first set; A second determination submodule is configured to determine that the second set is a target set in a case where an association evaluation index between the second set and the first set meets a preset numerical range; wherein the association evaluation index at least includes support, credibility and positivity; A third determination submodule is configured to sum the data in the target set by dimension respectively, and then divide by the target dimension to obtain a target feature.

9. The apparatus of claim 7, wherein, The sample current data includes a first sub-sample sequence, the first sub-sample sequence being obtained by sampling a direct current bus current of the simulation system in a case that the simulation system is in an arc fault non-existing state; the device further includes: a first calculation module configured to calculate an average value of the first sub-sample sequence to obtain a first average value; a normalization module configured to divide the target feature by the first average value to obtain a normalized target feature.

10. The apparatus of claim 9, wherein, The sample current data includes a second sub-sample sequence, the second sub-sample sequence being obtained by sampling a direct current bus current of the simulation system in a case that the simulation system is in an arc fault existing state; the device further includes: a second calculation module configured to calculate an average value of the second sub-sample sequence to obtain a second average value; a third calculation module configured to divide the second average value by the first average value to obtain a feature evaluation index of the target feature; an effectiveness determination module configured to determine that the target feature is effective in a case that the feature evaluation index is greater than a preset threshold.

11. The apparatus of claim 7, wherein, The simulation system includes a direct current simulation power supply, a fault arc generator, a resistor, and a grid-connected inverter; the direct current simulation power supply, the fault arc generator, and the resistor are connected in series; the fault arc generator is configured to ignite a fault arc; the grid-connected inverter is connected in parallel with the resistor and is configured to be connected to a power grid.

12. The apparatus of claim 11, wherein, An electrode material of the fault arc generator includes at least one of aluminum, brass, red copper, nodular cast iron, stainless steel, and graphite; the fault arc generator is connected in parallel with a fault switch, a state of the fault switch including closing and opening; in a case that the fault switch is in the opening state, the fault arc generator is connected to the simulation system; in a case that the fault switch is in the closing state, the fault arc generator is disconnected from the simulation system; The acquisition module includes: a first acquisition sub-module configured to sample a direct current bus current of the simulation system in a first preset time period to obtain a first sub-sample sequence; a first switching sub-module configured to switch an electrode material of the fault arc generator to a target material; a second switching sub-module configured to switch the fault switch to an opening state; an arc ignition sub-module configured to ignite an arc by using the fault arc generator; a second acquisition sub-module configured to sample a direct current bus current of the simulation system in a second preset time period to obtain a second sub-sample sequence; a third switching sub-module configured to switch the fault switch to a closing state; a third acquisition sub-module configured to sample a direct current bus current of the simulation system in a third preset time period to obtain a third sub-sample sequence.

13. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

14. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

15. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images