DC fault arc detection method and device

Abstract

The invention provides a DC fault arc detection method and device, and the method comprises the steps: carrying out the processing of a to-be-analyzed electrical signal sequence through combining three feature extraction technologies: wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction, and classical modal decomposition and reconstruction, and obtaining a first electrical feature signal sequence, a second electrical feature signal sequence, and a third electrical feature signal sequence. The method can reveal the fault features of the electrical signals from multiple dimensions, achieves feature fusion, effectively improves the accuracy and robustness of fault detection, reduces the phenomena of false alarm and missing alarm, is high in adaptability, is suitable for analysis of various electrical signals, and provides precise and reliable technical support for arc fault detection of a direct current power supply system.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a DC fault arc detection method and device. Background Art

[0002] In recent years, due to the rapid increase of DC power equipment and the increase of distributed energy, DC power supply has been increasingly widely used in distribution networks. Compared with AC power supply, DC power supply has the advantages of low energy loss, high power supply efficiency, and low line cost. It is widely used in large data centers, electric vehicles, space shuttles, electrified ships and other fields. However, in DC distribution networks, due to the small cross-section of the conductors, low mechanical strength, and low insulation level of the lines, insulation damage, line aging, and conductor breakage are very likely to occur during the operation of the system, leading to the generation of DC arcs. The power supply system of spacecraft, the electrical system of automobiles, etc., these power electronic systems are also the hardest hit areas for DC arc faults. DC arcs have no current zero point and cannot be extinguished by themselves. If the fault cannot be detected and eliminated in time, the DC arc will endanger the power supply system and control system. In severe cases, it may cause fires and explosions, posing a threat to the stable operation of equipment and systems and the personal safety of operators. Summary of the invention

[0003] The technical problem to be solved by the embodiments of the present invention is to provide a method and device for detecting a DC fault arc, so as to improve the accuracy and efficiency of the DC fault arc detection.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a DC fault arc detection method, comprising the following steps:

[0005] Sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence;

[0006] Extracting an electrical signal sequence to be analyzed that matches a preset time window from the electrical signal sequence, wherein the electrical signal sequence to be analyzed includes a current signal sequence and a voltage signal sequence to be analyzed;

[0007] Performing wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical characteristic signal sequence, performing intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical characteristic signal sequence, and performing classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical characteristic signal sequence;

[0008] When the load type of the monitored load is unknown, similarity measurement is performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads, and the first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads are input into a pre-trained first probabilistic neural network to obtain the load type of the monitored load;

[0009] When the load type of the monitored load is known, similarity measurements are performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis are input into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

[0010] Optionally, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;

[0011] The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

[0012] Optionally, the performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the multiple preset types of loads, further includes:

[0013] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0014] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0015] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0016] Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0017] Optionally, the performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis further includes:

[0018] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0019] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0020] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0021] Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0022] Optionally, the method further comprises:

[0023] After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

[0024] The embodiment of the present invention further provides a DC fault arc detection device, comprising:

[0025] A sampling module, used for sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence;

[0026] A preprocessing module, used for extracting a to-be-analyzed electrical signal sequence that matches a preset time window from the electrical signal sequence, wherein the to-be-analyzed electrical signal sequence includes a to-be-analyzed current signal sequence and a to-be-analyzed voltage signal sequence;

[0027] a feature extraction module, configured to perform wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical feature signal sequence, perform intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical feature signal sequence, and perform classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical feature signal sequence;

[0028] A load type identification module, for, when the load type of the monitored load is unknown, performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads, respectively, and inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads into a pre-trained first probabilistic neural network to obtain the load type of the monitored load;

[0029] A load fault identification module is used to perform similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load when the load type of the monitored load is known, to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and input the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

[0030] Optionally, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;

[0031] The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

[0032] Optionally, the load type identification module is further used to:

[0033] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0034] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0035] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0036] Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0037] Optionally, the load fault identification module is further used to:

[0038] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0039] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0040] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0041] Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0042] Optionally, the feature extraction module is further used to:

[0043] After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

[0044] The embodiments of the present invention have the following beneficial effects:

[0045] The embodiments of the present invention adopt a variety of feature extraction methods, namely wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction, and classical mode decomposition and reconstruction, to process the electrical signal sequence to be analyzed, thereby obtaining electrical feature signal sequences of multiple dimensions, and these features are integrated to improve the accuracy of fault detection. The embodiments of the present invention effectively reduce the risk of safety accidents such as fires and explosions caused by arc faults by real-time monitoring and rapid processing of DC arc faults, and ensure the stable operation of equipment and systems. The embodiments of the present invention are applicable to various DC power supply systems, such as large data centers, electric vehicles, space shuttles, electrified ships, etc., and have broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0047] Figure 1 The figure is a flow chart of a DC fault arc detection method in one embodiment of the present invention.

[0048] Figure 2 The figure is a structural diagram of a DC fault arc detection device in one embodiment of the present invention. DETAILED DESCRIPTION

[0049] The detailed description of the drawings is intended as an illustration of the current embodiment of the present application, and is not intended to represent the only form in which the present application can be implemented. It should be understood that the same or equivalent functions can be accomplished by different embodiments intended to be included in the spirit and scope of the present application.

[0050] See also Figure 1 An embodiment of the present invention provides a DC fault arc detection method, comprising the following steps:

[0051] Step S10, sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence.

[0052] Specifically, the description in step S10 involves the basic process of electrical signal sampling. The sampling frequency refers to the number of samples per unit time, usually in Hertz (Hz). The preset sampling frequency is a parameter set before signal acquisition. It determines the sampling time interval. This frequency needs to be high enough to ensure that the original signal can be accurately restored.

[0053] The electrical signal of the monitored load refers to the electrical signal generated by the monitoring target (ie, the load) during operation, including current and voltage signals. The load can be any device or system that uses direct current.

[0054] Sampling refers to recording the value of an electrical signal at a specific point in time according to a preset sampling frequency. This process is the first step in digitization, converting a continuous analog signal into a discrete digital signal.

[0055] A series of numerical values ​​obtained through sampling are arranged in chronological order to form an electrical signal sequence. In this step, the loop current signal sequence and the arc voltage signal sequence are obtained. The loop current signal sequence refers to the change of current during the operation of the load, which reflects the electrical behavior and power demand of the load; the arc voltage signal sequence refers to the change of voltage measured at both ends of the load, which can reveal the existence and characteristics of the arc, because the generation of the arc will cause specific changes in the voltage signal.

[0056] Step S20: extracting an electrical signal sequence to be analyzed that matches a preset time window from the electrical signal sequence, wherein the electrical signal sequence to be analyzed includes a current signal sequence and a voltage signal sequence to be analyzed.

[0057] Specifically, before the analysis, a specific time window has been set. This time window is determined based on the analysis and monitoring requirements of the fault arc characteristics, and it represents the duration of the signal segment extracted from the electrical signal sequence. The electrical signal sequence to be analyzed refers to the part extracted from the entire electrical signal sequence that matches the preset time window. This part of the signal sequence will be used as the object of analysis to detect the characteristics of the fault arc. The current signal sequence to be analyzed is a part of the electrical signal sequence to be analyzed, which specifically represents the current changes within the preset time window. The voltage signal sequence to be analyzed is a part of the electrical signal sequence to be analyzed, which represents the voltage changes within the preset time window.

[0058] Step S30, performing wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical characteristic signal sequence, performing intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical characteristic signal sequence, and performing classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical characteristic signal sequence.

[0059] Specifically, wavelet packet decomposition is a more sophisticated signal processing method that not only decomposes the low-frequency part of the signal, but also further decomposes the high-frequency part. This method can more effectively extract detailed information from the signal. Specifically, the electrical signal sequence to be analyzed is decomposed into multiple sub-bands through wavelet packet transform, and each sub-band contains signal components in different frequency ranges. The decomposed sub-bands are selected and reconstructed to extract specific frequency features, which help to identify the signal characteristics of arc faults. The first electrical characteristic signal sequence is obtained through this process, which contains important time-frequency information of the signal, which is helpful for subsequent fault detection and analysis.

[0060] Intrinsic time scale decomposition is a nonlinear signal processing technique that can decompose signals according to their inherent characteristics and is suitable for time-frequency analysis of non-stationary signals. Specifically, the electrical signal sequence to be analyzed is decomposed into several intrinsic rotation components (PROD) and a trend term, and each PROD component represents a different time scale characteristic of the signal. The decomposed PROD components and trend terms are reconstructed to obtain a second electrical characteristic signal sequence, which can reflect the time scale changes of the signal and is very useful for detecting transient characteristics of arc faults.

[0061] Classical modal decomposition is an adaptive time-frequency analysis technique that can decompose complex signals into a series of intrinsic mode functions (IMFs), each of which represents an inherent vibration mode of the signal. Specifically, the electrical signal sequence to be analyzed is subjected to EMD decomposition to obtain several IMFs and a residual component. The decomposed IMFs are selected and reconstructed to form a third electrical characteristic signal sequence. This sequence can reveal the intrinsic vibration characteristics of the signal and help identify weak signals of arc faults.

[0062] Through these three different decomposition and reconstruction techniques, the method of this embodiment can extract the characteristics of electrical signals from different angles, providing rich characteristic information for subsequent fault detection. These characteristic signal sequences will be used as input data for subsequent similarity measurement and fault detection analysis, thereby improving the accuracy and reliability of detection.

[0063] Step S40, when the load type of the monitored load is unknown, similarity measurement is performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads, and the first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads are input into a pre-trained first probabilistic neural network to obtain the load type of the monitored load.

[0064] Specifically, step S40 is to determine the type of the monitored load by comparing the similarity between the electrical characteristic signal sequence and electrical characteristic sample sequences of multiple preset types of loads when the load type of the monitored load is unknown.

[0065] Similarity measurement is a method for evaluating the similarity between two data sets. In step S40, it is necessary to perform similarity measurement on the three extracted electrical characteristic signal sequences and the electrical characteristic sample sequences of multiple preset types of loads. The similarity measurement can adopt multiple methods, such as Euclidean distance, cosine similarity, correlation coefficient, etc.

[0066] The first electrical characteristic signal sequence (the characteristics obtained by wavelet packet decomposition and reconstruction) is respectively measured for similarity with the first electrical characteristic sample sequences of multiple preset types of loads, so as to obtain first similarity measurement values ​​corresponding to the multiple preset types of loads.

[0067] The second electrical characteristic signal sequence (the characteristic obtained by decomposing and reconstructing the inherent time scale) is respectively measured for similarity with the second electrical characteristic sample sequences of multiple preset types of loads, so as to obtain second similarity measurement values ​​corresponding to the multiple preset types of loads.

[0068] The third electrical characteristic signal sequence (the characteristics obtained by classical modal decomposition and reconstruction) is respectively measured for similarity with the third electrical characteristic sample sequences of multiple preset types of loads to obtain third similarity measurement values ​​corresponding to the multiple preset types of loads.

[0069] The obtained similarity measure value is used as an input feature and input into the pre-trained first probabilistic neural network model. The probabilistic neural network is a neural network based on probability statistics, which is suitable for classification problems, especially when processing uncertainty and probabilistic data. Before implementing step S40, the first probabilistic neural network needs to be trained using electrical feature samples of known load types. During the training process, the network learns how to distinguish different load types based on the input similarity measure value. The first probabilistic neural network outputs the type of monitored load based on the input first, second and third similarity measure values. The result of the network output is based on the pattern recognition ability learned during the training process, and it can identify the load type that best matches the input feature.

[0070] For example, assuming there are n preset types of loads, there are n groups of similarity measurement values, each group of similarity measurement values ​​includes first, second and third similarity measurement values, and the n groups of similarity measurement values ​​are input into the first probabilistic neural network. The first probabilistic neural network will output the probability that the monitored load belongs to the n preset types of loads, and the load type with the highest probability is the identified load type.

[0071] Step S50, when the load type of the monitored load is known, the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence are respectively measured for similarity with the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis are input into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

[0072] Specifically, step S50 is to detect the presence of a DC fault arc by comparing the similarity of the extracted electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the load type when the type of the monitored load is known. In this step, the type of the monitored load has been determined, which means that the electrical characteristic sample sequence related to the specific load type can be used as a reference for fault detection. According to the previous step (e.g., S30), three different electrical characteristic signal sequences have been extracted from the original electrical signal. Next, it is necessary to measure the similarity of these three electrical characteristic signal sequences with the electrical characteristic sample sequence of the known load type to obtain the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis, the purpose of which is to quantify the degree of similarity between the two sequences. The three similarity measurement values ​​obtained will be used as input features and sent to the pre-trained second probabilistic neural network (PNN). This neural network has learned how to distinguish between normal operating state and fault state according to these similarity measurement values ​​during the training process. The second probabilistic neural network will process the input similarity measurement value and output a detection result. This detection result is usually a classification label, which indicates whether the monitored load is in a "normal operating" state or "there is a DC fault arc". If the output indicates "normal operation", the monitored load has not detected a fault arc. If the output indicates "DC fault arc exists", it means that the monitored load may have a fault and further inspection or maintenance measures are required.

[0073] Further, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;

[0074] The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

[0075] Specifically, the first, second and third electrical characteristic signal sequences further include a current characteristic signal sequence and a voltage characteristic signal sequence. Similarly, the electrical characteristic sample sequence corresponding to each preset type of load also includes a current and voltage characteristic sample sequence.

[0076] The first current characteristic signal sequence is a characteristic sequence extracted from the original current signal by wavelet packet decomposition and reconstruction method. It contains key information in the current signal and is used to characterize the current characteristics of the load. The first voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by wavelet packet decomposition and reconstruction method. It reflects the important characteristics of the voltage signal.

[0077] The second current characteristic signal sequence is a characteristic sequence extracted from the original current signal by the intrinsic time scale decomposition and reconstruction method. It provides another perspective of the current signal and may capture information that the wavelet packet decomposition fails to extract. The second voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by the intrinsic time scale decomposition and reconstruction method, and is also used to reveal the characteristics of the voltage signal.

[0078] The third current characteristic signal sequence is a characteristic sequence extracted from the original current signal by the classical modal decomposition and reconstruction method. It provides an additional dimension for the analysis of the current signal. The third voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by the classical modal decomposition and reconstruction method, which further enriches the characteristic information of the voltage signal.

[0079] For each preset type of load, there is a corresponding sequence of electrical characteristic samples, which are recorded when the load is operating normally and used as a reference standard.

[0080] The first current characteristic sample sequence is a sample of the first current characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by wavelet packet decomposition and reconstruction method. The second current characteristic sample sequence is a sample of the second current characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by intrinsic time scale decomposition and reconstruction method. The third current characteristic sample sequence is a sample of the third current characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by classical modal decomposition and reconstruction method.

[0081] The first voltage characteristic sample sequence is a sample of the first voltage characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by wavelet packet decomposition and reconstruction method. The second voltage characteristic sample sequence is a sample of the second voltage characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by intrinsic time scale decomposition and reconstruction method. The third voltage characteristic sample sequence is a sample of the third voltage characteristic signal sequence recorded by the preset type load during normal operation, which is obtained by classical mode decomposition and reconstruction method.

[0082] In step S50, for each preset type of load, the following similarity metric values ​​are calculated respectively:

[0083] A similarity measure between the first current characteristic signal sequence and the corresponding first current characteristic sample sequence.

[0084] A similarity measure between the second current characteristic signal sequence and the corresponding second current characteristic sample sequence.

[0085] A similarity measure between the third current characteristic signal sequence and the corresponding third current characteristic sample sequence.

[0086] A similarity measure between the first voltage characteristic signal sequence and the corresponding first voltage characteristic sample sequence.

[0087] A similarity measure between the second voltage characteristic signal sequence and the corresponding second voltage characteristic sample sequence.

[0088] A similarity measure between the third voltage characteristic signal sequence and the corresponding third voltage characteristic sample sequence.

[0089] These similarity measures will be used as input features and fed into a pre-trained second probabilistic neural network to detect the presence of DC fault arcs. Through this refined feature extraction and comparison, the accuracy and reliability of fault detection can be improved.

[0090] Further, the performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the multiple preset types of loads, further includes:

[0091] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0092] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0093] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0094] Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0095] Specifically, for each similarity metric of a preset type of load, the following six similarity metrics are obtained: a first current similarity metric, a second current similarity metric, a third current similarity metric, a first voltage similarity metric, a second voltage similarity metric, and a third voltage similarity metric. These similarity metrics together constitute a comprehensive evaluation of the similarity of electrical characteristics between the monitored load and the corresponding preset type of load. These metrics are then input into a pre-trained probabilistic neural network to identify the type of the monitored load. Through this detailed comparison and measurement, the load type can be identified more accurately, thereby improving the operation and maintenance efficiency and safety of the electrical system.

[0096] Further, the performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis further includes:

[0097] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0098] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0099] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0100] Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0101] Specifically, similarity measurements are performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load, respectively, to obtain the following six similarity measurement values ​​for fault analysis: a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value. These similarity measurement values ​​together constitute a comprehensive evaluation of the electrical characteristic similarity between the monitored load and the corresponding known type of load. These measurement values ​​are then input into a pre-trained probabilistic neural network to detect whether a DC fault arc exists.

[0102] Furthermore, the step S30 further includes:

[0103] After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

[0104] Specifically, in step S30, in addition to performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to obtain the electrical characteristic signal sequence, further processing of these characteristic signal sequences, namely segmentation and dimensionality reduction, is also included. The first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are segmented into equal-length sub-segments. The length of the sub-segment depends on the total length of the signal and the required resolution. For example, if the original signal sequence has 1000 data points and we decide that each sub-segment contains 100 data points, then the entire sequence will be segmented into 10 equal-length sub-segments. For each sub-segment, the average value of its data points is calculated. The average value is used as the representative value of the sub-segment, which can effectively reduce the dimension of the data. By calculating the average value of each sub-segment, the original electrical characteristic signal sequence is converted into a low-dimensional signal sequence. This low-dimensional sequence contains the key information of the original signal, but the number of data points is greatly reduced. For example, if each original feature signal sequence has 1000 data points, after segmentation and calculation of the average value, the new low-dimensional signal sequence will have only 10 data points (assuming that each sub-segment has 100 data points). Dimensionality reduction can reduce the amount of data for subsequent similarity metric calculations and neural network processing, and improve computational efficiency. By calculating the sub-segment average, the main features of the signal can be highlighted and the impact of noise and details on the analysis can be reduced. Low-dimensional data is easier to analyze and understand, which helps to improve the accuracy of fault detection and load type identification. Through this series of processing, the original electrical signal is converted into a low-dimensional feature signal sequence that is easier to process and analyze, providing effective data input for subsequent fault detection and load type identification.

[0105] See also Figure 2 Another embodiment of the present invention further provides a DC fault arc detection device, comprising:

[0106] A sampling module 1, used for sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence;

[0107] A preprocessing module 2, used for extracting a to-be-analyzed electrical signal sequence that matches a preset time window from the electrical signal sequence, wherein the to-be-analyzed electrical signal sequence includes a to-be-analyzed current signal sequence and a to-be-analyzed voltage signal sequence;

[0108] The feature extraction module 3 is used to perform wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical feature signal sequence, perform intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical feature signal sequence, and perform classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical feature signal sequence;

[0109] A load type identification module 4 is used for, when the load type of the monitored load is unknown, respectively performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement values, second similarity measurement values ​​and third similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads, and inputting the first similarity measurement values, second similarity measurement values ​​and third similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads into a pre-trained first probabilistic neural network to obtain the load type of the monitored load;

[0110] The load fault identification module 5 is used to perform similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load when the load type of the monitored load is known, to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and input the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

[0111] Further, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;

[0112] The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

[0113] Furthermore, the load type identification module 4 is further used to:

[0114] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0115] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0116] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0117] Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0118] Furthermore, the load fault identification module 5 is further used for:

[0119] Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value;

[0120] Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value;

[0121] Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value;

[0122] Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

[0123] Furthermore, the feature extraction module 3 is further used for:

[0124] After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

[0125] It should be noted that the device of this embodiment corresponds to the method of the above embodiment. Therefore, the contents not described in detail in the device of this embodiment can be obtained by referring to the contents of the method of the above embodiment, and will not be repeated in this embodiment.

[0126] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A DC fault arc detection method, characterized in that: The following steps are involved: Sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence; Extracting an electrical signal sequence to be analyzed that matches a preset time window from the electrical signal sequence, wherein the electrical signal sequence to be analyzed includes a current signal sequence and a voltage signal sequence to be analyzed; Performing wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical characteristic signal sequence, performing intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical characteristic signal sequence, and performing classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical characteristic signal sequence; When the load type of the monitored load is unknown, similarity measurement is performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads, and the first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads are input into a pre-trained first probabilistic neural network to obtain the load type of the monitored load; When the load type of the monitored load is known, similarity measurements are performed on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis are input into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

2. The DC fault arc detection method according to claim 1, characterized in that: The first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence; The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

3. The DC fault arc detection method according to claim 2, characterized in that: The method further comprises: performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the multiple preset types of loads. Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value; Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value; Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value; Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

4. The DC fault arc detection method according to claim 2, characterized in that: The performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis further comprises: Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value; Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value; Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value; Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

5. The DC fault arc detection method according to claim 2, characterized in that: The method further comprises: After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

6. A DC fault arc detection device, characterized in that: include: A sampling module, used for sampling the electrical signal of the monitored load according to a preset sampling frequency to obtain an electrical signal sequence, wherein the electrical signal sequence includes a loop current signal sequence and an arc voltage signal sequence; A preprocessing module, used for extracting a to-be-analyzed electrical signal sequence that matches a preset time window from the electrical signal sequence, wherein the to-be-analyzed electrical signal sequence includes a to-be-analyzed current signal sequence and a to-be-analyzed voltage signal sequence; a feature extraction module, configured to perform wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical feature signal sequence, perform intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical feature signal sequence, and perform classical mode decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical feature signal sequence; A load type identification module, for, when the load type of the monitored load is unknown, performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain first similarity measurement value, second similarity measurement value and third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads, respectively, and inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the multiple preset types of loads into a pre-trained first probabilistic neural network to obtain the load type of the monitored load; A load fault identification module is used to perform similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load when the load type of the monitored load is known, to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and input the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a DC fault arc detection result of the monitored load; the DC fault arc detection result is normal operation or the presence of a DC fault arc.

7. The DC fault arc detection device according to claim 6, characterized in that: The first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence; The electrical characteristic sample sequence corresponding to each preset type of load includes a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load is operating normally.

8. The DC fault arc detection device according to claim 7, characterized in that: The load type identification module is further used to: Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first voltage similarity metric value; Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second voltage similarity metric value; Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a third voltage similarity metric value; Among them, the similarity measurement values ​​of the electrical characteristics between the monitored load and the multiple preset types of loads all include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

9. The DC fault arc detection device according to claim 7, characterized in that: The load fault identification module is further used to: Calculating the Euclidean distance between the first current characteristic signal sequence and the first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity metric value; and calculating the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first voltage similarity metric value; Calculating the Euclidean distance between the second current characteristic signal sequence and the second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity metric value; and calculating the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second voltage similarity metric value; Calculating the Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity metric value; and calculating the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third voltage similarity metric value; Among them, the similarity measurement values ​​of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence include a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.

10. The DC fault arc detection method according to claim 7, characterized in that: The feature extraction module is further used for: After performing wavelet packet decomposition and reconstruction, intrinsic time scale decomposition and reconstruction on the electrical signal sequence to be analyzed, and obtaining the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence, the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence are respectively divided into sub-segments of equal length, and then the average value of each sub-segment is calculated to represent each sub-segment accordingly, thereby converting the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence, and the third voltage characteristic signal sequence into low-dimensional signal sequences.

Images