Signal source classification method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a signal source classification method and device, a nonvolatile storage medium and electronic equipment. The method comprises the steps that a plurality of time domain pulse signals in a target time period are acquired, and the plurality of time domain pulse signals are used for detecting whether the switch cabinet has a fault or not; determining respective time domain features and frequency domain features of the plurality of time domain pulse signals; according to the respective time domain features and frequency domain features of the plurality of time domain pulse signals, generating data points corresponding to the plurality of time domain pulse signals, and obtaining a plurality of data points; clustering the plurality of data points to obtain a plurality of time domain pulse signal groups; and determining signal source types corresponding to the plurality of time domain pulse signal groups, and obtaining the signal source types corresponding to the plurality of time domain pulse signals. The technical problem that the multi-source discharge signal in the switch cabinet cannot be accurately identified is solved.

Description

Technical Field

[0001] The present invention relates to the field of switch cabinet equipment monitoring and fault diagnosis in an electric power system, and in particular to a signal source classification method, device, non-volatile storage medium and electronic equipment. Background Art

[0002] Switchgear equipment plays an important role in the power system, and its operating status has a significant impact on the power supply reliability of the power system. However, since the switchgear equipment may be affected by process limitations, improper handling and other factors during the design, manufacturing, installation and operation and maintenance, as well as external reasons such as lightning overvoltage, dirt, weak insulation, etc., the switchgear equipment often has defects or hidden dangers of varying degrees. These defects and hidden dangers may cause equipment failures, manifested as external insulation to ground flashover breakdown, internal insulation to ground flashover breakdown, phase-to-phase insulation flashover breakdown, bushing flashover breakdown, etc. The occurrence of switchgear equipment failure may have serious consequences. The direct harm is the damage to the switchgear equipment, and the indirect harm may be the damage to the safety and stability of the power grid due to the tripping of the switchgear equipment, and then a power outage may occur, causing losses to users' electricity and the national economy. In the high-frequency current monitoring of the switchgear, environmental interference and multi-source discharge signals are often encountered, making it difficult to distinguish between environmental interference and local discharge and to identify multi-source discharge signals.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a signal source classification method, device, non-volatile storage medium and electronic device to at least solve the technical problem that multi-source discharge signals in a switch cabinet cannot be accurately identified.

[0005] According to one aspect of an embodiment of the present invention, a signal source classification method is provided, including: obtaining multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether there is a fault in a switch cabinet; determining the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals; generating data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals, to obtain multiple data points; clustering the multiple data points to obtain multiple time domain pulse signal groups; determining the signal source type corresponding to each of the multiple time domain pulse signal groups, to obtain the signal source type corresponding to each of the multiple time domain pulse signals.

[0006] Optionally, multiple time domain pulse signals within the target time period are obtained, including: real-time detection of the amplitude of the high-frequency current time domain signal of the switch cabinet within the target time period; starting from multiple moments when the amplitude of the high-frequency current time domain signal is greater than the trigger threshold, capturing the waveform of the high-frequency current time domain signal within a predetermined pulse duration to obtain multiple time domain pulse signals.

[0007] Optionally, multiple data points are clustered to obtain multiple time domain pulse signal groups, including: determining multiple initial groups based on multiple data points; updating the multiple initial groups with the goal of minimizing the distance between data points in the group until a predetermined termination condition is reached, thereby obtaining multiple time domain pulse signal groups.

[0008] Optionally, with the goal of minimizing the distance between data points within the group, multiple initial groupings are updated until a predetermined termination condition is reached to obtain multiple time domain pulse signal groupings, including: determining the distance between every two initial groupings, merging the two initial groupings with the closest distance to obtain the grouping after the first update; updating the grouping after the first update according to the average distance between every two groups in the grouping after the first update until the predetermined termination condition is reached; and determining multiple time domain pulse signal groupings based on the multiple clustering groupings obtained when the predetermined termination condition is reached.

[0009] Optionally, based on multiple cluster groups obtained when a predetermined termination condition is reached, multiple time domain pulse signal groups are determined, including: determining a predetermined termination condition, wherein the predetermined termination condition is that the number of groups obtained by clustering is a specified number; according to the predetermined termination condition, determining multiple cluster groups; according to the multiple cluster groups, determining multiple time domain pulse signal groups.

[0010] Optionally, determine the signal source type corresponding to each of the multiple time domain pulse signal groups to obtain the signal source type corresponding to each of the multiple time domain pulse signals, including: determine the spectra of each of the multiple time domain pulse signal groups to obtain multiple spectra; and determine the signal source type corresponding to each of the multiple spectra based on the characteristics of each of the multiple spectra, that is, the signal source type corresponding to each of the multiple time domain pulse signals.

[0011] According to another aspect of an embodiment of the present invention, a signal source classification device is provided, including: a first acquisition module, used to acquire multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether there is a fault in the switch cabinet; a first determination module, used to determine the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals; a first generation module, used to generate data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals, to obtain multiple data points; a first clustering module, used to cluster the multiple data points, to obtain multiple time domain pulse signal groups; a second determination module, used to determine the signal source type corresponding to each of the multiple time domain pulse signal groups, to obtain the signal source type corresponding to each of the multiple time domain pulse signals.

[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided. The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the signal source classification methods.

[0013] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the signal source classification methods.

[0014] According to yet another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above signal source classification methods is implemented.

[0015] In an embodiment of the present invention, multiple time domain pulse signals are obtained within a target time period, wherein the multiple time domain pulse signals are used to detect whether a switch cabinet has a fault; the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals are determined; data points corresponding to the multiple time domain pulse signals are generated according to the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals, thereby obtaining multiple data points; the multiple data points are clustered to obtain multiple time domain pulse signal groups; the signal source types corresponding to the multiple time domain pulse signal groups are determined, thereby obtaining the signal source types corresponding to the multiple time domain pulse signals. The technical problem that the multi-source discharge signals in the switch cabinet cannot be accurately identified is solved, and the purpose of accurately distinguishing the multi-source discharge signals of the switch cabinet is achieved, thereby achieving the technical effect of improving the efficiency and accuracy of signal source identification of the discharge signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a signal source classification method provided according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of a signal source classification device provided according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to an embodiment of the present invention, a method embodiment of signal source classification is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 is a flow chart of a signal source classification method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0024] Step S102: acquiring a plurality of time domain pulse signals within a target time period, wherein the plurality of time domain pulse signals are used to detect whether a switch cabinet has a fault.

[0025] In this step, in the monitoring and fault diagnosis of the switch cabinet equipment, the monitoring equipment will be used to monitor the high-frequency current signal of the switch cabinet in real time. When the switch cabinet is operating normally, the time domain signal collected by the monitoring equipment is usually stable, continuous, and has clear waveforms. The waveform shows regular periodic changes, and the amplitude and frequency remain basically unchanged. There are no obvious mutations or abnormal fluctuations. When the switch cabinet fails, the time domain signal of the switch cabinet at the time of the failure often shows unstable, irregular, and abnormal changes. Pulse signals may appear, which are manifested as instantaneous mutations or waveform fluctuations of the current. These time domain pulse signals are collected using acquisition equipment.

[0026] In an optional embodiment, multiple time domain pulse signals within a target time period are obtained, including: real-time detection of the amplitude of the high-frequency current time domain signal of the switch cabinet within the target time period; starting from multiple moments when the amplitude of the high-frequency current time domain signal is greater than the trigger threshold, capturing the waveform of the high-frequency current time domain signal within a predetermined pulse duration to obtain multiple time domain pulse signals.

[0027] Optionally, the high-frequency current time domain signal of the switch cabinet is monitored in real time. When a certain fault occurs in the switch cabinet, the monitoring device will detect that the amplitude of the high-frequency current time domain signal is greater than the set trigger threshold. At this time, the acquisition device is triggered to start collecting the time domain signal. This moment corresponds to the moment t0 of the high-frequency current time domain signal. From this moment, the high-frequency current time domain signal that satisfies t-t0<=N is collected until the predetermined pulse duration N is reached. The collection of the time domain signal is terminated. The collected time domain signal is a time domain pulse signal. The switch cabinet is continuously monitored until the monitored high-frequency current time domain signal is greater than the trigger threshold again. The acquisition device is triggered to collect other time domain pulse signals. This process is continued until the preset time period M is reached, and multiple time domain pulse signals are obtained.

[0028] Step S104, determining the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals.

[0029] In this step, the time domain characteristics of each pulse of the time domain pulse signal refers to the time domain analysis of each pulse signal, and the extracted characteristics such as pulse amplitude, pulse width, pulse rise time, pulse fall time, etc. The time domain pulse signal refers to the characteristics of the signal presenting a pulse shape in time, and each pulse represents an instantaneous energy concentration. These time domain characteristics can be used to describe and distinguish the differences between different pulse signals, which is of great significance for signal processing and identification. By analyzing the time domain characteristics of the pulse signal, the characteristics and properties of the signal can be better understood, providing a reference for further signal processing and application. The time domain features in this application include but are not limited to the time domain equivalent amplitude, the time domain equivalent peak value, and the time domain equivalent time constant. The calculation method is as follows:

[0030] (1) Time domain equivalent amplitude Aeq : The time domain equivalent amplitude is used to describe the amplitude characteristics of the signal in the time domain and represents the average amplitude change rate of the signal.

[0031]

[0032] Where T is the total duration of the signal, and x(t) represents the pulse of the signal in the time domain.

[0033] (2) Time domain equivalent peak value P eq : The time domain equivalent peak is used to describe the peak characteristics of the signal in the time domain, indicating the maximum amplitude change rate of the signal.

[0034]

[0035] Among them, T is the total duration of the signal, x(t) represents the pulse of the signal in the time domain, and N represents the duration of the signal.

[0036] (3) Time domain equivalent time constant τ eq : The time domain equivalent time constant is used to describe the response speed of a signal in the time domain, indicating the time it takes for the signal amplitude to change to its initial value.

[0037]

[0038] Where T is the total duration of the signal, and x(t) represents the pulse of the signal in the time domain.

[0039] Frequency domain features refer to a set of characteristic parameters or spectrum information obtained when analyzing these pulse signals in the frequency domain. Frequency domain features include the spectrum diagram of the pulse signal, the main frequency components in the spectrum, the amplitude and phase information of the spectrum, etc. By analyzing the frequency domain characteristics of the time domain pulse signal, we can have a deeper understanding of the frequency distribution characteristics of the signal, so as to process and analyze the signal more accurately. The frequency domain features in this application include frequency domain equivalent energy, frequency domain equivalent concentration, frequency domain equivalent slope, and frequency domain equivalent harmonic richness. The calculation process is as follows: The time domain pulse signal is converted into a signal X(f) in the frequency domain through Fourier transform. The conversion formula is as follows:

[0040]

[0041] Where N is the duration of the signal, f is the frequency, and i is the imaginary unit. Based on the frequency domain signal, the frequency domain characteristics of each pulse can be calculated as follows:

[0042] (1) Frequency domain equivalent energy E eq : Frequency domain equivalent energy is used to describe the energy distribution characteristics of the signal in the frequency domain, indicating the rate of change of the signal's energy with frequency.

[0043]

[0044] Among them, f min and f max T are the lowest and highest frequencies of the signal respectively.

[0045] (2) Frequency domain equivalent concentration C eq : The frequency domain equivalent concentration is used to describe the energy distribution concentration of the signal in the frequency domain.

[0046]

[0047] (3) Frequency domain equivalent slope S eq : The frequency domain equivalent slope is used to describe the speed of change of the signal in the frequency domain.

[0048]

[0049] Among them, f min and f max T are the lowest and highest frequencies in the frequency domain respectively.

[0050] (4) Frequency domain equivalent harmonic richness HR eq : The frequency domain equivalent harmonic richness is used to describe the richness of the harmonic components of the signal in the frequency domain.

[0051]

[0052] Among them, f min and f max T is the lowest and highest frequency in the frequency domain, and X(f) represents the frequency component of the signal in the frequency domain.

[0053] Step S106, generating data points corresponding to the multiple time domain pulse signals respectively according to the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals, thereby obtaining multiple data points.

[0054] In this step, each time-domain pulse signal can be represented by a point in a multidimensional space to facilitate cluster analysis. The dimension of the multidimensional space is determined according to the time-domain characteristics and frequency-domain characteristics of each pulse signal, that is, the number of time-domain characteristics and frequency-domain characteristics is the dimension of the space. If there are three time-domain features and four frequency-domain features, each pulse signal can be regarded as a seven-dimensional data point.

[0055] Step S108, clustering the multiple data points to obtain multiple time domain pulse signal groups.

[0056] In this step, the clustering method used can be a hierarchical clustering method, which includes bottom-up clustering and top-down clustering, and the main difference lies in the order and method of clustering. Bottom-up clustering is a bottom-up method that starts from a single data point and gradually merges similar data points until all data points are merged into one group. Top-down clustering is a top-down method that starts from the whole and gradually subdivides into smaller groups until each data point is independently called a group. Bottom-up clustering methods are usually based on distance or similarity metrics, such as nearest neighbor clustering or average distance clustering. Top-down clustering methods usually use methods such as hierarchical clustering or binary clustering, which can better handle large data sets and high-dimensional data. The bottom-up clustering method is used in this application to calculate the distance between each pair of data points and merge the two nearest data points into one class. Recalculate the distance between the new class and other classes, repeat the above steps until the termination condition is reached, and obtain multiple clustering groups, that is, multiple time domain pulse signal groups.

[0057] In an optional embodiment, multiple data points are clustered to obtain multiple time domain pulse signal groups, including: determining multiple initial groups based on the multiple data points; updating the multiple initial groups with the goal of minimizing the distance between data points in the group until a predetermined termination condition is reached, thereby obtaining multiple time domain pulse signal groups.

[0058] Optionally, a bottom-up hierarchical clustering method is used, each data point is regarded as an initial group, and the distance between each two initial groups is calculated using the Euclidean distance method. The calculation method is:

[0059]

[0060] Among them, x and y are the feature vectors of the sample, and K is the dimension of the feature.

[0061] The distance between each pair of initial groups is calculated, and the two initial groups with the closest distance are merged into a new group to obtain multiple new groups. The distance between the multiple new groups is calculated, and the two new groups with the closest distance are merged again. The process is repeated until the predetermined termination condition is reached, and clustering is stopped to obtain multiple time domain pulse signal groups.

[0062] In an optional embodiment, with the goal of minimizing the distance between data points within the group, multiple initial groups are updated until a predetermined termination condition is reached to obtain multiple time domain pulse signal groups, including:

[0063] Determine the distance between every two initial groups, merge the two initial groups with the closest distance to obtain the first updated group; update the first updated group according to the average distance between every two groups in the first updated group until a predetermined termination condition is reached; determine multiple time domain pulse signal groups based on the multiple cluster groups obtained when the predetermined termination condition is reached.

[0064] Optionally, during the initial grouping, there is only one data point in each group, so the distance between each two data points can be directly calculated, that is, the distance between each two groups, and the two initial groups with the closest distance are merged into a new group to obtain the first updated group. There may be multiple data points in each group after the first update. When calculating the distance between two groups, it is necessary to first calculate the distance between the data points in the first updated group and the data points in other groups, and then calculate the average distance between the two first updated groups. The calculation formula is:

[0065]

[0066] Among them, n i and n j is cluster C i and C j The number of samples in .

[0067] For example, cluster C i There are data points A and B, cluster C j There are data points E and F. The distance a between A and E, the distance b between A and F, the distance c between B and E, and the distance d between B and F are calculated respectively. Then cluster C i and cluster C j The distance between them is: The two groups updated for the first time with the closest average distance are merged into a new group to obtain the group updated for the second time. The group updated for the second time is continuously updated according to the process of updating the group updated for the first time, that is, the average distance between the two groups updated for the second time is calculated, and the two groups updated for the second time with the closest average distance are merged until the preset termination condition is reached and clustering is stopped. At this time, the clustered grouping obtained is the grouping of multiple time domain pulse signals.

[0068] In an optional embodiment, based on multiple cluster groups obtained when a predetermined termination condition is reached, multiple time domain pulse signal groups are determined, including: determining a predetermined termination condition, wherein the predetermined termination condition is that the number of groups obtained by clustering is a specified number; according to the predetermined termination condition, determining multiple cluster groups; according to the multiple cluster groups, determining multiple time domain pulse signal groups.

[0069] Optionally, a predetermined termination condition is determined, that is, when performing cluster analysis, when the number of groups obtained by clustering reaches a preset specified number, the algorithm will stop running. This predetermined termination condition can help avoid infinite loops or over-clustering during the clustering process. For example, if we want to divide a set of data into 5 different groups, we can set this predetermined termination condition to stop running when the number of groups obtained by the algorithm is 5. In this way, the algorithm will end after reaching 5 groups and output the final clustering result, which is a plurality of time domain pulse signal groups.

[0070] Step S110, determining the signal source type corresponding to each of the multiple time domain pulse signal groups, and obtaining the signal source type corresponding to each of the multiple time domain pulse signals.

[0071] It can be understood that in this step, after clustering the collected multiple time domain pulse signals, multiple time domain pulse signal groups are obtained, each group of time domain pulse signals will present relatively similar characteristics, and each type of signal source will also present different characteristics. The signal source type corresponding to each group of time domain pulse signals is determined based on the consistency of the characteristics presented by each group of time domain pulse signals and the signal source type.

[0072] In an optional embodiment, the signal source type corresponding to each of the multiple time domain pulse signal groups is determined to obtain the signal source type corresponding to each of the multiple time domain pulse signals, including: determining the spectra of each of the multiple time domain pulse signal groups to obtain multiple spectra; and determining the signal source type corresponding to each of the multiple spectra based on the characteristics of each of the multiple spectra, that is, the signal source type corresponding to each of the multiple time domain pulse signals.

[0073] Optionally, multiple time-domain pulse signals are grouped and converted into PRPS spectra respectively through a conversion formula, and each group of time-domain pulse signals corresponds to a PRPS spectrum. The conversion formula is:

[0074] phase=(pulse.time%T sample )×360 / T sample

[0075] period=(pulse.time / T sample )%F

[0076] amplitude=max(abs(f(t)))

[0077] Among them, phase, period, and amplitude are the phase, period, and amplitude of the corresponding PRPS spectrum, respectively. f(t) is the corresponding pulse time domain signal. pulse.time is the starting time of the pulse time domain signal. T sampleis a power frequency cycle, and F is the power frequency. The signal source type is identified by the characteristics of each PRPS spectrum to determine the type of signal source.

[0078] Through the above, multiple time domain pulse signals are obtained within the target time period, wherein the multiple time domain pulse signals are used to detect whether there is a fault in the switch cabinet; the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals are determined; according to the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals, the data points corresponding to the multiple time domain pulse signals are generated to obtain multiple data points; the multiple data points are clustered to obtain multiple time domain pulse signal groups; the signal source types corresponding to the multiple time domain pulse signal groups are determined to obtain the signal source types corresponding to the multiple time domain pulse signals. The technical problem that the multi-source discharge signals in the switch cabinet cannot be accurately identified is solved, and the purpose of accurately distinguishing the multi-source discharge signals of the switch cabinet is achieved, thereby achieving the technical effect of improving the efficiency and accuracy of switch cabinet fault detection.

[0079] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation manner.

[0080] Step S1, obtaining multiple time domain pulse signals within the target time period, including: real-time detection of the amplitude of the high-frequency current time domain signal of the switch cabinet within the target time period; starting from multiple moments when the amplitude of the high-frequency current time domain signal is greater than the trigger threshold, capturing the waveform of the high-frequency current time domain signal within a predetermined pulse duration to obtain multiple time domain pulse signals.

[0081] Optionally, the monitoring device can monitor the high-frequency current time domain signal of the switch cabinet in real time. When a certain fault occurs in the switch cabinet, the monitoring device will detect that the amplitude of the high-frequency current time domain signal is greater than the set trigger threshold. At this time, the acquisition device is triggered to start collecting the time domain signal. This moment corresponds to the moment t0 of the high-frequency current time domain signal. From this moment, the high-frequency current time domain signal that satisfies t-t0<=N is collected until the predetermined pulse duration N is reached. The collection of the time domain signal is terminated. The collected time domain signal is a time domain pulse signal. The switch cabinet is continuously monitored until the monitored high-frequency current time domain signal is greater than the trigger threshold again. The acquisition device is triggered to collect other time domain pulse signals. This process continues until the preset time period M is reached, and multiple time domain pulse signals are obtained.

[0082] Step S2, determining the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals.

[0083] Optionally, the time domain characteristics of each pulse of the signal refer to the time domain analysis of each pulse signal, and the extracted characteristics such as pulse amplitude, pulse width, pulse rise time, pulse fall time, etc. The time domain pulse signal refers to the characteristics of the signal presenting a pulse shape in time, and each pulse represents an instantaneous energy concentration. The time domain characteristics in this application include but are not limited to the time domain equivalent amplitude, time domain equivalent peak value, and time domain equivalent time constant. The calculation method is as follows:

[0084] (1) Time domain equivalent amplitude A eq : The time domain equivalent amplitude is used to describe the amplitude characteristics of the signal in the time domain and represents the average amplitude change rate of the signal.

[0085]

[0086] Where T is the total duration of the signal, and x(t) represents the pulse of the signal in the time domain.

[0087] (2) Time domain equivalent peak value P eq : The time domain equivalent peak is used to describe the peak characteristics of the signal in the time domain, indicating the maximum amplitude change rate of the signal.

[0088]

[0089] Among them, T is the total duration of the signal, x(t) represents the pulse of the signal in the time domain, and N represents the duration of the signal.

[0090] (3) Time domain equivalent time constant τ eq : The time domain equivalent time constant is used to describe the response speed of a signal in the time domain, indicating the time it takes for the signal amplitude to change to its initial value.

[0091]

[0092] Where T is the total duration of the signal, and x(t) represents the pulse of the signal in the time domain.

[0093] Frequency domain features refer to a set of characteristic parameters or spectrum information obtained when analyzing these pulse signals in the frequency domain. Frequency domain features include the spectrum diagram of the pulse signal, the main frequency components in the spectrum, the amplitude and phase information of the spectrum, etc. By analyzing the frequency domain characteristics of the time domain pulse signal, we can have a deeper understanding of the frequency distribution characteristics of the signal, so as to process and analyze the signal more accurately. The frequency domain features in this application include frequency domain equivalent energy, frequency domain equivalent concentration, frequency domain equivalent slope, and frequency domain equivalent harmonic richness. The calculation process is as follows: The time domain pulse signal is converted into a signal X(f) in the frequency domain through Fourier transform. The conversion formula is as follows:

[0094]

[0095] Where N is the duration of the signal, f is the frequency, and i is the imaginary unit. Based on the frequency domain signal, the frequency domain characteristics of each pulse can be calculated as follows:

[0096] (1) Frequency domain equivalent energy E eq : Frequency domain equivalent energy is used to describe the energy distribution characteristics of the signal in the frequency domain, indicating the rate of change of the signal's energy with frequency.

[0097]

[0098] Among them, f min and f max T are the lowest and highest frequencies of the signal respectively.

[0099] (2) Frequency domain equivalent concentration C eq : The frequency domain equivalent concentration is used to describe the energy distribution concentration of the signal in the frequency domain.

[0100]

[0101] (3) Frequency domain equivalent slope S eq : The frequency domain equivalent slope is used to describe the speed of change of the signal in the frequency domain.

[0102]

[0103] Among them, f min and f max T are the lowest and highest frequencies in the frequency domain respectively.

[0104] (4) Frequency domain equivalent harmonic richness HR eq : The frequency domain equivalent harmonic richness is used to describe the richness of the harmonic components of the signal in the frequency domain.

[0105]

[0106] Among them, f min and f max T is the lowest and highest frequency in the frequency domain, and X(f) represents the frequency component of the signal in the frequency domain.

[0107] Step S3, generating data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals, to obtain multiple data points.

[0108] Optionally, in order to perform cluster analysis of pulse signals, each time-domain pulse signal can be regarded as a data point in a multidimensional space. The dimension of the multidimensional space depends on the number of time-domain features and frequency-domain features of each pulse signal, that is, the total number of time-domain features and frequency-domain features determines the dimension of the space. For example, if a pulse signal has two time-domain features and two frequency-domain features, then the pulse signal can be represented as a data point in a four-dimensional space.

[0109] Step S4, clustering multiple data points to obtain multiple time domain pulse signal groups, including: determining multiple initial groups based on multiple data points; updating the multiple initial groups with the goal of minimizing the distance between data points in the group until a predetermined termination condition is reached to obtain multiple time domain pulse signal groups.

[0110] Alternatively, a bottom-up hierarchical clustering method can be used to treat each data point as an initial group and use the Euclidean distance method to calculate the distance between each two initial groups. The calculation method is:

[0111]

[0112] Where x and y are the feature vectors of the sample, and K is the dimension of the feature. For example, if the coordinates of the x data point are (6, 5) and the coordinates of the y data point are (4, 3), then the distance between the two data points is:

[0113]

[0114] The distance between each pair of initial groups is calculated, and the two initial groups with the closest distance are merged into a new group to obtain multiple new groups. The distance between the multiple new groups is calculated, and the two new groups with the closest distance are merged again. The process is repeated until the predetermined termination condition is reached, and clustering is stopped to obtain multiple time domain pulse signal groups.

[0115] Step S41, with the goal of minimizing the distance between data points within the group, multiple initial groupings are updated until a predetermined termination condition is reached to obtain multiple time domain pulse signal groupings, including: determining the distance between every two initial groupings, merging the two initial groupings with the closest distance to obtain the grouping after the first update; updating the grouping after the first update according to the average distance between every two groups in the grouping after the first update until the predetermined termination condition is reached; and determining multiple time domain pulse signal groupings based on the multiple clustering groupings obtained when the predetermined termination condition is reached.

[0116] Optionally, during the initial grouping, there is only one data point in each group, so the distance between each two data points can be directly calculated, that is, the distance between each two groups, and the two initial groups with the closest distance are merged into a new group to obtain the first updated group. There may be multiple data points in each group after the first update. When calculating the distance between two groups, it is necessary to first calculate the distance between the data points in the first updated group and the data points in other groups, and then calculate the average distance between the two first updated groups. The calculation formula is:

[0117]

[0118] Among them, n i and n j is cluster C i and C j The number of samples in .

[0119] For example, cluster C i There are data points A, B, C, cluster C j There are data points E and F. The distance a between A and E, the distance b between A and F, the distance c between B and E, the distance d between B and F, the distance e between C and E, and the distance f between C and F are calculated respectively. Then cluster C i and cluster C j The distance between them is: The two groups updated for the first time with the closest average distance are merged into a new group to obtain a group updated for the second time. The group updated for the second time is updated continuously according to the process of updating the group updated for the first time until the preset termination condition is reached and clustering is stopped. At this time, the clustered group obtained is a grouping of multiple time domain pulse signals.

[0120] Step S42, based on the multiple cluster groups obtained when the predetermined termination condition is reached, multiple time domain pulse signal groups are determined, including: determining the predetermined termination condition, wherein the predetermined termination condition is that the number of groups obtained by clustering is a specified number; according to the predetermined termination condition, multiple cluster groups are determined; according to the multiple cluster groups, multiple time domain pulse signal groups are determined.

[0121] Optionally, a predetermined termination condition is determined, that is, when performing cluster analysis, when the number of groups obtained by clustering reaches a preset specified number, the algorithm will stop running. This predetermined termination condition can help avoid infinite loops or over-clustering during the clustering process. For example, if we want to divide a set of data into 5 different groups, we can set this predetermined termination condition to stop running when the number of groups obtained by the algorithm is 5. In this way, the algorithm will end after reaching 5 groups and output the final clustering result, which is a plurality of time domain pulse signal groups.

[0122] Step S5, determining the signal source type corresponding to each of the multiple time domain pulse signal groups, and obtaining the signal source type corresponding to each of the multiple time domain pulse signals, including: determining the spectra of each of the multiple time domain pulse signal groups to obtain multiple spectra; determining the signal source type corresponding to each of the multiple spectra based on the characteristics of each of the multiple spectra, that is, the signal source type corresponding to each of the multiple time domain pulse signals.

[0123] Optionally, multiple time-domain pulse signals are grouped and converted into PRPS spectra respectively through a conversion formula, and each group of time-domain pulse signals corresponds to a PRPS spectrum. The conversion formula is:

[0124] phase=(pulse.time%T sample )×360 / T sample

[0125] period=(pulse.time / T sample )%F

[0126] amplitude=max(abs(f(t)))

[0127] Among them, phase, period, and amplitude are the phase, period, and amplitude of the corresponding PRPS spectrum, respectively. f(t) is the corresponding pulse time domain signal. pulse.time is the starting time of the pulse time domain signal. T sample is a power frequency cycle, and F is the power frequency. The signal source type is identified by the characteristics of each PRPS spectrum to determine the type of signal source.

[0128] The above optional implementation achieves at least the following effects: solves the technical problem of being unable to accurately identify multi-source discharge signals in the switch cabinet, achieves the purpose of accurately distinguishing multi-source discharge signals in the switch cabinet, and further achieves the technical effect of improving the efficiency and accuracy of signal source identification of the discharge signal.

[0129] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0130] In this embodiment, a signal source classification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0131] According to an embodiment of the present invention, there is also provided an apparatus embodiment for implementing a signal source classification method. Figure 2 is a schematic diagram of a signal source classification device according to an embodiment of the present invention. Figure 2 As shown, the signal source classification device includes a first acquisition module 21, a first determination module 22, a first generation module 23, a first clustering module 24, and a second determination module 25. The device is described below.

[0132] The first acquisition module 21 is used to acquire multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether the switch cabinet has a fault.

[0133] The first determination module 22 is connected to the first acquisition module 21 and is used to determine the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals.

[0134] The first generating module 23 is connected to the first determining module 22, and is used to generate data points corresponding to the multiple time domain pulse signals respectively according to the time domain characteristics and frequency domain characteristics of the multiple time domain pulse signals, so as to obtain multiple data points.

[0135] The first clustering module 24 is connected to the first generating module 23 and is used to cluster multiple data points to obtain multiple time domain pulse signal groups.

[0136] The second determination module 25 is connected to the first clustering module 24 and is used to determine the signal source type corresponding to each of the multiple time-domain pulse signal groups, and obtain the signal source type corresponding to each of the multiple time-domain pulse signals.

[0137] In a signal source classification device provided by an embodiment of the present invention, a first acquisition module is set to acquire multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether there is a fault in the switch cabinet; a first determination module is used to determine the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals; a first generation module is used to generate data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals, and obtain multiple data points; a first clustering module is used to cluster multiple data points to obtain multiple time domain pulse signal groups; a second determination module is used to determine the signal source type corresponding to each of the multiple time domain pulse signal groups, and obtain the signal source type corresponding to each of the multiple time domain pulse signals. The technical problem that the multi-source discharge signal in the switch cabinet cannot be accurately identified is solved, and the purpose of accurately distinguishing the multi-source discharge signal of the switch cabinet is achieved, thereby achieving the technical effect of improving the efficiency and accuracy of signal source identification of the discharge signal.

[0138] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0139] It should be noted that the first acquisition module 21, the first determination module 22, the first generation module 23, the first clustering module 24, and the second determination module 25 correspond to steps S102 to S110 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the modules as part of the device can be run in a computer terminal.

[0140] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0141] The above-mentioned signal source classification device may also include a processor and a memory. The first acquisition module 21, the first determination module 22, the first generation module 23, the first clustering module 24, the second determination module 25, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0142] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0143] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a signal source classification method is implemented.

[0144] like Figure 3 As shown, an embodiment of the present invention provides an electronic device, the electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: the memory is used to store a computer program, wherein when the computer program is executed by the processor, the processor implements the above-mentioned signal source classification method. The device in this article may be a server, a PC, etc.

[0145] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: computer instructions are executed by a processor to perform the above-mentioned signal source classification method.

[0146] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0150] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0151] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0152] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0153] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0154] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0155] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A signal source classification method, characterized in that: include: Acquire multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether a switch cabinet has a fault; Determining the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals; Generating data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals to obtain multiple data points; Clustering the multiple data points to obtain multiple time-domain pulse signal groups; The signal source types corresponding to each of the multiple time-domain pulse signal groups are determined to obtain the signal source types corresponding to each of the multiple time-domain pulse signals.

2. The method according to claim 1, characterized in that The step of acquiring a plurality of time domain pulse signals within a target time period includes: Real-time detection of the amplitude of the high-frequency current time domain signal of the switch cabinet within the target time period; Starting from multiple moments when the amplitude of the high-frequency current time domain signal is greater than a trigger threshold, the waveform of the high-frequency current time domain signal within a predetermined pulse duration is captured to obtain the multiple time domain pulse signals.

3. The method according to claim 1, characterized in that The clustering of the multiple data points to obtain multiple time domain pulse signal groups includes: determining a plurality of initial groups based on the plurality of data points; With the goal of minimizing the distance between data points within the group, the multiple initial groups are updated until a predetermined termination condition is reached, thereby obtaining the multiple time-domain pulse signal groups.

4. The method according to claim 3, characterized in that The method of updating the multiple initial groups with the goal of minimizing the distance between data points within the group until a predetermined termination condition is reached to obtain the multiple time domain pulse signal groups includes: Determine the distance between each two initial groups, merge the two initial groups with the closest distance, and obtain the first updated group; updating the first updated groups according to the average distance between every two groups in the first updated groups until the predetermined termination condition is reached; The multiple time-domain pulse signal groups are determined based on the multiple cluster groups obtained when the predetermined termination condition is reached.

5. The method according to claim 4, characterized in that The determining the multiple time-domain pulse signal groups based on the multiple cluster groups obtained when the predetermined termination condition is reached includes: Determining the predetermined termination condition, wherein the predetermined termination condition is that the number of groups obtained by the clustering is a specified number; Determining the plurality of cluster groups according to the predetermined termination condition; The multiple time-domain pulse signal groups are determined according to the multiple cluster groups.

6. The method according to claim 1, characterized in that The determining the signal source type corresponding to each of the plurality of time domain pulse signal groups to obtain the signal source type corresponding to each of the plurality of time domain pulse signals comprises: Determine the spectra of each of the multiple time-domain pulse signal groups to obtain multiple spectra; According to the respective characteristics of the multiple spectrograms, the signal source types corresponding to the multiple spectrograms are determined, that is, the signal source types corresponding to the multiple time-domain pulse signals.

7. A signal source classification device, characterized in that: include: A first acquisition module is used to acquire multiple time domain pulse signals within a target time period, wherein the multiple time domain pulse signals are used to detect whether the switch cabinet has a fault; A first determination module, used to determine the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals; A first generating module, configured to generate data points corresponding to each of the multiple time domain pulse signals according to the time domain characteristics and frequency domain characteristics of each of the multiple time domain pulse signals, thereby obtaining multiple data points; A first clustering module, used for clustering the plurality of data points to obtain a plurality of time-domain pulse signal groups; The second determination module is used to determine the signal source type corresponding to each of the multiple time domain pulse signal groups, and obtain the signal source type corresponding to each of the multiple time domain pulse signals.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the signal source classification method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the signal source classification method described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by a processor to execute the signal source classification method according to any one of claims 1 to 6.

Images