Power transmission line fault identification method and device based on phase-space reconstruction, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power transmission line fault identification method and device based on phase-space reconstruction, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring recording data of three-phase current of a power transmission line; based on preset embedded dimensions and delay time, phase space reconstruction is carried out on the recording data of each phase of current in the three-phase current, and trajectory data of the recording data of each phase of current in a phase space are obtained; performing clustering processing on the trajectory data corresponding to each phase of current to obtain a clustering result corresponding to each phase of current; and determining a fault identification result of the power transmission line based on the clustering result. The method can accurately identify the fault of the power transmission line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system relay protection, and in particular to a power transmission line fault identification method and device based on phase space reconstruction, a computer device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the development of power system relay protection technology, fault diagnosis technology based on fault electrical quantity characteristic analysis has emerged. This technology identifies abnormal system states by monitoring and analyzing changes in line voltage, current and other parameters.

[0003] In traditional technology, the handling of high-resistance ground faults mainly relies on threshold-based identification methods or artificial intelligence-based identification methods. Threshold-based identification methods set reasonable current or voltage thresholds based on long-term operating experience, and determine whether a fault has occurred by comparing real-time monitored electrical quantities with preset thresholds. Artificial intelligence-based identification methods achieve intelligent identification of fault types by training historical fault data models.

[0004] However, the current threshold-based identification method is affected by the complexity of ground faults, and it is difficult to set reliable thresholds with strong applicability, which limits the accuracy of fault identification. The artificial intelligence-based identification method is limited by sample imbalance and complex power grid operating environments, and its accuracy and generalization ability are still insufficient, making it difficult to be widely applied in actual production. SUMMARY

[0005] Therefore, it is necessary to provide a power transmission line fault identification method, device, computer device, computer readable storage medium and computer program product based on phase space reconstruction, which can accurately identify power transmission line faults.

[0006] In a first aspect, the present application provides a power transmission line fault identification method based on phase space reconstruction, comprising:

[0007] Obtaining recorded wave data of three-phase currents of a power transmission line;

[0008] Based on a preset embedding dimension and a delay time, the recorded wave data of each phase current in the three-phase currents is reconstructed in phase space to obtain trajectory data of the recorded wave data of each phase current in the phase space;

[0009] The trajectory data corresponding to each phase current is respectively clustered to obtain a clustering result corresponding to each phase current;

[0010] Based on the clustering result, a fault identification result of the power transmission line is determined.

[0011] In one of the embodiments, the phase space reconstruction is performed on the recorded wave data of each of the three-phase currents based on a preset embedding dimension and a preset delay time, to obtain trajectory data of the recorded wave data of each of the three-phase currents in a phase space, including:

[0012] The time series data of each of the three-phase currents is obtained from the recorded wave data of the three-phase currents.

[0013] The phase space reconstruction is performed on the time series data of each of the three-phase currents based on a preset embedding dimension and a preset delay time, to obtain trajectory data of the recorded wave data of each of the three-phase currents in a phase space.

[0014] In one of the embodiments, the embedding dimension is 2, and the delay time is one fourth of a sampling period.

[0015] In one of the embodiments, the trajectory data of each of the three-phase currents is clustered to obtain a clustering result corresponding to each of the three-phase currents, including:

[0016] The trajectory data is rotated and scaled in the phase space to obtain a plurality of data points.

[0017] The distance between each data point in the plurality of data points and a distribution center of the plurality of data points is calculated.

[0018] The clustering is performed based on the distance to obtain a clustering result corresponding to each of the three-phase currents.

[0019] In one of the embodiments, the clustering result includes a first clustering result and a second clustering result, the first clustering result corresponds to one cluster, and the second clustering result corresponds to two clusters.

[0020] In one of the embodiments, the fault identification result of the power transmission line is determined based on the clustering result, including:

[0021] In a case where the clustering result corresponding to any of the three-phase currents is the second clustering result, it is determined that the fault identification result of the power transmission line is a high-resistance ground fault.

[0022] In a second aspect, the application further provides a power transmission line fault identification device based on phase space reconstruction, including:

[0023] An acquisition module is configured to acquire recorded wave data of three-phase currents of a power transmission line.

[0024] a phase space reconstruction module, configured to perform phase space reconstruction on the recorded wave data of each of the three-phase currents respectively based on a preset embedding dimension and a preset delay time, to obtain trajectory data of the recorded wave data of each of the three-phase currents in a phase space;

[0025] a clustering module, configured to perform clustering processing on the trajectory data corresponding to each of the three-phase currents respectively, to obtain a clustering result corresponding to each of the three-phase currents;

[0026] a fault identification module, configured to determine a fault identification result of the power transmission line based on the clustering result.

[0027] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps of the method according to any one of the preceding aspects.

[0028] In a fifth aspect, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps of the method according to any one of the preceding aspects.

[0029] The power transmission line fault identification method and device based on phase space reconstruction, the computer device, the computer readable storage medium and the computer program product have the following advantages. The recorded wave data of three-phase currents is projected into a high-dimensional phase space defined by an embedding dimension and a delay time through phase space reconstruction. Since the fault current signal, the normal load current and noise signal may overlap or be similar in waveform in a single time dimension, it is difficult to distinguish them. Through phase space reconstruction, the internal differences in geometric structure and dynamic characteristics between the fault signal and the normal signal can be amplified. Then, the trajectory data of each phase current in the phase space is clustered. When a fault occurs, the trajectory data during the fault period will form one or more clusters that are significantly different from the normal state trajectory due to the mutation of its dynamic characteristics. According to the clustering result, the fault can be identified automatically and accurately without presetting a threshold. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0031] Figure 1This is a flowchart illustrating a transmission line fault identification method based on phase space reconstruction in one embodiment.

[0032] Figure 2 This is a flowchart illustrating step S120 in one embodiment;

[0033] Figure 3 This is a flowchart illustrating step S130 in one embodiment;

[0034] Figure 4 This is a flowchart illustrating a transmission line fault identification method based on phase space reconstruction in another embodiment.

[0035] Figure 5 This is a schematic diagram of the three-phase current signal generated by simulation in one embodiment when a high-resistance ground fault occurs in a certain phase of a transmission line;

[0036] Figure 6 To Figure 5 A schematic diagram of the trajectory data obtained by reconstructing the phase space of the current signal of the faulty phase.

[0037] Figure 7 To Figure 5 A schematic diagram of trajectory data obtained by reconstructing the phase space of the current signal in the normal phase.

[0038] Figure 8 To Figure 6 A schematic diagram illustrating the clustering results obtained by clustering trajectory data in the image;

[0039] Figure 9 To Figure 7 A schematic diagram illustrating the clustering results obtained by clustering trajectory data in the image;

[0040] Figure 10 This is a structural block diagram of a transmission line fault identification device based on phase space reconstruction in one embodiment;

[0041] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "a plurality of" used in the present application means two or more. The term "and / or" used in the present application means one of the options or any combination of the options.

[0044] In one embodiment, as shown in Figure 1 A power line fault identification method based on phase space reconstruction is provided. The embodiment is exemplified by applying the method to a terminal. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be realized through the interaction of the terminal and the server. In the embodiment, the method includes the following steps:

[0045] In step S110, the recording wave data of the three-phase current of the power line is obtained.

[0046] Exemplarily, the three-phase current recording wave data of the power line can be collected based on a fault recording device installed on the power line. The three-phase current is usually composed of three sinusoidal currents with the same frequency, equal amplitude and a phase difference of 120°. For example, when a single-phase ground fault occurs in phase A, the fault recording device can record the current waveform data including the process before and after the fault occurs.

[0047] In step S120, the recording wave data of each phase current in the three-phase current is reconstructed in phase space based on a preset embedding dimension and delay time, to obtain the trajectory data of the recording wave data of each phase current in the phase space.

[0048] The embedding dimension and the delay time can be pre-calibrated according to experience or algorithm.

[0049] Exemplarily, the process of reconstructing each phase current in phase space includes: for any phase current sequence, a series of points in phase space is constructed according to the preset embedding dimension and delay time, and the coordinates of each phase space point are composed of current values at different times in the original time sequence. For example, a one-dimensional current sequence with a length of N can be reconstructed into a three-dimensional phase space trajectory containing T points.

[0050] In step S130, the trajectory data corresponding to each phase current is respectively processed by clustering to obtain the clustering result corresponding to each phase current.

[0051] Exemplarily, a clustering algorithm (for example, a K-Means clustering algorithm) can be used to perform clustering analysis on the trajectory data corresponding to the three phases respectively, and a preset clustering number K=2 is used to determine whether the points in the phase space are obviously divided into two different clusters. The two clusters correspond to the normal state and the fault state of the system respectively. In the case of high-resistance ground fault, the three-phase current changes little, and the traditional protection device is difficult to accurately identify. By mapping the current signal to a high-dimensional space through phase space reconstruction, the fault characteristics can be effectively amplified, so that the normal phase and the fault phase show obvious differences in the reconstructed phase space.

[0052] In step S140, the trajectory data corresponding to each phase current is respectively subjected to clustering processing to obtain a clustering result corresponding to each phase current.

[0053] Exemplarily, if the clustering result of a certain phase current is two classes, it is determined that the phase is a fault phase; if the clustering result of a certain phase current is one class, it is determined that the phase is a normal phase. The fault identification result can include single-phase high-resistance ground fault and multi-phase high-resistance ground fault.

[0054] In the above power transmission line fault identification method based on phase space reconstruction, the three-phase current recording data is reconstructed in the phase space, and is projected into a high-dimensional phase space defined by embedding dimension and delay time. Since in a single time dimension, the fault current signal and the normal load current, noise and other signals may overlap or be similar in waveform, it is difficult to distinguish them. Through phase space reconstruction, the internal differences in geometric structure and dynamic characteristics between the fault signal and the normal signal can be amplified. Then, by performing clustering processing on the trajectory data of each phase current in the phase space, since the trajectory data during the fault period will form one or more clusters different from the normal state trajectory due to the mutation of its dynamic characteristics when the fault occurs, according to the clustering result, automatic and accurate fault identification can be achieved without preset threshold.

[0055] In an exemplary embodiment, as shown in Figure 2 The above step S120 can include:

[0056] In step S201, time series data of each phase current in the three-phase current is obtained from the recording data of the three-phase current.

[0057] Exemplarily, the time series data of the three-phase current can be extracted from the recording data, and respectively denoted as , , wherein A, B and C respectively represent the three phases of the power transmission line, and m is the length of the recording data.

[0058] In step S202, the time series data of each phase current is reconstructed in phase space based on the preset embedding dimension and delay time, to obtain trajectory data of the recording wave data of each phase current in the phase space.

[0059] Exemplarily, the reconstructed two-dimensional phase space trajectory X2 can be expressed as follows:

[0060] (1);

[0061] (2);

[0062] (3);

[0063] wherein X Ae , X Be , and X Ce correspond to the reconstructed trajectories of phase A, phase B, and phase C respectively, e is the embedding dimension, d is the sampling point number corresponding to the delay time, and m is the length of the recording wave data. Specifically, each sampling point in the one-dimensional time series is mapped to the two-dimensional phase space for reconstruction, to obtain a two-dimensional vector with the origin as the starting point, and the trajectories of the sequence in the phase space are formed by connecting the ends of all vectors in sequence.

[0064] In this embodiment, the independent time series of each phase current is extracted to ensure the accurate reservation of the fault phase feature; the phase space reconstruction of each phase data based on the preset embedding dimension and delay time can convert the fault characteristics hidden in the one-dimensional waveform into clear and distinguishable trajectory forms in the high-dimensional space, to provide input data with large information quantity and high distinguishability for the clustering analysis.

[0065] In an exemplary embodiment, the embedding dimension is 2 and the delay time is one fourth of the sampling period.

[0066] Specifically, the embedding dimension e is set to 2 and the delay time is set to one fourth of the sampling period, and this parameter combination is suitable for the high-resistance ground fault identification scene after a large number of experiments. At this time, the reconstructed two-dimensional phase space trajectory X2 can be specifically expressed as:

[0067] (4);

[0068] (5);

[0069] (6);

[0070] wherein X A2 , X B2 , and X C2 ​The phase space reconstruction trajectories of the A-phase, the B-phase and the C-phase in the embedding dimension of 2 are not corresponded.

[0071] In an exemplary embodiment, as shown in FIG. 13, Figure 3 The step S130 can include the following steps.

[0072] In step S301, the trajectory data is rotated and scaled in the phase space to obtain a plurality of data points.

[0073] In step S302, the distance between each data point in the plurality of data points and the distribution center of the plurality of data points is calculated.

[0074] In step S303, the clustering processing is performed based on the distance to obtain the clustering result corresponding to the phase.

[0075] Exemplarily, after the trajectory data reconstructed in the phase space is standardized and pretreated, the data point set can be rotated to the principal component direction by the principal component analysis (PCA) method or the like, and scaled to normalize the data distribution. The transformed data points are approximately circularly distributed on a two-dimensional plane, which facilitates subsequent clustering analysis based on distance.

[0076] In this embodiment, by rotating and scaling the trajectory in the phase space, the differences in scale and direction of the trajectory caused by different fault levels or operating conditions are reduced, and the adaptability and robustness of the clustering algorithm to different operating conditions are improved. By calculating the distance of each data point relative to the distribution center, the high-dimensional trajectory form difference is converted into a deviation degree, and clustering is performed based on this distance. The abnormal trajectory points caused by the sudden change of the dynamic characteristics of the fault can be accurately identified, so as to separate the fault state from the normal state. Therefore, the clustering efficiency and the capture ability of the fault characteristics are improved, and the accuracy and reliability of the fault identification result are ensured.

[0077] In an exemplary embodiment, the clustering result can include a first type of clustering result and a second type of clustering result. The clustering number corresponding to the first type of clustering result is 1, and the clustering number corresponding to the second type of clustering result is 2.

[0078] Specifically, for the trajectory data of each phase current, the clustering analysis can be achieved by the following steps: first, the distribution center of all data points in the phase space is calculated, which is the mean point of the coordinates of each data point; then, the Euclidean distance of each data point to the distribution center is calculated to form a distance data set; and then, the distance data set is analyzed by using a density-based clustering algorithm. When the distance distribution of all data points presents a single dense region, it is determined as the first type of clustering result, corresponding to the clustering number of 1, which represents that the phase is operating normally; when the distance distribution is obviously separated into two dense regions, it is determined as the second type of clustering result, corresponding to the clustering number of 2, which represents that the phase has a fault.

[0079] Optionally, a threshold segmentation method can also be used for clustering: first, calculate the Euclidean distance of all data points to the distribution center; then determine the distance threshold, which can be obtained by historical data analysis or adaptive algorithm; then divide the data points with distance less than the threshold into the near-center region, and the data points with distance greater than the threshold into the far-center region; finally, count the data point distribution of the two regions. When the proportion of data points in the far-center region is lower than the set threshold, it is determined as the first type of clustering result; when the proportion of data points in the far-center region is significant and reaches the set threshold, it is determined as the second type of clustering result.

[0080] In an exemplary embodiment, as shown in Figure 4 , the above step S140 can include:

[0081] Step S401, in the case that the clustering result corresponding to any phase current in the three-phase current is the second type of clustering result, determining that the fault identification result of the power transmission line is that there is a high-resistance grounding fault.

[0082] In one possible implementation, please refer to Figures 5 to 9 , Figure 5 for a schematic diagram of the three-phase current signal generated by simulation of a power transmission line when a certain phase of the power transmission line has a high-resistance grounding fault in an embodiment. Among them, the A phase has a 4000Ω high-resistance grounding fault. Figure 6 for a schematic diagram of the trajectory data obtained by phase space reconstruction of the current signal of the fault phase in Figure 5 . Figure 7 for a schematic diagram of the trajectory data obtained by phase space reconstruction of the current signal of the normal phase in Figure 5 . Figure 8 for a schematic diagram of the clustering result obtained by clustering the trajectory data in Figure 6 . Figure 9 for a schematic diagram of the clustering result obtained by clustering the trajectory data in Figure 7 .

[0083] In summary, the above power transmission line fault identification method based on phase space reconstruction, by projecting the three-phase current recording data into a high-dimensional phase space defined by the embedding dimension and the delay time through phase space reconstruction, can amplify the inherent differences in geometric structure and dynamic characteristics between the fault signal and the normal signal, because in a single time dimension, the fault current signal and the normal load current, noise and other signals may have overlapping or similarity in waveform, making it difficult to distinguish. Further, by clustering the trajectory data of each phase current in the phase space, since the trajectory data during the fault will form one or more clusters significantly different from the normal state trajectory due to the mutation of its dynamic characteristics when the fault occurs, according to the clustering result, the fault can be identified automatically and accurately without pre-setting the threshold.

[0084] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other sequences. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of the steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least some of the other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0085] Based on the same inventive concept, the embodiments of the present application also provide a phase space reconstruction-based power transmission line fault identification device for implementing the above-mentioned phase space reconstruction-based power transmission line fault identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more phase space reconstruction-based power transmission line fault identification device embodiments provided below can refer to the limitations of the phase space reconstruction-based power transmission line fault identification method in the above text, which will not be repeated here.

[0086] In one exemplary embodiment, as shown in Figure 10 A phase space reconstruction-based power transmission line fault identification device 500 is provided, comprising: an acquisition module 501, a phase space reconstruction module 502, a clustering module 503, and a fault identification module 504, wherein:

[0087] The acquisition module 501 is configured to acquire recorded wave data of three-phase currents of a power transmission line.

[0088] The phase space reconstruction module 502 is configured to perform phase space reconstruction on the recorded wave data of each phase current in the three-phase currents based on a preset embedding dimension and a delay time, to obtain trajectory data of the recorded wave data of each phase current in the phase space.

[0089] The clustering module 503 is configured to perform clustering processing on the trajectory data corresponding to each phase current, to obtain a clustering result corresponding to each phase current.

[0090] The fault identification module 504 is configured to determine a fault identification result of the power transmission line based on the clustering result.

[0091] In one embodiment, the phase space reconstruction module 502 is further configured to:

[0092] obtain time series data of each phase current in the three-phase current from the recorded wave data of the three-phase current;

[0093] reconstruct a phase space based on a preset embedding dimension and a preset delay time, to obtain trajectory data of the recorded wave data of each phase current in the phase space.

[0094] In one embodiment, the embedding dimension is 2 and the delay time is one fourth of a sampling period.

[0095] In one embodiment, the clustering module 503 is further configured to:

[0096] perform rotation and scaling transformation on the trajectory data in the phase space to obtain a plurality of data points;

[0097] calculate distances between each data point in the plurality of data points and a distribution center of the plurality of data points;

[0098] perform clustering processing based on the distances to obtain a clustering result corresponding to the phase.

[0099] In one embodiment, the clustering result includes a first clustering result and a second clustering result, the first clustering result corresponds to one cluster, and the second clustering result corresponds to two clusters.

[0100] In one embodiment, the fault identification module 504 is further configured to:

[0101] In a case where the clustering result corresponding to any phase current in the three-phase current is the second clustering result, determine that the fault identification result of the power transmission line is that there is a high-resistance ground fault.

[0102] Each module in the power transmission line fault identification device based on phase space reconstruction can be realized by software, hardware, and combinations thereof, in whole or in part. Each module described above can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to each module.

[0103] In one exemplary embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in Figure 11As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the external terminal in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. The computer program is executed by the processor to realize a power transmission line fault identification method based on phase space reconstruction. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0104] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0105] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the above method embodiments.

[0106] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the above method embodiments.

[0107] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in each of the above method embodiments.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0109] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0110] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for power transmission line fault identification based on phase space reconstruction, characterized in that, The method comprises: obtaining recorded wave data of three-phase currents of a power transmission line; based on a preset embedding dimension and delay time, reconstructing phase space for the recorded wave data of each phase current in the three-phase currents respectively to obtain trajectory data of the recorded wave data of each phase current in the phase space; respectively clustering the trajectory data corresponding to each phase current to obtain a clustering result corresponding to each phase current; based on the clustering result, determining a fault identification result of the power transmission line.

2. The method of claim 1, wherein, The method comprises: obtaining recorded wave data of three-phase currents of a power transmission line; based on a preset embedding dimension and delay time, reconstructing phase space for the recorded wave data of each phase current in the three-phase currents respectively to obtain trajectory data of the recorded wave data of each phase current in the phase space; 3. The method according to claim 1 or 2, characterized in that, respectively clustering the trajectory data corresponding to each phase current to obtain a clustering result corresponding to each phase current; 4. The method of claim 1, wherein, based on the clustering result, determining a fault identification result of the power transmission line. The embedding dimension is 2, and the delay time is one fourth of a sampling period. The method comprises: rotating and scaling the trajectory data in the phase space to obtain a plurality of data points; 5. The method according to claim 1 or 4, characterized in that, calculating distances between each data point in the plurality of data points and a distribution center of the plurality of data points; 6. The method of claim 5, wherein, based on the distances, clustering to obtain a clustering result corresponding to a phase. The clustering result comprises a first type of clustering result and a second type of clustering result, the clustering number corresponding to the first type of clustering result is 1, and the clustering number corresponding to the second type of clustering result is 2.

7. A power transmission line fault identification device based on phase space reconstruction, characterized by, The method comprises: in a case where the clustering result corresponding to any phase current in the three-phase currents is the second type of clustering result, determining that the fault identification result of the power transmission line is that there is a high-resistance ground fault. The device comprises: an obtaining module configured to obtain recorded wave data of three-phase currents of a power transmission line; a phase space reconstruction module configured to, based on a preset embedding dimension and delay time, reconstruct phase space for the recorded wave data of each phase current in the three-phase currents respectively to obtain trajectory data of the recorded wave data of each phase current in the phase space; 8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, a clustering module configured to respectively cluster the trajectory data corresponding to each phase current to obtain a clustering result corresponding to each phase current; 9. A computer readable storage medium having stored thereon a computer program, characterized in that, a fault identification module configured to, based on the clustering result, determine a fault identification result of the power transmission line.

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

Images