Medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing

Abstract

The invention provides a medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing, and belongs to the technical field of cable monitoring, and the method comprises the steps: employing electromagnetic sensing nodes disposed in a multi-voltage power supply network to synchronously collect an initial traveling wave response signal, extracting the traveling wave characteristic index, and calculating the traveling wave characteristic index of the initial traveling wave response signal; identifying the traveling wave characteristic indexes according to the difference characteristic template, and determining a first traveling wave boundary used for representing and distinguishing the low-voltage cable area and the medium-voltage cable area and a second traveling wave boundary used for representing and distinguishing the medium-voltage cable area and the high-voltage cable area; and marking a medium-voltage cable area by using the first traveling wave boundary and the second traveling wave boundary, after marking a medium-voltage electromagnetic sensing node corresponding to the medium-voltage cable area, receiving a real-time traveling wave response signal transmitted by the medium-voltage electromagnetic sensing node, and carrying out single-phase earth fault monitoring on the medium-voltage cable area according to the real-time traveling wave response signal. And outputting a monitoring early warning signal.

Description

Technical Field

[0001] The present application relates to the technical field of cable monitoring, and in particular to a distributed monitoring method for medium-voltage cables based on electromagnetic traveling wave sensing. Background Art

[0002] As medium-voltage distribution networks continue to grow in size and complexity, the operational status of cables, a crucial vehicle for power transmission, directly impacts power supply reliability. Medium-voltage cables are typically laid underground, interwoven with high- and low-voltage cables. These cables create complex and difficult-to-identify routes. Long-term operation in complex environments makes them susceptible to factors such as insulation aging, mechanical damage, and partial discharge, leading to single-phase grounding faults. Failure to provide timely monitoring and early warning can lead to even more serious power outages.

[0003] Currently, traditional cable monitoring methods rely primarily on partial discharge detection, infrared temperature measurement, or impedance measurement, often suffering from limited monitoring range, weak anti-interference capabilities, and difficulty in achieving distributed positioning. Existing traveling wave monitoring technologies are mostly applied to high-voltage transmission lines. However, due to the diverse voltage levels and complex topology of medium-voltage cable networks, the propagation characteristics of traveling wave signals differ significantly from those of high-voltage lines. In multi-voltage power supply networks (such as mixed low-voltage, medium-voltage, and high-voltage areas), the propagation paths of traveling wave signals are complex, with significant boundary reflections and attenuation effects. This poses challenges in accurately extracting and zoning fault traveling wave signals, making traditional methods difficult to directly apply. This, in turn, hinders the rapid location and accurate early warning of single-phase grounding faults in medium-voltage cables. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical deficiencies, especially the technical deficiencies in the prior art that affect the rapid location and accurate early warning of single-phase grounding faults in medium-voltage cables.

[0005] In a first aspect, the present application provides a method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing, the method comprising:

[0006] The initial traveling wave response signal is synchronously collected using electromagnetic sensor nodes deployed in a multi-voltage power supply network;

[0007] Extracting traveling wave characteristic indicators of the initial traveling wave response signal, identifying the traveling wave characteristic indicators according to a pre-constructed difference feature template, and determining a first traveling wave boundary and a second traveling wave boundary, wherein the first traveling wave boundary is used to represent the transition boundary that distinguishes the low-voltage cable area from the medium-voltage cable area, and the second traveling wave boundary is used to represent the transition boundary that distinguishes the medium-voltage cable area from the high-voltage cable area;

[0008] Using the first traveling wave boundary and the second traveling wave boundary to mark the medium voltage cable area, and marking the medium voltage electromagnetic sensor node corresponding to the medium voltage cable area;

[0009] Receive the real-time traveling wave response signal transmitted by the medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, monitor the single-phase grounding fault in the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring early warning signal.

[0010] In one embodiment, the process of constructing the difference feature template includes:

[0011] Under each pre-established excitation test condition, a plurality of traveling wave response signal samples synchronously collected by the electromagnetic sensor nodes are obtained, wherein the plurality of traveling wave response signal samples include traveling wave response signals obtained by testing a multi-voltage power supply network at different voltage levels;

[0012] Identifying traveling wave characteristic index samples of traveling wave response signal samples, the traveling wave characteristic index samples including frequency spectrum characteristics, propagation velocity characteristics and amplitude attenuation characteristics;

[0013] According to the difference in feature distribution extracted from the traveling wave feature index samples, a difference feature template is determined.

[0014] In one embodiment, the process of constructing the difference feature template further includes:

[0015] Acquiring at least one abnormal excitation test condition, the abnormal excitation test condition including a single-phase ground fault condition;

[0016] Under abnormal excitation test conditions, obtain high-voltage traveling wave response signal samples in the high-voltage cable area, medium-voltage traveling wave response signal samples in the medium-voltage cable area, and low-voltage traveling wave response signal samples in the low-voltage cable area in the multi-voltage power supply network;

[0017] Analyze the traveling wave abnormal characteristic index samples of the high-pressure traveling wave response signal samples, the low-pressure traveling wave response signal samples, and the medium-pressure traveling wave response signal samples;

[0018] A feature comparison is performed based on the traveling wave anomaly feature index sample and the traveling wave feature index sample to obtain a discriminative enhancement feature, and the difference feature template is updated according to the discriminative enhancement feature.

[0019] In one embodiment, the step of updating the difference feature template according to the distinguishing enhancement feature includes:

[0020] A boundary enhancement feature set for distinguishing voltage levels is constructed using discriminative enhancement features, which include spectrum stretching interval features, propagation velocity step features, and reflection amplitude change features.

[0021] According to the boundary enhancement feature set and the traveling wave anomaly feature index samples, the classification model is trained, and the output results of the trained classification model are used to update the difference feature template.

[0022] In one embodiment, the step of determining the first traveling wave boundary and the second traveling wave boundary comprises:

[0023] The difference feature template is used to identify the characteristic index of the traveling wave and obtain the characteristic mutation area;

[0024] After calculating the gradient change rate of each mutation point in the characteristic mutation area, the first characteristic mutation point is selected as the first traveling wave boundary, and the second characteristic mutation point is selected as the second traveling wave boundary, wherein the gradient change rates of the first characteristic mutation point and the second characteristic mutation point are both greater than the preset threshold, the gradient change rate of the first characteristic mutation point is the largest, and the gradient change rate of the second characteristic mutation point is second to the gradient change rate of the first characteristic mutation point.

[0025] In one embodiment, the step of performing single-phase ground fault monitoring on a medium voltage cable area according to a real-time traveling wave response signal and outputting a monitoring warning signal includes:

[0026] A single-phase grounding fault template model is constructed, and the signal feature matching of the real-time traveling wave response signal is performed using the single-phase grounding fault template model to output a single-phase grounding fault score.

[0027] If the single-phase grounding fault score is greater than the preset fault threshold, the real-time traveling wave response signal is analyzed, the single-phase grounding fault location coordinates in the medium-voltage cable area are extracted, and a monitoring warning signal is output according to the single-phase grounding fault location coordinates.

[0028] In one embodiment, the step of analyzing the real-time traveling wave response signal to extract the location coordinates of the single-phase grounding fault in the medium voltage cable area includes:

[0029] Analyze the traveling wave timestamps of the real-time traveling wave response signal and calculate the wave head arrival time difference sequence;

[0030] After obtaining the layout path of the medium-voltage cable area, analyze the wave head arrival time difference series to predict the wave speed propagation data;

[0031] The traveling wave attenuation factor is introduced to correct the wave velocity propagation data and obtain the single-phase grounding fault location coordinates.

[0032] In a second aspect, the present application provides a medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing, the device comprising:

[0033] An initial traveling wave response signal acquisition module is used to synchronously acquire the initial traveling wave response signal using electromagnetic sensor nodes arranged in a multi-voltage power supply network;

[0034] A traveling wave boundary determination module is used to extract traveling wave characteristic indicators of the initial traveling wave response signal, identify the traveling wave characteristic indicators according to a pre-constructed difference feature template, and determine a first traveling wave boundary and a second traveling wave boundary, wherein the first traveling wave boundary is used to represent the transition boundary between the low-voltage cable area and the medium-voltage cable area, and the second traveling wave boundary is used to represent the transition boundary between the medium-voltage cable area and the high-voltage cable area;

[0035] A medium voltage cable area marking module is used to mark the medium voltage cable area using the first traveling wave boundary and the second traveling wave boundary, and mark the medium voltage electromagnetic sensor node corresponding to the medium voltage cable area;

[0036] The detection and warning signal output module is used to receive the real-time traveling wave response signal transmitted by the medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, monitor the single-phase grounding fault in the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring and warning signal.

[0037] In a third aspect, the present application provides a storage medium: the storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing as described in any one of the above embodiments.

[0038] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;

[0039] The memory stores computer-readable instructions, which, when executed by one or more processors, execute the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing in any one of the above embodiments.

[0040] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0041] The distributed monitoring method for medium-voltage cables based on electromagnetic traveling wave sensing provided by the present application, by deploying electromagnetic sensor nodes in a multi-voltage power supply network, synchronously collecting initial traveling wave response signals, and identifying traveling wave characteristic indicators based on pre-built difference feature templates, accurately determines the first traveling wave boundary between the low-voltage cable area and the medium-voltage cable area, and the second traveling wave boundary between the medium-voltage cable area and the high-voltage cable area, thereby achieving accurate division and marking of the medium-voltage cable area, and effectively solving the problems of complex cable laying, difficult path identification, and easy signal attenuation and reflection in the medium-voltage distribution network, resulting in large monitoring errors. Furthermore, by utilizing the real-time traveling wave response signals collected by the marked medium-voltage electromagnetic sensor nodes, real-time monitoring and accurate early warning of single-phase grounding faults in the medium-voltage cable are carried out, and monitoring and early warning signals are output in a timely manner, which can achieve rapid detection and accurate positioning of faults, improve the coverage and response speed of monitoring, and significantly enhance the reliability and safety of power supply. In summary, the method of the present application overcomes the defects of traditional partial discharge detection, infrared temperature measurement and impedance measurement methods, such as limited monitoring range, weak anti-interference ability, and difficulty in achieving distributed positioning, and realizes the rapid positioning and accurate early warning of single-phase grounding faults in medium-voltage cables. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A flow chart of a method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing provided in an embodiment of the present application;

[0044] Figure 2 A schematic structural diagram of a medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] This application provides a method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing. The following embodiments are described using the method applied to computer equipment as an example. It is understood that the computer equipment can be any device with data processing capabilities, including but not limited to a single server, a server cluster, a personal laptop computer, a desktop computer, etc. Figure 1 As shown, the method includes:

[0048] S101: Synchronously collect initial traveling wave response signals using electromagnetic sensor nodes deployed in a multi-voltage power supply network.

[0049] A multi-voltage power supply network refers to a cable distribution system that includes multiple voltage levels, including low voltage (LV), medium voltage (MV), and high voltage (HV). It is typically used to accommodate diverse power demands and transmission and distribution scenarios. Electromagnetic sensor nodes are high-frequency electromagnetic sensors installed at key cable nodes (such as branch connection points, joints, and terminal substations). They detect transient traveling wave signals caused by external disturbances or internal faults in the cable line. Traveling wave response signals are high-frequency voltage or current waveforms that propagate through the cable following a fault, partial discharge, sudden load change, or operational disturbance. They reflect transient changes in the cable's state. Synchronous data acquisition ensures that all electromagnetic sensor nodes collect data based on the same time reference through high-precision time synchronization mechanisms (such as GPS clocks or the PTP precision clock protocol). This eliminates positioning errors caused by time deviations in data acquisition and improves the accuracy of subsequent analysis.

[0050] Specifically, the computer device can establish a communication connection with multiple electromagnetic sensor nodes deployed on a multi-voltage power supply network. The computer device can be equipped with a central processing unit (CPU), cache, timing control module, and high-precision clock module to coordinate the synchronous startup and data reception operations of all electromagnetic sensor nodes. Before the fault detection task begins, the computer device can issue a synchronization acquisition instruction to all electromagnetic sensor nodes. The instruction contains parameters such as timestamp, sampling frequency, and sampling duration, ensuring that each node begins data acquisition according to the unified timing requirements.

[0051] Next, after receiving the synchronous acquisition instruction, each electromagnetic sensor node uses its built-in high-precision clock to perform local timing, initiates high-frequency sampling of the transient traveling wave response signal at a predetermined time point, and uploads the raw signal data, including waveform, amplitude, arrival time, phase, and other characteristic information, to the computer device in real time or in batches. After receiving the data, the computer device can first perform timing alignment on the signal, verifying the timestamp and acquisition order of the data at each node to construct a complete traveling wave response time series.

[0052] Furthermore, computer equipment can perform denoising processing based on the collected traveling wave response signals, such as using wavelet transform, median filtering and other methods to eliminate irrelevant interference such as background power frequency disturbances and transient noise of switching operations; at the same time, it can extract key characteristic indicators of each node signal, such as peak value, order of wave arrival, frequency domain characteristics, etc., to provide accurate input for fault location, area division and boundary extraction.

[0053] It is understandable that due to the complex laying environment of medium-voltage cable lines, the interlaced paths, and the signals being easily affected by various factors such as attenuation and reflection, the use of electromagnetic sensor nodes for synchronous data collection can ensure that the data of each node is obtained under the same time reference, which helps to accurately restore the propagation path and characteristic changes of the traveling wave, and avoid positioning offset or misjudgment due to time deviation.

[0054] S102: Extract the traveling wave characteristic indicators of the initial traveling wave response signal, identify the traveling wave characteristic indicators according to a pre-constructed difference feature template, and determine the first traveling wave boundary and the second traveling wave boundary, wherein the first traveling wave boundary is used to represent the transition boundary that distinguishes the low-voltage cable area from the medium-voltage cable area, and the second traveling wave boundary is used to represent the transition boundary that distinguishes the medium-voltage cable area from the high-voltage cable area.

[0055] Among them, traveling wave characteristic indicators refer to physical characteristic parameters used to quantify the differences in traveling wave response signals in cables, including but not limited to the rise time, amplitude, polarity, main frequency component, energy distribution, propagation speed, attenuation of the traveling wave head, and the modal characteristics of multimode cables (such as the ratio of zero mode and line mode energy after phase mode conversion). These characteristics are used to reflect the signal propagation characteristics of cables of different voltage levels. Differential characteristic templates refer to a set of pre-defined rules for classifying and distinguishing traveling wave characteristics based on the physical structure of cables of different voltage levels (such as insulation layer thickness, capacitance, inductance, impedance, etc.) and experimental simulation results. The first traveling wave boundary refers to the transition boundary that can characterize the transition of traveling wave characteristics between the low-voltage cable area and the medium-voltage cable area. The second traveling wave boundary refers to the transition boundary that can characterize the transition of traveling wave characteristics between the medium-voltage cable area and the high-voltage cable area.

[0056] Specifically, after receiving the initial traveling wave response signal uploaded by each electromagnetic sensor node, the computer device can first preprocess the original traveling wave signal, including filtering and noise reduction, normalization and time alignment of the signal to ensure the accuracy and stability of feature extraction.

[0057] Next, the computer extracts the characteristic indicators of the traveling wave based on time-domain and frequency-domain analysis methods. Time-domain analysis involves measuring the rise time, peak amplitude, and polarity change of the traveling wave head. Frequency-domain analysis uses fast Fourier transforms (FFTs) or wavelet transforms to extract indicators such as the main frequency component, frequency band energy distribution, and spectral center. For multi-conductor cables, the computer can also convert phase-mode signals into zero-mode or line-mode signals to further extract modal characteristics.

[0058] Subsequently, the computer device compares the extracted traveling wave characteristic indicators with the difference characteristic templates pre-stored in the database. The difference characteristic templates contain characteristic thresholds for low-voltage, medium-voltage and high-voltage cables. For example, the rise time threshold of the low-voltage cable is less than a preset value, and the high-frequency component is lower than a certain energy ratio. When the comparison results show that the traveling wave characteristics gradually transition from low-voltage characteristics to medium-voltage characteristics, the computer device can automatically determine that this is the first traveling wave boundary; when the traveling wave characteristics further transition from medium-voltage characteristics to high-voltage characteristics, it is marked as the second traveling wave boundary. Among them, the low-voltage characteristics can be rapid attenuation and high-frequency loss, the medium-voltage characteristics can be stable propagation and high-frequency retention, and the high-voltage characteristics can be low-speed propagation and low-frequency dominance.

[0059] Understandably, due to significant differences in structure, electrical parameters, and insulation properties among cables of different voltage levels, traveling waves exhibit unique rise times, frequency-domain energy distribution, and attenuation characteristics during propagation. By performing feature extraction and comparing identification with differential feature templates using computer equipment, not only can the low-voltage, medium-voltage, and high-voltage regions of the cable be effectively distinguished, and the first and second traveling wave boundaries automatically determined, but the accuracy and stability of traveling wave boundary identification can also be improved, ensuring the precision and reliability of regional monitoring and fault location.

[0060] S103: Marking a medium-voltage cable area using the first traveling wave boundary and the second traveling wave boundary, and marking a medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area.

[0061] Among them, the medium-voltage cable area refers to the cable section corresponding to the two boundaries, which belongs to the medium-voltage cable section with a voltage level in the range of 10~35kV; the medium-voltage electromagnetic sensor node refers to a high-frequency electromagnetic sensing device deployed inside the medium-voltage cable area and used to collect the traveling wave response signal of the cable in this area. Its physical location is between the first traveling wave boundary and the second traveling wave boundary.

[0062] Specifically, the computer device can perform a region marking operation on the cable topology diagram based on the spatial coordinates of the first and second wave boundaries. Preferably, the cable topology diagram is an electronic structure file in a known format, such as a GIS coordinate map or a CAD topology map, which stores the physical path information and length data of each cable segment. The computer device can mark boundary points on the topology diagram and automatically calculate the distance segment between the two boundary points. For example, if the first boundary is located 100 meters from the cable starting point and the second boundary is located 500 meters, the 100-500 meter area is automatically demarcated as the medium-voltage cable zone.

[0063] Next, the computer enters the node screening process. It retrieves all registered electromagnetic sensor nodes and their location information, determining whether each node's coordinates lie within the medium-voltage cable range. Nodes that meet the criteria are marked as medium-voltage electromagnetic sensor nodes and their IDs are added to the medium-voltage monitoring node whitelist. Low-voltage or high-voltage nodes outside this area can also be excluded from the traveling wave acquisition task.

[0064] Understandably, due to the significant differences in structure, electrical parameters, and signal response characteristics between low-voltage, medium-voltage, and high-voltage cables, mixing sensor data from non-target voltage levels into medium-voltage cable fault detection can easily introduce interference signals, leading to misjudgments or missed detections. Therefore, using computer equipment to precisely delineate the medium-voltage cable area based on identified traveling wave boundaries, and screening out electromagnetic sensor nodes within that area, retaining only valid signals from the medium-voltage section for analysis, can significantly improve the targetedness and accuracy of fault detection. This method also effectively reduces computing resource consumption, avoids processing redundant data, and improves real-time monitoring efficiency.

[0065] S104: Receive a real-time traveling wave response signal transmitted by a medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, perform single-phase grounding fault monitoring on the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring warning signal.

[0066] The real-time traveling wave response signal refers to the transient voltage / current waveform signal collected by the medium-voltage electromagnetic sensor nodes within the medium-voltage cable area during the monitoring process with millisecond or even microsecond resolution. It is used to reflect transient events occurring in the cable. Single-phase grounding fault monitoring refers to the detection of abnormal discharge or short circuit between a single-phase conductor of a medium-voltage cable and the ground based on the characteristics of the traveling wave signal. The monitoring warning signal is the alarm information output by computer equipment after analyzing the real-time traveling wave data. It usually contains the fault type, location, time of occurrence, and recommended disposal measures, which are used to alert maintenance personnel or automatically trigger subsequent protection actions.

[0067] Specifically, the computer first establishes a high-speed data communication link with the medium-voltage electromagnetic sensor nodes marked within the medium-voltage cable area, such as a fiber optic network, 5G, or dedicated wireless link, to support low-latency transmission of real-time data streams. The computer continuously receives real-time traveling wave response signals uploaded by each medium-voltage node and automatically classifies and aligns the data based on node ID and timestamp, generating a complete multi-node traveling wave response matrix.

[0068] The computer then extracts multi-dimensional features from the real-time traveling wave response signal, including but not limited to wave arrival time difference, phase offset, abnormal waveform amplitude changes, and frequency domain energy distribution variations, to identify the unique traveling wave pattern of a single-phase grounding fault. Furthermore, the computer combines the traveling wave propagation velocity with the physical location coordinates of the nodes to perform fault location calculations based on the multi-node time difference method, accurately determining the spatial position of the fault point in the cable.

[0069] Furthermore, after confirming and locating the fault characteristics, the computer equipment generates a monitoring warning signal based on the preset fault identification threshold. This warning signal can be pushed to the operation and maintenance platform in real time, triggering an audible and visual alarm or automatically switching the grid protection logic. Simultaneously, the warning history data can be recorded and a detailed fault report generated for subsequent analysis and maintenance decision-making.

[0070] As can be understood, single-phase grounding faults manifest as high-frequency, rapidly propagating transient traveling wave signals in medium-voltage cables. Computer equipment, by receiving real-time traveling wave response signals from medium-voltage electromagnetic sensor nodes and performing feature extraction and fault location analysis based on multi-node information, can not only promptly detect single-phase grounding anomalies in cables but also precisely locate the fault, effectively shortening troubleshooting time. Furthermore, by outputting monitoring and early warning signals, it can promptly alert operations and maintenance personnel or automatically trigger subsequent protective measures, thereby reducing the risk of accidents escalating and ensuring the safe and stable operation of the power grid.

[0071] In the above embodiment, by deploying electromagnetic sensor nodes in a multi-voltage power supply network, synchronously collecting initial traveling wave response signals, and identifying traveling wave characteristic indicators based on pre-constructed difference feature templates, the first traveling wave boundary between the low-voltage cable area and the medium-voltage cable area, as well as the second traveling wave boundary between the medium-voltage cable area and the high-voltage cable area, is accurately determined. This achieves accurate division and marking of the medium-voltage cable area, effectively solving the problems of complex cable laying, difficult path identification, and easy signal attenuation and reflection in the medium-voltage distribution network, resulting in large monitoring errors. Furthermore, by using the real-time traveling wave response signals collected by the marked medium-voltage electromagnetic sensor nodes, real-time monitoring and accurate early warning of single-phase grounding faults in the medium-voltage cable are performed, and monitoring and early warning signals are output in a timely manner. This enables rapid detection and accurate positioning of faults, improves monitoring coverage and response speed, and significantly enhances power supply reliability and safety. In summary, the method of the present application overcomes the shortcomings of traditional partial discharge detection, infrared temperature measurement, and impedance measurement methods, such as limited monitoring range, weak anti-interference ability, and difficulty in achieving distributed positioning, and achieves rapid positioning and accurate early warning of single-phase grounding faults in medium-voltage cables.

[0072] In one embodiment, the process of constructing the difference feature template includes:

[0073] Under each pre-established excitation test condition, a plurality of traveling wave response signal samples synchronously collected by the electromagnetic sensor nodes are obtained, wherein the plurality of traveling wave response signal samples include traveling wave response signals obtained by testing a multi-voltage power supply network at different voltage levels;

[0074] Identifying traveling wave characteristic index samples of traveling wave response signal samples, the traveling wave characteristic index samples including frequency spectrum characteristics, propagation velocity characteristics and amplitude attenuation characteristics;

[0075] According to the difference in feature distribution extracted from the traveling wave feature index samples, a difference feature template is determined.

[0076] Among them, the excitation test conditions refer to the external electrical input environment used to actively stimulate the cable's traveling wave response signal, including a variety of controllable excitation modes such as pulse voltage excitation, step voltage excitation, and swept frequency signal excitation, which are used to simulate the transient electromagnetic characteristics of the cable under different working conditions. The traveling wave response signal sample refers to the transient traveling wave voltage or current waveform data set synchronously collected by the electromagnetic sensor node under different excitation test conditions. The traveling wave characteristic index sample refers to the characteristic parameter sample identified and extracted from the traveling wave response signal sample for quantifying the cable's electrical characteristics, specifically including frequency spectrum characteristics, propagation velocity characteristics, and amplitude attenuation characteristics. The frequency spectrum characteristics are used to describe the main frequency and frequency band energy distribution, the propagation velocity characteristics are used to characterize the time delay and speed of traveling waves propagating in the cable, and the amplitude attenuation characteristics are used to reflect the attenuation rate of the signal with propagation distance.

[0077] Specifically, the computer equipment first constructs multiple excitation test conditions to systematically stimulate the cable's traveling wave response signal. Preferably, the excitation conditions include pulse voltage excitation to simulate transient impacts, step voltage excitation to simulate transient fluctuations caused by switching operations, and swept frequency signal excitation to test the cable's frequency response characteristics, with the sweep frequency range covering low to high frequencies. The excitation test conditions are applied to low-voltage cables, medium-voltage cables, and high-voltage cables, respectively, and executed under different operating conditions such as no-load, light-load, and full-load to fully cover possible actual electromagnetic disturbances and ensure the integrity and representativeness of the test.

[0078] Under each excitation condition, the computer instructs each electromagnetic sensor node to synchronously initiate high-precision sampling, ensuring strict temporal consistency in signal capture and avoiding feature extraction errors caused by time offsets. The traveling wave response signal samples collected by the nodes can be categorized and stored according to voltage level and excitation condition, forming a library of traveling wave response signal samples at multiple voltage levels.

[0079] Next, the computer equipment performs feature extraction processing on each traveling wave response signal sample. It can extract frequency spectrum features and obtain the main frequency and frequency band energy distribution through the fast Fourier transform algorithm. It can also calculate the propagation speed characteristics, and calculate the propagation speed of the traveling wave based on the wave arrival time difference between different nodes and the path length. It can also analyze the amplitude attenuation characteristics, and obtain the signal attenuation characteristics by measuring the attenuation rate of the traveling wave amplitude with the propagation distance, thereby generating a complete set of traveling wave characteristic indicator samples. Subsequently, the traveling wave characteristic indicator samples under each voltage level are statistically analyzed to obtain their characteristic distribution information such as mean, variance, and extreme value range. Combined with multi-feature fusion analysis, multiple features such as propagation speed and frequency spectrum energy distribution are combined to further improve the discrimination and accuracy of voltage level identification.

[0080] Finally, the computer automatically extracts quantifiable characteristic distribution differences based on the statistical distribution differences between characteristic indicator samples at different voltage levels and constructs a differential feature template based on this information. This differential feature template is stored as a multi-dimensional classification threshold, including propagation velocity threshold, frequency band energy ratio threshold, amplitude attenuation threshold, etc., and is used to automatically identify cable voltage levels and regional boundaries during actual operation, enabling accurate identification and intelligent management of cable zones, further improving the reliability and efficiency of monitoring and early warning.

[0081] In this embodiment, because multi-voltage cables exhibit significant differences in structural parameters, insulation properties, and electromagnetic propagation characteristics, a computer device, under pre-established multiple excitation test conditions, actively acquires multiple traveling wave response signal samples synchronously collected by electromagnetic sensor nodes. Comprehensive feature index identification and difference extraction based on frequency spectrum characteristics, propagation velocity characteristics, and amplitude attenuation characteristics can significantly improve the accuracy of identifying areas with cables of different voltage levels. Furthermore, by establishing a differential feature template, a reliable basis can be provided for the automatic identification of traveling wave boundaries and the precise marking of medium-voltage cable areas, reducing the false detection rate and missed detection rate in actual on-site monitoring, enhancing the system's adaptive ability to identify cable status in complex multi-voltage power supply networks, and improving the overall efficiency and accuracy of medium-voltage cable fault monitoring and early warning.

[0082] In one embodiment, the process of constructing the difference feature template further includes:

[0083] Acquiring at least one abnormal excitation test condition, the abnormal excitation test condition including a single-phase ground fault condition;

[0084] Under abnormal excitation test conditions, obtain high-voltage traveling wave response signal samples in the high-voltage cable area, medium-voltage traveling wave response signal samples in the medium-voltage cable area, and low-voltage traveling wave response signal samples in the low-voltage cable area in the multi-voltage power supply network;

[0085] Analyze the traveling wave abnormal characteristic index samples of the high-pressure traveling wave response signal samples, the low-pressure traveling wave response signal samples, and the medium-pressure traveling wave response signal samples;

[0086] A feature comparison is performed based on the traveling wave anomaly feature index sample and the traveling wave feature index sample to obtain a discriminative enhancement feature, and the difference feature template is updated according to the discriminative enhancement feature.

[0087] Among them, abnormal excitation test conditions refer to the electrical excitation environment used to simulate the cable under abnormal operating conditions (such as single-phase ground faults). The traveling wave response signal is actively stimulated by external electrical disturbances to evaluate the differences in the characteristics of the cable under abnormal conditions. The single-phase ground fault condition is a typical abnormal excitation test condition. It is formed by connecting any phase conductor of the cable to the ground directly or through a certain resistance to form a ground current path, simulating the common ground fault mode in actual operation. The traveling wave abnormal characteristic index sample is a set of characteristic parameters extracted from the traveling wave response signal sample under abnormal conditions. It is used to quantify the differential characteristics of the cable under abnormal operating conditions, including frequency spectrum characteristics, propagation speed characteristics, amplitude attenuation characteristics, waveform distortion characteristics, zero mode and line mode energy ratio, etc. The discriminative enhancement feature refers to a feature set that can further improve the accuracy of voltage level area identification after comparison with the traveling wave characteristic index sample under normal operating conditions.

[0088] Specifically, the computer device first configures at least one abnormal excitation test condition, preferably a single-phase ground fault condition, to simulate ground faults that may occur in medium-voltage cables or other voltage-level cables during actual operation. To achieve this condition, the computer device controls the fault generator to apply a specific ground current to the target cable, set the ground resistance value, select different fault locations, and determine the initial current phase angle, fully covering abnormal response conditions under low and high resistance conditions and at different locations.

[0089] Next, under abnormal excitation test conditions, the computer instructs electromagnetic sensor nodes distributed across each voltage level of the multi-voltage power supply network to synchronously initiate high-precision data acquisition. Specifically, the nodes acquire high-voltage traveling wave response signal samples from the high-voltage cable area, medium-voltage traveling wave response signal samples from the medium-voltage cable area, and low-voltage traveling wave response signal samples from the low-voltage cable area, forming a complete sample library under abnormal operating conditions.

[0090] After completing data acquisition, the computer equipment performs feature analysis on the traveling wave response signal samples in the three regions and extracts samples of abnormal traveling wave characteristic indicators. Preferably, the analysis includes extracting frequency spectrum features to observe changes in high-frequency components in the fault signal, extracting propagation velocity features to analyze wave velocity anomalies caused by reflections at the fault point, extracting amplitude attenuation features to measure changes in signal energy loss caused by the fault, and also includes the degree of waveform distortion and zero-mode component energy ratio to further identify ground current paths and waveform distortion. Through multi-dimensional feature analysis, the differences in the electromagnetic propagation characteristics of the cable under abnormal operating conditions are comprehensively characterized.

[0091] The computer then compares the abnormal traveling wave characteristic indicator samples with the normal traveling wave characteristic indicator samples, calculating the significance difference between the different features. It automatically selects the features that contribute most to voltage level area identification, forming a set of distinguishing enhanced features. For example, a medium-voltage cable under fault conditions may exhibit a shorter rise time, stronger high-frequency oscillation energy, and a significant zero-mode dominant component. These characteristics are more distinguishing than the characteristic indicators under normal conditions.

[0092] Finally, the computer equipment updates the original difference feature template based on the obtained discriminative enhancement features, and improves the voltage level recognition accuracy of the template under abnormal conditions by dynamically adjusting the classification threshold or adding new feature dimensions, ensuring that the cable area and voltage level can still be accurately identified in the fault scenario, thereby enhancing the reliability and robustness of the subsequent monitoring and early warning system.

[0093] In this embodiment, by acquiring and configuring abnormal excitation test conditions, it is possible to actively simulate actual fault scenarios, thereby enabling the computer equipment to obtain the traveling wave response characteristics under different voltage level regions, analyze the significant differences between abnormal and normal characteristics, and extract distinguishing enhancement features. Furthermore, using the distinguishing enhancement features to update the difference feature template helps to improve the accuracy of cable zoning and fault identification capabilities under abnormal operating conditions. Ultimately, even in complex situations such as single-phase ground faults, it can still ensure accurate identification of voltage level regions and reliable early warning, effectively improving the overall safety and operational stability of the system.

[0094] In one embodiment, the step of updating the difference feature template according to the distinguishing enhancement feature includes:

[0095] A boundary enhancement feature set for distinguishing voltage levels is constructed using discriminative enhancement features, which include spectrum stretching interval features, propagation velocity step features, and reflection amplitude change features.

[0096] According to the boundary enhancement feature set and the traveling wave anomaly feature index samples, the classification model is trained, and the output results of the trained classification model are used to update the difference feature template.

[0097] Among them, the spectrum stretching interval feature refers to the phenomenon that the spectrum width of the traveling wave signal is expanded due to a cable fault or abnormal excitation, which manifests as an increase in high-frequency energy or a shift in frequency distribution. It is used to describe the frequency response differences of cables of different voltage levels under abnormal excitation. The propagation velocity step feature refers to the characteristic that the propagation velocity of the traveling wave signal in cables of different voltage levels shows a significant mutation at the fault point or reflection point. It is used to characterize the differences in the internal medium and structural changes of the cable. The reflection amplitude change feature refers to the relative change between the reflected wave amplitude and the incident wave amplitude when the traveling wave signal encounters a fault point or impedance discontinuity in the cable and is reflected. It is used to quantify the impedance matching and loss characteristics of the cable. The boundary enhancement feature set is a multidimensional feature set formed by combining discriminative enhancement features. It is used to finely divide the voltage level boundary area and support classification model training.

[0098] Specifically, the computer equipment first uses the previously acquired distinguishing enhancement features to extract spectrum stretch interval characteristics, propagation velocity step characteristics, and reflection amplitude change characteristics from both abnormal excitation test data and normal operating condition data, and then numerically expresses them. To ensure the comprehensiveness and accuracy of the feature description, the computer equipment performs multi-node synchronous measurements in cable areas at each voltage level, extracting key parameters such as signal energy distribution, velocity change amplitude, and reflection amplitude ratio under different fault conditions and excitation modes.

[0099] Next, the computer performs a fusion analysis of the extracted spectrum stretch interval features, propagation velocity step features, and reflection amplitude change features to form a boundary enhancement feature set used to describe the boundaries of the voltage level region. Preferably, a multidimensional feature vector assembly method is used to combine the individual features into a set of overall feature vectors to enhance the richness and expressiveness of the model input. Simultaneously, the computer performs feature correlation analysis to screen the features that contribute most to the voltage level classification, thereby avoiding redundant information interference and improving training efficiency and classification accuracy.

[0100] Subsequently, the computer equipment uses the boundary enhancement feature set and the corresponding traveling wave anomaly characteristic indicator samples as training data input to construct a classification model. Preferably, a classification algorithm based on supervised learning, such as random forest, support vector machine, or neural network, can be selected. During the model training process, the cable voltage level is set as the label information. Through strategies such as sample grouping, cross-validation, and hyperparameter tuning, the classification model is ensured to have good generalization ability and stability. After the model is trained, the computer equipment automatically generates and updates the difference feature template based on the training output results, ultimately forming the latest difference feature template dataset that can be used for real-time monitoring.

[0101] In this embodiment, the computer device constructs a boundary enhancement feature set by utilizing the discriminative enhancement features, and trains a classification model based on the feature set and abnormal feature samples, which can significantly enhance the automatic recognition accuracy of cable areas of different voltage levels. Furthermore, by dynamically updating the training results of the classification model to the difference feature template, not only the timeliness and accuracy of the voltage level area division are guaranteed, but also the reliability and robustness under abnormal working conditions are improved. In this way, even in the case of complex interference such as spectrum broadening, sudden changes in propagation speed or drastic changes in reflection amplitude during cable operation, the cable voltage level can still be accurately identified, ensuring the stable and accurate execution of fault monitoring and early warning functions, thereby effectively improving the safety and operation efficiency of the overall distribution network.

[0102] In one embodiment, the step of determining the first traveling wave boundary and the second traveling wave boundary comprises:

[0103] The difference feature template is used to identify the characteristic index of the traveling wave and obtain the characteristic mutation area;

[0104] After calculating the gradient change rate of each mutation point in the characteristic mutation area, the first characteristic mutation point is selected as the first traveling wave boundary, and the second characteristic mutation point is selected as the second traveling wave boundary, wherein the gradient change rates of the first characteristic mutation point and the second characteristic mutation point are both greater than the preset threshold, the gradient change rate of the first characteristic mutation point is the largest, and the gradient change rate of the second characteristic mutation point is second to the gradient change rate of the first characteristic mutation point.

[0105] Among them, the characteristic mutation area refers to the cable section where the spatial distribution of the traveling wave characteristic indicators undergoes a significant jump, usually representing the transition area between different voltage levels or different structural segments. The gradient change rate refers to the rate of change of the characteristic indicator with space or distance. It is used to quantify the degree of sharp change of the indicator at the mutation point and is an important parameter for measuring the intensity of the mutation. The first characteristic mutation point refers to the point in the characteristic mutation area where the gradient change rate is the largest and exceeds the preset threshold. It is used to define the transition boundary between the low-voltage cable area and the medium-voltage cable area. The second characteristic mutation point refers to the point where the gradient change rate is the second largest and exceeds the preset threshold. It is used to define the transition boundary between the medium-voltage cable area and the high-voltage cable area.

[0106] Specifically, the computer device first compares and analyzes the real-time collected traveling wave characteristic indicators based on a pre-constructed differential feature template. Preferably, the traveling wave characteristic indicators include propagation velocity, frequency band energy ratio, amplitude attenuation rate, etc. The computer device scans the entire length of the cable section by section, compares the currently measured indicator values ​​with the characteristic range of the corresponding voltage level in the differential feature template, and automatically marks areas where the indicators deviate significantly, identifying them as characteristic mutation areas. For example, if the propagation velocity of a certain cable segment rapidly decreases from 180 meters per microsecond to 150 meters per microsecond, and the frequency band energy ratio changes significantly, the computer device determines that segment as a characteristic mutation area.

[0107] Furthermore, the computer calculates the gradient change rate for each candidate mutation point within the identified characteristic mutation region. Preferably, a first-order difference or sliding window differential method can be used, combined with spatial distance coordinates, to obtain the local gradient change rate of the characteristic indicator and compare it with a preset threshold. The point with the largest gradient change rate is preferentially selected as the first characteristic mutation point, while the point with the second largest gradient change rate is selected as the second characteristic mutation point. Both points must meet the condition of being greater than the preset gradient threshold to ensure the significance of the mutation and the accuracy of the boundary.

[0108] Finally, the computer defines the first characteristic mutation point with the largest gradient change rate as the first traveling wave boundary, which indicates the transition from the low-voltage cable area to the medium-voltage cable area. The second characteristic mutation point with the second largest gradient change rate is defined as the second traveling wave boundary, which indicates the transition from the medium-voltage cable area to the high-voltage cable area. For complex cable topologies, this iterative gradient calculation and mutation point screening can achieve precise segmentation and labeling of multiple voltage switching zones, meeting the requirements for dynamic identification of medium-voltage cable areas in complex networks.

[0109] In this embodiment, the computer device uses differential feature templates to identify real-time traveling wave characteristic indicators, quickly identifying characteristic mutation areas and precisely locating the spatial location of voltage level changes. Furthermore, based on the gradient change rate, it performs refined quantitative analysis of each mutation point and selects the first characteristic mutation point with the largest change rate and the second characteristic mutation point with the second largest change rate, significantly improving the accuracy and stability of boundary identification. This approach ensures high adaptability of boundary identification for cable areas of different voltage levels, providing a reliable foundation for fault monitoring, traveling wave analysis, and real-time early warning in medium-voltage cable areas. It enables precise definition and efficient monitoring of medium-voltage cable fault areas, improving the safety and intelligence of the entire distribution network.

[0110] In one embodiment, the steps of performing single-phase ground fault monitoring on a medium voltage cable area according to a real-time traveling wave response signal and outputting a monitoring warning signal include:

[0111] A single-phase grounding fault template model is constructed, and the signal feature matching of the real-time traveling wave response signal is performed using the single-phase grounding fault template model to output a single-phase grounding fault score.

[0112] If the single-phase grounding fault score is greater than the preset fault threshold, the real-time traveling wave response signal is analyzed, the single-phase grounding fault location coordinates in the medium-voltage cable area are extracted, and a monitoring warning signal is output according to the single-phase grounding fault location coordinates.

[0113] Among them, the single-phase grounding fault template model refers to a mathematical model trained by machine learning or statistical modeling methods using a large number of historical single-phase grounding fault traveling wave response signal samples or simulation data samples, and is used to match and score the characteristics of whether a single-phase grounding fault exists in the real-time traveling wave response signal. It contains multi-dimensional indicator information such as zero-mode component amplitude characteristics, high-frequency energy characteristics, rise time characteristics, and attenuation characteristics. The single-phase grounding fault score refers to the quantitative score generated by the computer equipment based on the matching results of the single-phase grounding fault template model and the real-time traveling wave response signal characteristics, which is used to indicate whether the current signal highly conforms to the single-phase grounding fault mode. The single-phase grounding fault location coordinates refer to the spatial coordinates calculated by the computer equipment based on the real-time traveling wave propagation speed and the arrival time difference detected by each node, which is used to accurately calibrate the occurrence location of the single-phase grounding fault in the cable.

[0114] Specifically, the computer device first receives the traveling wave response signal of the medium-voltage cable area from the multi-voltage power supply network in real time. Preferably, the signal is synchronously collected by distributed electromagnetic sensor nodes, has high-frequency transient characteristics and high time accuracy, and can effectively reflect the transient fault characteristics of the cable. After receiving the real-time traveling wave response signal, the computer device calls the pre-trained single-phase grounding fault template model to perform feature matching analysis on the signal. Preferably, the computer device will automatically extract key features for discrimination from the real-time signal, such as zero-mode component amplitude, spectral energy distribution, high-frequency content, rise time, and reflected signal amplitude change, and perform multi-dimensional comparison with the standard features in the single-phase grounding fault template model, calculate the matching similarity between the signal and the template, and finally output the single-phase grounding fault score.

[0115] The computer then compares the single-phase ground fault score with a preset fault determination threshold. If the score exceeds the threshold, the current traveling wave response signal highly matches the characteristics of a single-phase ground fault. The computer then further analyzes the real-time traveling wave response signal in detail. Using the reception time differences between each sensor node and the known propagation speed of the cable, the computer calculates the spatial coordinates of the single-phase ground fault location, known as the single-phase ground fault location coordinates. This location result is typically expressed as a specific number of meters or a percentage from the cable starting point to ensure accurate positioning.

[0116] Finally, the computer automatically generates a monitoring and warning signal based on the single-phase grounding fault's location coordinates. Preferably, this signal includes not only the fault type (single-phase grounding fault) and precise spatial location coordinates, but also the fault's rating (e.g., medium, high) and recommended response measures. The computer then outputs this monitoring and warning signal in real time via a graphical human-machine interface, mobile terminal SMS push notifications, or an operations and maintenance scheduling platform, enabling maintenance personnel to obtain fault information immediately and arrive at the fault site with precision.

[0117] In this embodiment, by constructing a single-phase grounding fault template model and performing feature matching on the real-time traveling wave response signal, the computer equipment can quickly quantify whether the current signal has single-phase grounding fault characteristics, thereby significantly improving the accuracy and timeliness of fault identification; further positioning is performed when the score is greater than the threshold, ensuring the spatial and accurate identification of the fault source, avoiding maintenance time delays caused by large-scale inspections; at the same time, based on the fault score and positioning results, the monitoring and early warning signal is output, which can provide operation and maintenance personnel with immediate, clear and accurate decision support information, improve the overall operational reliability and safety of the medium-voltage cable system, and realize intelligent and automated detection and disposal of single-phase grounding faults, which helps to avoid grid operation risks and ensure the stability of power supply.

[0118] In one embodiment, the step of analyzing the real-time traveling wave response signal to extract the location coordinates of the single-phase grounding fault in the medium voltage cable area includes:

[0119] Analyze the traveling wave timestamps of the real-time traveling wave response signal and calculate the wave head arrival time difference sequence;

[0120] After obtaining the layout path of the medium-voltage cable area, analyze the wave head arrival time difference series to predict the wave speed propagation data;

[0121] The traveling wave attenuation factor is introduced to correct the wave velocity propagation data and obtain the single-phase grounding fault location coordinates.

[0122] Among them, the traveling wave timestamp refers to the precise arrival time of the wave head obtained by the computer device through the signal mutation point detection algorithm after receiving the traveling wave response signal. It is used to identify the timing information of the traveling wave arriving at each sensor node. The wave head arrival time difference sequence refers to the time difference sequence between adjacent nodes calculated based on the traveling wave timestamps of each electromagnetic sensor node. It is used to characterize the relative time delay characteristics of traveling wave propagation. The medium-voltage cable regional layout path refers to the actual physical laying line of the medium-voltage cable, including spatial information such as length, branches, joints, and curved paths, which is used to accurately calculate the traveling wave propagation distance. Wave velocity propagation data refers to the average speed information of the traveling wave propagating in the cable obtained based on the time difference sequence and layout path prediction. The traveling wave attenuation factor refers to the energy attenuation rate caused by resistance, insulation loss and dispersion effects during the propagation of the traveling wave in the cable. It is used to correct the wave velocity and propagation characteristics.

[0123] Specifically, the computer first receives real-time traveling wave response signals synchronously collected by multiple electromagnetic sensor nodes within the medium-voltage cable area. It then uses signal processing techniques such as wavelet transforms or differential methods to detect the sudden rise of the traveling wave, accurately extracting the traveling wave timestamp information for each node. Preferably, the detected timestamps of each node are sorted, and the arrival time differences between adjacent nodes are calculated sequentially to generate a wave head arrival time difference sequence, which reflects the actual delay information of the traveling wave propagating from the fault source to each node.

[0124] Next, the computer acquires information about the medium-voltage cable routing in the area. This routing includes data such as the actual cable length, routing, bend radius, branch nodes, and joint locations. Preferably, a cable routing topology model is automatically constructed by reading cable engineering design drawings or a pre-stored digital topology database. Subsequently, the acquired wave arrival time difference sequence and the routing path are used, combined with the characteristics of the cable material (such as cross-linked polyethylene insulation), to predict the propagation velocity of the traveling wave and provide a preliminary estimate of the propagation characteristic parameters of the traveling wave in the cable.

[0125] Furthermore, considering that traveling waves are affected by factors such as resistance, dielectric loss, and dispersion during cable propagation, the computer equipment introduces a traveling wave attenuation factor to correct the wave velocity propagation data. Specifically, based on actual cable parameters such as resistivity, dielectric loss tangent, distributed capacitance, and the real-time detected main frequency component of the traveling wave, the energy attenuation per unit length is calculated, and the predicted wave velocity propagation data is dynamically adjusted. Using the corrected wave velocity propagation data, the time difference sequence is matched with the path length difference, and the spatial location of the single-phase grounding fault is accurately inferred using the least squares method or optimization solution algorithm. Ultimately, the single-phase grounding fault location coordinates are obtained, and accurate distance information is output.

[0126] In this embodiment, by analyzing the traveling wave timestamp of the real-time traveling wave response signal and calculating the wave head arrival time difference sequence, the computer equipment can accurately obtain the timing propagation characteristics of the fault wave from the source point to each node; combined with the layout path analysis time difference sequence of the medium-voltage cable area, the theoretical propagation path and speed characteristics of the traveling wave can be accurately predicted based on the actual cable topology; further introducing the traveling wave attenuation factor to correct the wave speed propagation data can effectively compensate for the speed and energy attenuation deviations caused by cable impedance, dielectric loss and dispersion effects, thereby improving the accuracy and reliability of fault location.

[0127] The following describes the medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing provided by the embodiment of the present application. The medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing described below and the medium voltage cable distributed monitoring method based on electromagnetic traveling wave sensing described above can be referred to each other. Figure 2 As shown, the present application provides a medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing, the device comprising:

[0128] An initial traveling wave response signal acquisition module 201 is configured to synchronously acquire an initial traveling wave response signal using electromagnetic sensor nodes deployed in a multi-voltage power supply network;

[0129] A traveling wave boundary determination module 202 is configured to extract traveling wave characteristic indicators from the initial traveling wave response signal, identify the traveling wave characteristic indicators according to a pre-constructed difference feature template, and determine a first traveling wave boundary and a second traveling wave boundary, wherein the first traveling wave boundary is used to represent the transition boundary between the low-voltage cable area and the medium-voltage cable area, and the second traveling wave boundary is used to represent the transition boundary between the medium-voltage cable area and the high-voltage cable area;

[0130] A medium voltage cable area marking module 203 is configured to mark a medium voltage cable area using the first traveling wave boundary and the second traveling wave boundary, and mark a medium voltage electromagnetic sensor node corresponding to the medium voltage cable area;

[0131] The detection warning signal output module 204 is used to receive the real-time traveling wave response signal transmitted by the medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, monitor the single-phase grounding fault in the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring warning signal.

[0132] In one embodiment, the traveling wave boundary determination module 202 includes:

[0133] A traveling wave response signal sample acquisition unit is configured to acquire, under each pre-established excitation test condition, a plurality of traveling wave response signal samples synchronously collected by the electromagnetic sensor nodes, wherein the plurality of traveling wave response signal samples include traveling wave response signals obtained by testing a multi-voltage power supply network at different voltage levels;

[0134] A traveling wave characteristic index sample identification unit is used to identify traveling wave characteristic index samples of traveling wave response signal samples, where the traveling wave characteristic index samples include frequency spectrum characteristics, propagation speed characteristics, and amplitude attenuation characteristics;

[0135] The difference feature template determining unit is used to determine the difference feature template according to the feature distribution difference extracted from the traveling wave feature index samples.

[0136] In one embodiment, the traveling wave boundary determination module 202 further includes:

[0137] an abnormal excitation test condition acquisition unit, configured to acquire at least one abnormal excitation test condition, the abnormal excitation test condition including a single-phase ground fault condition;

[0138] A low-voltage traveling wave response signal sample acquisition unit is used to acquire high-voltage traveling wave response signal samples in the high-voltage cable area, medium-voltage traveling wave response signal samples in the medium-voltage cable area, and low-voltage traveling wave response signal samples in the low-voltage cable area in the multi-voltage power supply network under abnormal excitation test conditions;

[0139] A traveling wave abnormal characteristic index sample analysis unit is used to analyze the traveling wave abnormal characteristic index samples of the high-pressure traveling wave response signal sample, the low-pressure traveling wave response signal sample and the medium-pressure traveling wave response signal sample;

[0140] The difference feature template updating unit is used to perform feature comparison based on the traveling wave abnormal feature index sample and the traveling wave feature index sample to obtain the distinguishing enhanced feature and update the difference feature template according to the distinguishing enhanced feature.

[0141] In one embodiment, the difference feature template updating unit includes:

[0142] A discriminative enhancement feature set construction subunit is used to construct a boundary enhancement feature set for distinguishing voltage levels using the discriminative enhancement features, the discriminative enhancement features including spectrum stretching interval features, propagation velocity step features, and reflection amplitude change features;

[0143] The difference feature template updating subunit is used to train the classification model according to the boundary enhancement feature set and the traveling wave anomaly feature indicator sample, and update the difference feature template using the output result of the trained classification model.

[0144] In one embodiment, the traveling wave boundary determination module 202 includes:

[0145] A characteristic mutation region determination unit is used to identify the traveling wave characteristic index using a difference feature template to obtain a characteristic mutation region;

[0146] A traveling wave boundary determination unit is used to select a first characteristic mutation point as a first traveling wave boundary and a second characteristic mutation point as a second traveling wave boundary after calculating the gradient change rate of each mutation point in the characteristic mutation area, wherein the gradient change rates of the first characteristic mutation point and the second characteristic mutation point are both greater than a preset threshold, the gradient change rate of the first characteristic mutation point is the largest, and the gradient change rate of the second characteristic mutation point is second to the gradient change rate of the first characteristic mutation point.

[0147] In one embodiment, the detection warning signal output module 204 includes:

[0148] A single-phase grounding fault score output unit is used to construct a single-phase grounding fault template model, use the single-phase grounding fault template model to perform signal feature matching on the real-time traveling wave response signal, and output a single-phase grounding fault score;

[0149] The detection and warning signal output unit is used to analyze the real-time traveling wave response signal if the single-phase grounding fault score is greater than the preset fault threshold, extract the single-phase grounding fault location coordinates located in the medium-voltage cable area, and output a monitoring and warning signal according to the single-phase grounding fault location coordinates.

[0150] In one embodiment, the detection warning signal output unit includes:

[0151] The wave head arrival time difference sequence calculation subunit is used to analyze the traveling wave timestamp of the real-time traveling wave response signal and calculate the wave head arrival time difference sequence;

[0152] The wave velocity propagation data prediction subunit is used to obtain the layout path of the medium voltage cable area, analyze the wave head arrival time difference series, and predict the wave velocity propagation data;

[0153] The single-phase grounding fault location coordinate determination subunit is used to introduce the traveling wave attenuation factor to correct the wave velocity propagation data to obtain the single-phase grounding fault location coordinates.

[0154] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing as described in any of the above embodiments.

[0155] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing as described in any of the above embodiments.

[0156] Schematically, as Figure 3 As shown, Figure 3 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 can be provided as a server. Figure 3 Computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions executable by processing component 302, such as application programs. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 302 is configured to execute the instructions to implement the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing according to any of the above-described embodiments.

[0157] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0158] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0159] Finally, it should be noted that, in this article, relational terms such as first and second are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. Without further restriction, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element. Herein, "one," "said," "the," and "its" may also include plural forms unless the context clearly indicates otherwise. A plurality refers to at least two, such as 2, 3, 5, or 8. "And / or" includes any and all combinations of the relevant listed items.

[0160] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0161] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A distributed monitoring method for medium voltage cables based on electromagnetic traveling wave sensing, characterized in that: The method comprises: The initial traveling wave response signal is synchronously collected using electromagnetic sensor nodes deployed in a multi-voltage power supply network; Extracting a traveling wave characteristic index of the initial traveling wave response signal, identifying the traveling wave characteristic index according to a pre-constructed difference feature template, and determining a first traveling wave boundary and a second traveling wave boundary, wherein the first traveling wave boundary is used to represent a transition boundary distinguishing a low-voltage cable area from a medium-voltage cable area, and the second traveling wave boundary is used to represent a transition boundary distinguishing a medium-voltage cable area from a high-voltage cable area; Using the first traveling wave boundary and the second traveling wave boundary to mark a medium voltage cable area, and marking a medium voltage electromagnetic sensor node corresponding to the medium voltage cable area; Receive a real-time traveling wave response signal transmitted by a medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, perform single-phase grounding fault monitoring on the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring warning signal.

2. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 1, characterized in that: The process of constructing the difference feature template includes: Under each pre-established excitation test condition, obtaining a plurality of traveling wave response signal samples synchronously collected by the electromagnetic sensor node, wherein the plurality of traveling wave response signal samples include traveling wave response signals obtained by testing the multi-voltage power supply network at different voltage levels; Identifying a traveling wave characteristic index sample of the traveling wave response signal sample, wherein the traveling wave characteristic index sample includes a frequency spectrum feature, a propagation velocity feature, and an amplitude attenuation feature; The difference feature template is determined according to the feature distribution difference extracted from the traveling wave feature index samples.

3. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 2, characterized in that: The process of constructing the difference feature template further includes: Acquiring at least one abnormal excitation test condition, wherein the abnormal excitation test condition includes a single-phase ground fault condition; Under the abnormal excitation test condition, obtaining high-voltage traveling wave response signal samples in the high-voltage cable area, medium-voltage traveling wave response signal samples in the medium-voltage cable area, and low-voltage traveling wave response signal samples in the low-voltage cable area in the multi-voltage power supply network; analyzing traveling wave abnormality characteristic index samples of the high-pressure traveling wave response signal sample, the low-pressure traveling wave response signal sample, and the medium-pressure traveling wave response signal sample; A feature comparison is performed based on the traveling wave abnormality feature index sample and the traveling wave feature index sample to obtain a distinguishing enhancement feature, and the difference feature template is updated according to the distinguishing enhancement feature.

4. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 3 is characterized in that: The step of updating the difference feature template according to the distinguishing enhancement feature includes: Constructing a boundary enhancement feature set for distinguishing voltage levels using the distinguishing enhancement features, wherein the distinguishing enhancement features include spectrum stretching interval features, propagation velocity step features, and reflection amplitude change features; A classification model is trained according to the boundary enhancement feature set and the traveling wave abnormality feature index sample, and the output result of the trained classification model is used to update the difference feature template.

5. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 1, characterized in that: The step of determining the first traveling wave boundary and the second traveling wave boundary comprises: Using the difference feature template to identify the traveling wave characteristic index to obtain a characteristic mutation area; After calculating the gradient change rate of each mutation point in the characteristic mutation area, the first characteristic mutation point is selected as the first traveling wave boundary, and the second characteristic mutation point is selected as the second traveling wave boundary, wherein the gradient change rates of the first characteristic mutation point and the second characteristic mutation point are both greater than a preset threshold, the gradient change rate of the first characteristic mutation point is the largest, and the gradient change rate of the second characteristic mutation point is second to the gradient change rate of the first characteristic mutation point.

6. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 1, characterized in that: The step of performing single-phase grounding fault monitoring on the medium voltage cable area according to the real-time traveling wave response signal and outputting a monitoring warning signal comprises: Constructing a single-phase grounding fault template model, using the single-phase grounding fault template model to perform signal feature matching on the real-time traveling wave response signal, and outputting a single-phase grounding fault score; If the single-phase grounding fault score is greater than a preset fault threshold, the real-time traveling wave response signal is analyzed, the single-phase grounding fault location coordinates located in the medium-voltage cable area are extracted, and the monitoring warning signal is output according to the single-phase grounding fault location coordinates.

7. The method for distributed monitoring of medium voltage cables based on electromagnetic traveling wave sensing according to claim 6, characterized in that: The step of analyzing the real-time traveling wave response signal to extract the location coordinates of the single-phase grounding fault located in the medium voltage cable area includes: Analyzing the traveling wave timestamp of the real-time traveling wave response signal and calculating the wave head arrival time difference sequence; After obtaining the layout path of the medium voltage cable area, analyzing the wave head arrival time difference sequence to predict wave speed propagation data; A traveling wave attenuation factor is introduced to correct the wave velocity propagation data to obtain the single-phase grounding fault location coordinates.

8. A medium voltage cable distributed monitoring device based on electromagnetic traveling wave sensing, characterized in that: The device comprises: An initial traveling wave response signal acquisition module is used to synchronously acquire the initial traveling wave response signal using electromagnetic sensor nodes arranged in a multi-voltage power supply network; a traveling wave boundary determination module, configured to extract a traveling wave characteristic index from the initial traveling wave response signal, identify the traveling wave characteristic index according to a pre-constructed difference feature template, and determine a first traveling wave boundary and a second traveling wave boundary, wherein the first traveling wave boundary is used to represent a transition boundary distinguishing a low-voltage cable area from a medium-voltage cable area, and the second traveling wave boundary is used to represent a transition boundary distinguishing a medium-voltage cable area from a high-voltage cable area; a medium-voltage cable area marking module, configured to mark a medium-voltage cable area using the first traveling wave boundary and the second traveling wave boundary, and mark a medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area; The detection and warning signal output module is used to receive the real-time traveling wave response signal transmitted by the medium-voltage electromagnetic sensor node corresponding to the medium-voltage cable area, monitor the single-phase grounding fault in the medium-voltage cable area according to the real-time traveling wave response signal, and output a monitoring warning signal.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to perform the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing as described in any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, execute the steps of the medium-voltage cable distributed monitoring method based on electromagnetic traveling wave sensing as described in any one of claims 1 to 7.

Images