Power grid fault isolation method and isolation system

Abstract

The invention discloses a power grid fault isolation method and isolation system, relates to the technical field of power systems, and can complete fault detection and isolation in a short time and reduce the influence of faults on a power grid. Through an accurate fault positioning technology, the isolation accuracy is improved; manual intervention is reduced, and the safety and efficiency of operation are improved. The scheme is characterized in that power grid operation data, equipment state data and external environment data are acquired according to a preset frequency; the data are integrated, and integrated data are obtained; extracting features of the integrated data to obtain power grid data features; comparing the power grid data feature with each abnormal feature in a preset abnormal feature library, and judging whether the power grid has a fault or not; when the power grid breaks down, the fault position, the fault type and the fault severity are determined; determining an isolation point, an isolation region section and an isolation strategy; and performing isolation operation on the isolation points and the isolation regions of the power grid. The method is used for power grid fault isolation.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly to a power grid fault isolation method and an isolation system. Background Art

[0002] A power grid fault refers to an unexpected fault occurring in a power system, which may lead to the interruption of power supply or damage to power equipment, bringing serious impacts to production, life and the environment. Power grid fault isolation is an important technology in the operation of power systems, and its purpose is to quickly and accurately cut off the faulty part during a fault to protect the safe and stable operation of the power grid. In recent years, with the rapid development of power systems, the scale of power grids has been continuously expanding and the structure has become increasingly complex. Power grid faults, especially large-scale power grid faults, may cause power supply interruptions, bringing serious impacts to social economy and people's lives.

[0003] In the prior art, power grid fault isolation methods mostly rely on manual operations and traditional protection devices, and this method has problems such as long response time and low isolation accuracy. In addition, with the large-scale grid connection of intermittent new energy generation, active distribution networks play an important role in utilizing renewable energy and improving the reliability of user power consumption. However, when a short-circuit fault occurs in an active distribution network, distributed power sources inject short-circuit current into the fault point, causing short-circuit current to flow through the switches downstream of the fault point, which makes the traditional short-circuit fault location and isolation methods ineffective. Summary of the Invention

[0004] The present invention provides a power grid fault isolation method and an isolation system, which can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operations.

[0005] To achieve the above object, the present invention adopts the following technical solutions: In a first aspect of the present invention, a power grid fault isolation method is provided, including: Collect power grid operation data, equipment status data and external environment data according to a preset frequency.

[0006] Based on data fusion technology, integrate the power grid operation data, the equipment status data and the external environment data to obtain integrated data.

[0007] Extract the features of the integrated data to obtain power grid data features.

[0008] Compare the power grid data features with each abnormal feature in a preset abnormal feature library to determine whether a fault has occurred in the power grid: If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library does not exceed the preset threshold, the power grid has not failed.

[0009] If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library exceeds the preset threshold, the power grid has failed.

[0010] When the power grid fails, determine the fault location, fault type, and fault severity.

[0011] Determine the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity.

[0012] Perform isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy.

[0013] Furthermore, the power grid fault isolation method, after collecting power grid operation data, equipment status data, and external environment data at a preset frequency, further includes: Preprocess the power grid operation data, equipment status data, and external environment data; wherein, the preprocessing includes but is not limited to data cleaning, data denoising, data filtering, data spectral analysis, data wavelet transform, and data standardization.

[0014] Furthermore, the power grid fault isolation method, after performing isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy, further includes: Use historical data and the power grid operation data to predict potential faults through a machine learning model.

[0015] Furthermore, the power grid fault isolation method, the power grid operation data includes: The power grid operation data includes but is not limited to voltage signals, current signals, frequency signals, and power factors.

[0016] Furthermore, the power grid fault isolation method, extract the characteristics of the integrated data to obtain power grid data characteristics, including: Extract the characteristics of the integrated data through principal component analysis, or linear discriminant analysis, or Fourier transform method, or deep learning method to obtain the power grid data characteristics.

[0017] Furthermore, the power grid fault isolation method, the power grid data characteristics include: The power grid data characteristics include but are not limited to frequency, amplitude, and energy.

[0018] Further, for the power grid fault isolation method, when a fault occurs in the power grid, determining the fault location, the fault type, and the fault severity includes: Determining the fault location by measuring the time difference of traveling waves arriving at different measurement points.

[0019] Analyzing the frequency and amplitude of the traveling waves to determine the fault type.

[0020] Determining the fault severity according to the first disturbance power peak obtained by multiplying the voltage traveling wave data and the current traveling wave data of two traveling wave measurement units on both sides of the fault location.

[0021] A second aspect of the present invention provides a power grid fault isolation system, including: An acquisition module for acquiring power grid operation data, equipment status data, and external environment data at a preset frequency.

[0022] An integration module for integrating the power grid operation data, the equipment status data, and the external environment data based on data fusion technology to obtain integrated data.

[0023] An extraction module for extracting the features of the integrated data to obtain power grid data features.

[0024] A judgment module for comparing the power grid data features with each abnormal feature in a preset abnormal feature library to judge whether a fault occurs in the power grid: If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, the power grid has not failed.

[0025] If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the power grid has failed.

[0026] A first determination module for determining the fault location, the fault type, and the fault severity when the power grid fails.

[0027] A second determination module for determining the isolation point, the isolation section, and the isolation strategy according to the fault location, the fault type, and the fault severity.

[0028] An execution module for performing isolation operations on the isolation point and the isolation section of the power grid according to the isolation strategy.

[0029] Further, the power grid fault isolation system further includes: a preprocessing module; A preprocessing module for preprocessing the grid operation data, the device status data, and the external environment data; wherein, the preprocessing includes but is not limited to data cleaning, data noise removal, data filtering, data spectral analysis, data wavelet transform, and data standardization.

[0030] Furthermore, the grid fault isolation system further includes: a prediction module; The prediction module is used to predict potential faults through a machine learning model by using historical data and the grid operation data.

[0031] The present invention provides a grid fault isolation method and an isolation system, including: collecting grid operation data, device status data, and external environment data at a preset frequency; integrating the grid operation data, device status data, and external environment data based on data fusion technology to obtain integrated data; extracting features of the integrated data to obtain grid data features; comparing the grid data features with each abnormal feature in a preset abnormal feature library to determine whether the grid has a fault: if the similarity between the grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, the grid has no fault; if the similarity between the grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the grid has a fault; when the grid has a fault, determining the fault location, fault type, and fault severity; determining the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity; performing isolation operations on the isolation point and isolation section of the grid according to the isolation strategy. Compared with the prior art, the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. The drawings are only used for the purpose of showing the implementation manner and are not considered as a limitation to the present invention.

[0033] Figure 1 It is a schematic flowchart of a grid fault isolation method in an embodiment of the present invention; Figure 2 It is a schematic flowchart of another grid fault isolation method in an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a grid fault isolation system in an embodiment of the present invention; Figure 4 It is a schematic structural diagram of another grid fault isolation system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs; the terms used in the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The terms "including" and "having" in the specification and claims of the present invention and their any variations are intended to cover non-exclusive inclusion.

[0036] In the description of the embodiments of the present invention, technical terms such as "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present invention, the meaning of "a plurality of" is more than two, unless otherwise specifically defined.

[0037] In the description of the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0038] In the description of the embodiments of the present invention, the term "a plurality of" means more than two (including two). Similarly, "a plurality of groups" means more than two groups (including two groups), and "a plurality of pieces" means more than two pieces (including two pieces).

[0039] In the description of the embodiments of the present invention, the orientation or positional relationship indicated by technical terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the embodiments of the present invention and simplifying the description, and does not indicate or imply that the indicated device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the embodiments of the present invention.

[0040] In the description of the embodiments of the present invention, unless otherwise clearly specified and defined, technical terms such as "installation", "connection", "linkage", "fixation" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral one; it can also be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances. Embodiment 1

[0041] An embodiment of the present invention provides a power grid fault isolation method, as Figure 1 shown, including: S101. Collect power grid operation data, equipment status data, and external environment data according to a preset frequency.

[0042] Among them, the preset frequency is the frequency of collecting power grid operation data, equipment status data, and external environment data according to a specific time interval. For example, the preset frequency of collecting power grid operation data is 1 second / time. It should be noted that: in the specific implementation of the present invention, the implementer can set the above preset frequency according to the actual situation or his own needs.

[0043] The power grid is a complex engineering system that is responsible for transmitting electrical energy from the power generation station to users' homes to meet the needs of daily life and industrial production. Power grid operation data refers to various types of data collected during the operation of the power system, such as voltage signals, current signals, frequency signals, and power factors.

[0044] Equipment status data refers to various status information collected during the operation of power system equipment. For example: physical quantities such as the temperature, pressure, rotation speed, vibration, current, and voltage of the equipment, as well as logical quantities such as the operation status, fault information, and production efficiency of the equipment.

[0045] External environment data refers to the external environment conditions of the power system, such as air temperature, air humidity, and air quality.

[0046] The collection of the above-mentioned various data is realized through corresponding sensors and smart meters. For example: the voltage signal is measured by a voltage sensor, the current and voltage of the equipment are measured by a smart meter, and the air temperature and humidity are measured by a temperature sensor and a humidity sensor.

[0047] S102. Based on data fusion technology, integrate the power grid operation data, equipment status data, and external environment data to obtain the integrated data.

[0048] Data fusion technology is a process of integrating data from different sources, different formats, or different structures into a unified data model or dataset. Its purpose is to improve the integrity, accuracy, and availability of data by integrating diverse data to support more in-depth analysis, decision-making, or application development. Common data fusion techniques include weighted average method, Bayesian method, and fuzzy logic method. Among them, the weighted average method assigns different weights to different data sources and then performs weighted summation to obtain the final fusion result; the Bayesian method is based on probability theory and updates the understanding and prediction of data by calculating posterior probabilities; the fuzzy logic method allows data to have a certain degree of ambiguity and performs data fusion through fuzzy sets and fuzzy rules.

[0049] S103. Extract the features of the integrated data to obtain power grid data features.

[0050] Feature extraction is a key step in smart grid monitoring and fault detection. It involves identifying and extracting key information that can represent the state of the power grid from a large amount of power grid operation data, equipment status data, and external environment data. The following are some power grid data features and their extraction methods: Voltage fluctuation: By real-time monitoring of voltage signals, statistical methods (such as calculating the standard deviation, maximum value, and minimum value of voltage) are used to extract voltage fluctuation features.

[0051] Frequency change: By monitoring the frequency signal of the power grid, features of frequency change can be extracted, such as frequency deviation, change rate, etc.

[0052] Power fluctuation: By analyzing the time series of power factors, features of power fluctuation can be extracted, such as the peak-to-valley difference of power, fluctuation frequency, etc.

[0053] Equipment status feature: By monitoring the real-time status data of equipment, equipment status features can be extracted, such as abnormal temperature, frequent operation of circuit breakers, etc.

[0054] External environment feature: By the data of external sensors, external environment features can be extracted, such as extreme weather events, sudden temperature changes, etc.

[0055] S104. Compare the power grid data features with each abnormal feature in the preset abnormal feature library to determine whether the power grid has a fault: S1041. If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed the preset threshold, the power grid has no fault.

[0056] S1042. If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the power grid has a fault.

[0057] Among them, the preset abnormal feature library is a key database in the power system for storing and identifying power grid abnormalities. It contains various predefined abnormal features, which are extracted from historical data and expert experience and used to compare with real-time power grid operation data to determine whether a power grid failure has occurred.

[0058] The similarity refers to the similarity or matching degree between the power grid data features and the features in the abnormal feature library, which can be calculated through various algorithms, such as cosine similarity, Euclidean distance, etc.

[0059] The preset threshold is a preset value used to determine whether the similarity is high enough to consider that a power grid failure has occurred.

[0060] S105. When a power grid failure occurs, determine the failure location, failure type, and failure severity.

[0061] Specifically, the traveling wave location technology can be used to determine the failure location by detecting the propagation of the traveling waves (instantaneous changes in voltage and current) generated by the failure in the power grid. In addition, an accurate fault location method based on PMU (phasor measurement unit) can also be used to eliminate false fault points by measuring the phase relationship between the measured point voltage and the calculated voltage at the fault point, realizing accurate fault location.

[0062] The failure types include transmission line failures, substation failures, and distribution line failures. Specifically, transmission line failures include line breaks, short circuits, etc.; substation failures include transformer failures, circuit breaker failures, etc.; distribution line failures include line short circuits, leakage, etc.

[0063] The severity refers to the degree of impact of the failure on the stability, power supply reliability, and safety of the power system. Evaluating the severity of a power grid failure usually involves multiple aspects, including the impact of the failure on power grid operation, possible economic losses, impact on the environment, and impact on public safety. The severity of a power grid failure can be divided into three levels: Minor: Failures that have little impact on system stability and power supply reliability.

[0064] Moderate: Failures that have a certain impact on system stability and power supply reliability.

[0065] Severe: Failures that have a greater impact on system stability and power supply reliability and may lead to system collapse or large-scale power outages.

[0066] S106. Determine the isolation point, isolation section, and isolation strategy according to the failure location, failure type, and failure severity.

[0067] Among them, the isolation point refers to the specific location in the power grid where isolation measures need to be taken, such as specific circuit breakers, disconnectors, or other devices that can cut off the current flow. The determination of the isolation point is usually based on the results of fault analysis to ensure that the fault is restricted to the smallest area.

[0068] The isolated section refers to a part of the power grid that needs to be isolated, which includes all power grid facilities between the isolation point and the next isolation point. The purpose of dividing the isolated section is to localize the fault and prevent the fault current from affecting a wider power grid area.

[0069] The isolation strategy is based on the analysis of the fault location, fault type, and fault severity, aiming to determine which parts of the power grid need to be isolated, as well as the order and method of isolation.

[0070] S107. Perform isolation operations on the isolation points and isolated sections of the power grid according to the isolation strategy.

[0071] The execution of the isolation operation involves actual physical operations, including but not limited to: disconnecting the circuit breaker, operating the disconnector, and reclosing operation. Specifically, disconnecting the circuit breaker is to operate the circuit breaker to cut off the current in the fault section, which is the most common isolation operation. Operating the disconnector is to physically isolate the fault section using the disconnector to ensure that the fault section is completely separated from other parts of the power grid. The reclosing operation is that the automatic reclosing device can automatically reclose after detecting an instantaneous fault. If the fault persists, it will automatically isolate the fault section.

[0072] An embodiment of the present invention provides a power grid fault isolation method, including: collecting power grid operation data, device status data, and external environment data according to a preset frequency; integrating the power grid operation data, device status data, and external environment data based on data fusion technology to obtain integrated data; extracting the features of the integrated data to obtain power grid data features; comparing the power grid data features with each abnormal feature in the preset abnormal feature library to determine whether the power grid has a fault: if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed the preset threshold, the power grid has no fault; if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the power grid has a fault; when the power grid has a fault, determine the fault location, fault type, and fault severity; determine the isolation point, isolated section, and isolation strategy according to the fault location, fault type, and fault severity; perform isolation operations on the isolation points and isolated sections of the power grid according to the isolation strategy. Compared with the prior art, the embodiment of the present invention can complete fault detection and isolation in a short time, reduce the impact of the fault on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operation. Embodiment Two

[0073] An embodiment of the present invention provides a power grid fault isolation method, as Figure 2 shown, including: S201. Collect power grid operation data, equipment status data, and external environment data at a preset frequency.

[0074] Specifically, in this embodiment, the corresponding sensors are used to collect power grid operation data, equipment status data, and external environment data at a preset frequency. For example: collect the voltage signal, current signal, frequency signal, and power factor of the power grid at a frequency of 1 second / time. Correspondingly, voltage sensors, current sensors, frequency sensors, and power factor sensors are selected to collect the above-mentioned various data.

[0075] S202. Preprocess the power grid operation data, equipment status data, and external environment data; where the preprocessing includes but is not limited to data cleaning, data denoising, data filtering, data spectral analysis, data wavelet transform, and data standardization.

[0076] Specifically, data cleaning, also known as data grooming, refers to a series of inspection and correction processes performed on data before data analysis and processing, aiming to improve data quality and ensure the accuracy, integrity, consistency, availability, and traceability of data.

[0077] Data denoising, usually called noise reduction or de-noising, refers to the process of reducing or eliminating noisy data in data processing and analysis. Noisy data refers to those data points that do not conform to the overall pattern of the data set and are generated due to errors or random interference. These noises may affect the results of data analysis and lead to inaccurate conclusions.

[0078] Data filtering is a signal processing technique used to remove unwanted frequency components from a signal and retain the useful signal. Common filtering methods include: low-pass filtering, high-pass filtering, band-pass filtering, band-stop filtering, etc.

[0079] Data spectral analysis is a technique for analyzing the frequency components of a signal, which involves decomposing the signal into its constituent frequency components. This analysis method is applied in many fields, including signal processing, communication, audio engineering, vibration analysis, etc.

[0080] Data wavelet transform is used to analyze the time-frequency characteristics of signals and images. It provides a time-frequency representation of the signal by decomposing the signal into waveforms (wavelets) of different scales and positions.

[0081] Data standardization refers to the process of uniformly processing data from different sources, formats, and specifications to make it comparable and operable. The purpose of data standardization is to improve indicators such as data quality, availability, and reliability, so as to better support data analysis and applications.

[0082] S203. Integrate the power grid operation data, equipment status data, and external environment data based on data fusion technology to obtain the integrated data.

[0083] Specifically, the weighted average method, Bayesian method, or fuzzy logic method can be selected to integrate the power grid operation data, equipment status data, and external environment data.

[0084] S204. Extract the features of the integrated data to obtain the power grid data features.

[0085] Specifically, the features of the power grid operation data are extracted by the principal component analysis method, or the linear discriminant analysis method, or the Fourier transform method, or the deep learning method to obtain the operation data features. The following will introduce each method in detail: The principal component analysis method is a statistical method used for dimensionality reduction and data extraction. It transforms a set of variables that may be correlated through an orthogonal transformation into a set of linearly uncorrelated variables, namely the principal components. These principal components can explain the main variability in the data, and usually only a few principal components can explain most of the data variation. In the power grid operation data, equipment status data, and external environment data, the principal component analysis method can be used to reduce the dimensionality of the data and extract the most important features.

[0086] The linear discriminant analysis method is a supervised learning dimensionality reduction technique aimed at finding the best projection direction so that the distances between data of different classes in this direction are as far as possible, while data of the same class are as close as possible. The linear discriminant analysis method finds this direction by maximizing the ratio of the between-class scatter matrix to the within-class scatter matrix. In the power grid data, the linear discriminant analysis method can be used to distinguish different power grid operation states, such as normal operation and abnormal states. The key features for distinguishing different states can be extracted through the linear discriminant analysis method.

[0087] The Fourier transform method is a mathematical method for converting a signal from the time domain to the frequency domain. It can analyze the frequency components of the signal and identify the periodic components in the signal. The voltage and current signals in the power grid operation data can be analyzed for their frequency components through the Fourier transform.

[0088] The deep learning method is a learning method based on artificial neural networks that can automatically learn complex patterns and features from a large amount of data. Deep learning models include convolutional neural networks, recurrent neural networks, long short-term memory networks, etc.

[0089] Among them, the power grid data features include but are not limited to frequency, amplitude, and energy.

[0090] S205. Compare the power grid data features with each abnormal feature in the preset abnormal feature library to determine whether a power grid fault has occurred: S2051. If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library does not exceed the preset threshold, the power grid has not failed.

[0091] For example: The power grid data characteristic is that the voltage fluctuation is within ±5%. There is a characteristic in the abnormal characteristic library that the voltage fluctuation exceeds ±10%. Through calculation, the similarity between the current power grid data characteristic and this abnormal characteristic is 50%, which is lower than the preset threshold of 60%. Therefore, the power grid has not failed.

[0092] S2052. If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library exceeds the preset threshold, the power grid has failed.

[0093] For example: The power grid data characteristics show that the voltage fluctuation suddenly increases to ±8% and the frequency deviation reaches ±0.09 Hz. The similarities with the characteristics of voltage fluctuation exceeding ±10% and frequency deviation exceeding ±0.1 Hz in the abnormal characteristic library are 80% and 90% respectively, both exceeding the preset threshold of 60%. Then it is determined that the power grid has failed.

[0094] S206. When the power grid fails, determine the fault location, fault type, and fault severity.

[0095] S2061. Determine the fault location by measuring the time difference of the traveling wave arriving at different measurement points.

[0096] For example: At both ends of the transmission line and install traveling wave sensors. When a fault occurs, the sensors record the time when the traveling wave arrives as , and the time recorded by the sensor is . If the speed of the traveling wave in the transmission line is , then the distance of the fault point from the sensor can be calculated by the following formula:

[0097] In the formula, represents the distance of the fault point from the sensor , represents the speed of the traveling wave in the transmission line, represents the time recorded by the sensor , represents the time when the traveling wave arrives recorded by the sensor .

[0098] S2062. Analyze the frequency and amplitude of the traveling wave to determine the fault type.

[0099] Among them, different types of faults will generate traveling waves with different characteristics, including different frequencies and amplitudes. For example: A short-circuit fault usually generates traveling waves with high amplitude and low frequency, while an arc fault may generate traveling waves with lower amplitude and higher frequency.

[0100] S2063. Determine the severity of the fault based on the first disturbance power peak obtained by multiplying the voltage traveling wave data and the current traveling wave data of two traveling wave measurement units on both sides of the fault location.

[0101] Among them, the traveling waves generated by the fault will affect both the voltage and the current at the same time. By analyzing the product of the voltage and current traveling wave data, the disturbance power peak can be obtained, and the magnitude of this peak can reflect the severity of the fault. For example: The voltage traveling wave data measured by the measurement units on both sides of the fault point is , and the current traveling wave data is . By calculating the product of and , the disturbance power is obtained:

[0102] In the formula, represents the disturbance power, represents the measured voltage traveling wave data, represents the measured current traveling wave data.

[0103] The first disturbance power peak represents the instantaneous power impact when the fault occurs, and the magnitude of the disturbance power peak can represent the severity of the accident.

[0104] S207. Determine the isolation point, isolation section and isolation strategy according to the fault location, fault type and fault severity.

[0105] Among them, the isolation point is determined according to the fault location, and the two nearest switches are selected as the isolation points, and these two switches are located upstream and downstream of the fault point respectively. The isolation section is the line part between the two switches, which is the area that needs to be isolated. The formulation of the isolation strategy includes closing the two switches to isolate the fault section, and at the same time considering power transfer through other lines or substations to reduce the impact of power outage.

[0106] S208. Perform isolation operations on the isolation points and isolation sections of the power grid according to the isolation strategy.

[0107] The execution of the isolation operation involves actual physical operations, including but not limited to: opening the circuit breaker, operating the disconnector and reclosing operation.

[0108] S209. Use historical data and power grid operation data to predict potential faults through a machine learning model.

[0109] Specifically, historical data (such as transformer fault records in the past 5 years) and corresponding power grid operation data (such as voltage and current) are collected; voltage fluctuation and current peak characteristics are extracted; the random forest algorithm, support vector machine or long short-term memory network is used to train the characteristics to construct a fault prediction model; the fault prediction model is used to predict new power grid operation data to obtain potential faults, so as to take measures in advance, such as increasing the monitoring frequency, preparing standby equipment or arranging maintenance work, to reduce the impact of faults.

[0110] It should be noted here that: for the detailed description of each step in this embodiment, reference can be made to other embodiments correspondingly, and details will not be repeated here.

[0111] The present invention provides a power grid fault isolation method, including: collecting power grid operation data, equipment status data and external environment data according to a preset frequency; integrating the power grid operation data, equipment status data and external environment data based on data fusion technology to obtain integrated data; extracting the characteristics of the integrated data to obtain power grid data characteristics; comparing the power grid data characteristics with each abnormal characteristic in a preset abnormal characteristic library to determine whether the power grid has a fault: if the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library does not exceed a preset threshold, the power grid has no fault; if the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library exceeds the preset threshold, the power grid has a fault; when the power grid has a fault, determining the fault location, fault type and fault severity; determining the isolation point, isolation section and isolation strategy according to the fault location, fault type and fault severity; performing isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy. Compared with the prior art, the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operations.

[0112] In addition, the embodiment of the present invention uses historical data and power grid operation data to predict potential faults through a machine learning model, realizes early warning of faults, can improve the safety and stability of the power system, and reduce the losses and impacts caused by faults.

[0113] An embodiment of the present invention provides a power grid fault isolation system, as Figure 3 shown, including: A collection module 31, configured to collect power grid operation data, equipment status data and external environment data according to a preset frequency.

[0114] An integration module 32, configured to integrate the power grid operation data, equipment status data and external environment data based on data fusion technology to obtain integrated data.

[0115] An extraction module 33, configured to extract the features of the integrated data to obtain power grid data features.

[0116] A judgment module 34, configured to compare the power grid data features with each abnormal feature in a preset abnormal feature library to judge whether a fault occurs in the power grid: If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, it means that no fault has occurred in the power grid.

[0117] If the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds a preset threshold, it means that a fault has occurred in the power grid.

[0118] A first determination module 35, configured to determine the fault location, fault type, and fault severity when a fault occurs in the power grid.

[0119] A second determination module 36, configured to determine the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity.

[0120] An execution module 37, configured to perform an isolation operation on the isolation point and isolation section of the power grid according to the isolation strategy.

[0121] It should be noted here that: for the detailed description of each component structure in this embodiment, reference can be made to other embodiments correspondingly, and details will not be elaborated here.

[0122] An embodiment of the present invention provides a power grid fault isolation system, including: a collection module for collecting power grid operation data, equipment status data, and external environment data at a preset frequency; an integration module for integrating the power grid operation data, equipment status data, and external environment data based on data fusion technology to obtain integrated data; an extraction module for extracting the features of the integrated data to obtain power grid data features; a judgment module for comparing the power grid data features with each abnormal feature in a preset abnormal feature library to judge whether the power grid has a fault: if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, the power grid has no fault; if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the power grid has a fault; a first determination module for determining the fault location, fault type, and fault severity when the power grid has a fault; a first determination module for determining the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity; an execution module for performing isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy. Compared with the prior art, the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention, and improve the safety and efficiency of operations. Compared with the prior art, the embodiment of the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention, and improve the safety and efficiency of operations.

[0123] An embodiment of the present invention provides a power grid fault isolation system, as Figure 4 shown, including: A collection module 41 for collecting power grid operation data, equipment status data, and external environment data at a preset frequency.

[0124] A preprocessing module 42 for preprocessing the power grid operation data, equipment status data, and external environment data; wherein, the preprocessing includes but is not limited to data cleaning, data denoising, data filtering, data spectrum analysis, data wavelet transform, and data standardization.

[0125] An integration module 43 for integrating the power grid operation data, equipment status data, and external environment data based on data fusion technology to obtain integrated data.

[0126] An extraction module 44 for extracting the features of the integrated data to obtain power grid data features.

[0127] A judgment module 45 for comparing the power grid data features with each abnormal feature in a preset abnormal feature library to judge whether the power grid has a fault: If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library does not exceed the preset threshold, the power grid has not failed.

[0128] If the similarity between the power grid data characteristics and a certain abnormal characteristic in the preset abnormal characteristic library exceeds the preset threshold, the power grid has failed.

[0129] The first determination module 46 is configured to determine the fault location, fault type, and fault severity when the power grid fails.

[0130] The fault location determination unit 461 determines the fault location by measuring the time difference of the traveling wave arriving at different measurement points.

[0131] The fault type determination unit 462 analyzes the frequency and amplitude of the traveling wave to determine the fault type.

[0132] The severity determination unit 463 determines the fault severity according to the first disturbance power peak obtained by multiplying the voltage traveling wave data and current traveling wave data of two traveling wave measurement units on both sides of the fault location.

[0133] The second determination module 47 is configured to determine the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity.

[0134] The execution module 48 is configured to perform isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy.

[0135] The prediction module 49, which is connected to the execution module, is configured to predict potential faults by using historical data and power grid operation data through a machine learning model.

[0136] It should be noted here that for the detailed description of the components in this embodiment, reference can be made to other embodiments correspondingly, and details are not described here again.

[0137] An embodiment of the present invention provides a power grid fault isolation system, including: a collection module for collecting power grid operation data, equipment status data, and external environment data at a preset frequency; an integration module for integrating the power grid operation data, equipment status data, and external environment data based on data fusion technology to obtain integrated data; an extraction module for extracting the features of the integrated data to obtain power grid data features; a judgment module for comparing the power grid data features with each abnormal feature in a preset abnormal feature library to judge whether the power grid has a fault: if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, the power grid has no fault; if the similarity between the power grid data features and a certain abnormal feature in the preset abnormal feature library exceeds the preset threshold, the power grid has a fault; a first determination module for determining the fault location, fault type, and fault severity when the power grid has a fault; a first determination module for determining the isolation point, isolation section, and isolation strategy according to the fault location, fault type, and fault severity; an execution module for performing isolation operations on the isolation point and isolation section of the power grid according to the isolation strategy. Compared with the prior art, the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operations. Compared with the prior art, the embodiment of the present invention can complete fault detection and isolation in a short time, reduce the impact of faults on the power grid; improve the accuracy of isolation through precise fault location technology; reduce manual intervention and improve the safety and efficiency of operations.

[0138] In addition, the embodiment of the present invention also adds a prediction module for predicting potential faults through a machine learning model using historical data and power grid operation data, realizing early warning of faults, improving the safety and stability of the power system, and reducing the losses and impacts caused by faults.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and the description of the present invention. In particular, as long as there is no structural conflict, the various technical features mentioned in each embodiment can be combined in any way. The present invention is not limited to the specific embodiments disclosed in the text, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for isolating a power grid fault, characterized in that: include: Collect grid operation data, equipment status data and external environment data at preset frequencies; Based on data fusion technology, the power grid operation data, the equipment status data and the external environment data are integrated to obtain integrated data; Extracting the characteristics of the integrated data to obtain power grid data characteristics; Compare the power grid data features with the abnormal features in the preset abnormal feature library to determine whether the power grid has a fault: If the similarity between the power grid data feature and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, then the power grid has not failed; If the similarity between the power grid data feature and a certain abnormal feature in the preset abnormal feature library exceeds a preset threshold, the power grid fails; When a fault occurs in the power grid, determining the fault location, fault type and fault severity; Determine an isolation point, an isolation section, and an isolation strategy according to the fault location, the fault type, and the fault severity; An isolation operation is performed on the isolation point and the isolation section of the power grid according to the isolation strategy.

2. The power grid fault isolation method according to claim 1, characterized in that: After collecting grid operation data, equipment status data and external environment data at a preset frequency, it also includes: The power grid operation data, the equipment status data and the external environment data are preprocessed; wherein the preprocessing includes but is not limited to data cleaning, data noise removal, data filtering, data spectrum analysis, data wavelet transform and data standardization.

3. The power grid fault isolation method according to claim 1, characterized in that: After performing isolation operations on the isolation point and the isolation section of the power grid according to the isolation strategy, the method further includes: Using historical data and the grid operation data, potential faults are predicted through machine learning models.

4. The power grid fault isolation method according to claim 1, characterized in that: The power grid operation data includes: The power grid operation data includes but is not limited to voltage signal, current signal, frequency signal and power factor.

5. The power grid fault isolation method according to claim 1, characterized in that: Extracting the characteristics of the integrated data to obtain the characteristics of the power grid data includes: The characteristics of the integrated data are extracted by principal component analysis, linear discriminant analysis, Fourier transform, or deep learning to obtain the characteristics of the power grid data.

6. The power grid fault isolation method according to claim 1, characterized in that: The grid data features include: The grid data characteristics include but are not limited to frequency, amplitude and energy.

7. The power grid fault isolation method according to claim 1, characterized in that: When a fault occurs in the power grid, determining the fault location, the fault type and the fault severity includes: Determine the fault location by measuring the time difference between the traveling wave reaching different measuring points; Analyzing the frequency and amplitude of the traveling wave to determine the fault type; The fault severity is determined according to a first disturbance power peak value obtained by multiplying voltage traveling wave data and current traveling wave data of two traveling wave measurement units on both sides of the fault location.

8. A power grid fault isolation system, characterized in that: include: A collection module is used to collect power grid operation data, equipment status data and external environment data at a preset frequency; An integration module, used to integrate the power grid operation data, the equipment status data and the external environment data based on data fusion technology to obtain integrated data; An extraction module, used to extract the features of the integrated data to obtain power grid data features; A judgment module is used to compare the power grid data features with the abnormal features in the preset abnormal feature library to determine whether the power grid has a fault: If the similarity between the power grid data feature and a certain abnormal feature in the preset abnormal feature library does not exceed a preset threshold, then the power grid has not failed; If the similarity between the power grid data feature and a certain abnormal feature in the preset abnormal feature library exceeds a preset threshold, the power grid fails; A first determination module is used to determine the fault location, fault type and fault severity when a fault occurs in the power grid; A second determination module is used to determine an isolation point, an isolation section and an isolation strategy according to the fault location, the fault type and the fault severity; An execution module is used to perform an isolation operation on the isolation point and the isolation section of the power grid according to the isolation strategy.

9. The power grid fault isolation system according to claim 8, characterized in that: Also includes: Preprocessing module; A preprocessing module is used to preprocess the power grid operation data, the equipment status data and the external environment data; wherein the preprocessing includes but is not limited to data cleaning, data noise removal, data filtering, data spectrum analysis, data wavelet transform and data standardization.

10. The power grid fault isolation system according to claim 8, characterized in that: Also includes: Prediction module; A prediction module is used to use historical data and the power grid operation data to predict potential faults through a machine learning model.

Images