Distance measuring and positioning method and system for grounding fault point of power distribution network

Abstract

The invention relates to a power distribution network ground fault point ranging and positioning method and system, and relates to the technical field of electric power. The method mainly comprises the steps of obtaining a fault point in a downstream line of a transformer substation; configuring a signal source in the transformer substation, and filtering false fault points in the fault points through reflection of the signal source to obtain real fault points; determining a target feature according to the zero-sequence current and the zero-sequence voltage of the line where the real fault point is located; inputting the target feature into a ground fault recognition model, and determining whether the real fault point is a ground fault point or not; if the real fault point is a ground fault point, determining the line type of a line where the ground fault point is located; and calculating the distance from the ground fault point to the transformer substation according to the line type.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method and system for measuring and locating a ground fault point in a distribution network. Background Art

[0002] In the context of smart distribution network construction, in order to improve power supply reliability, when a grounding fault occurs, it is necessary to intelligently determine the line where the grounding point is located and the branch location where it is located under the power supply state of the line, disconnect the branch where the grounding point is located, separate the grounding point from the distribution network, and restore the normal operation of other networks without faults to minimize the power outage area.

[0003] At present, when a single-phase grounding fault occurs in the distribution network, most of the traditional positioning methods are to use manual line inspection, and the staff will find the fault point by visual observation along the line. Usually, the line inspection distance of an outgoing line including each branch is tens of kilometers, and sometimes hundreds of kilometers. This method of locating the grounding fault point not only consumes a lot of manpower and material resources, but also takes a long time to find the grounding fault point. It is also difficult to find hidden faults such as insulator breakdown and internal faults of lightning arresters. In addition, the transportation environment of the rural distribution network is backward and the environment is poor, which prolongs the time of fault location, isolation and repair, and cannot adapt to the automation level of modern distribution networks. Summary of the invention

[0004] The present invention aims to provide a method and system for measuring and locating ground fault points in a distribution network to solve the deficiencies in the prior art. The technical problem to be solved by the present invention is achieved through the following technical solutions.

[0005] An embodiment of the present invention provides a method for measuring and locating a ground fault point in a distribution network, the method comprising:

[0006] Obtain the fault point in the downstream line of the substation;

[0007] A signal source is configured in the substation, and a pseudo fault point in the fault point is filtered out through reflection of the signal source to obtain a real fault point;

[0008] Determine the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located;

[0009] Inputting the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point;

[0010] If the real fault point is a ground fault point, determining the line type of the line where the ground fault point is located;

[0011] The distance from the ground fault point to the substation is calculated according to the line type.

[0012] In an optional embodiment, obtaining the fault point in the downstream line of the substation includes:

[0013] Obtaining transient traveling waves, voltages and currents generated by the downstream lines of the substation when a fault occurs, as well as data recorded by a fault recorder;

[0014] Determine the first fault point through the transient traveling wave; determine the second fault point through the voltage and current; determine the third fault point through the data recorded by the fault recorder;

[0015] The first fault point, the second fault point and the third fault point are determined as fault points in a downstream line.

[0016] In an optional embodiment, configuring a signal source in the substation and filtering the pseudo fault points in the fault points through reflection of the signal source to obtain the real fault point includes:

[0017] A signal source is configured in the substation so that the substation transmits a forward wave through the fault points corresponding to N positions, and generates a reflected wave after reaching the fault point, and the transmitted wave reaches the substation after passing through N positions;

[0018] If the forward wave and the reflected wave generated by the fault point are both transmitted and refracted at N positions, the fault point is determined to be a pseudo fault point.

[0019] In an optional embodiment, determining the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located includes:

[0020] Determine a current spectrum characteristic diagram and a voltage spectrum characteristic diagram corresponding to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located, respectively;

[0021] Determine a current characteristic value and a voltage characteristic value according to the current spectrum characteristic diagram and the voltage spectrum characteristic diagram respectively;

[0022] The current spectrum characteristic diagram, the voltage spectrum characteristic diagram, the current characteristic value, and the voltage characteristic value are determined as the target characteristics.

[0023] In an optional embodiment, the current characteristic value includes the amplitude, frequency and phase of the current; and the voltage characteristic value includes the amplitude, frequency and phase of the voltage.

[0024] In an optional embodiment, inputting the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point includes:

[0025] The target feature is input into a ground fault identification model, the current spectrum feature diagram and the current characteristic value are predicted by a first identification model in the ground fault identification model to obtain a first prediction value, and the voltage spectrum feature diagram and the voltage characteristic value are predicted by a second identification model in the ground fault identification model to obtain a second prediction value;

[0026] Obtaining a final prediction result according to the first prediction value and the second prediction value;

[0027] Whether the actual fault point is a grounding fault point is determined by the final prediction result.

[0028] In an optional embodiment, the training process of the ground fault identification model is:

[0029] Acquire a sample data set for training the ground fault identification model, wherein the sample data set includes sample data and corresponding sample labels;

[0030] Determine sample data characteristics according to the zero-sequence current and zero-sequence voltage in the sample data;

[0031] Inputting the sample data feature into the ground fault identification model to obtain a first prediction value and a second prediction value;

[0032] Calculate a loss value according to the first predicted value, the second predicted value and the sample label;

[0033] When the loss value is less than a preset value, the training of the ground fault identification model is completed.

[0034] In an optional embodiment, determining the line type of the line where the ground fault point is located includes:

[0035] Determine the lengths between the ground fault point and the first substation and the second substation as the first length and the second length respectively;

[0036] Calculating a discrimination coefficient by using the first length, the second length and the line mode wave velocity when a fault occurs at the ground fault point;

[0037] The line type of the line where the ground fault point is located is determined according to the discrimination coefficient.

[0038] In an optional embodiment, the calculating the distance from the ground fault point to the substation according to the line type includes:

[0039] If the line type is a main line, the distance from the ground fault point to the substation is calculated according to a first formula;

[0040] If the line type is a branch line, the distance from the ground fault point to the substation is calculated according to the second formula.

[0041] An embodiment of the present invention provides a distribution network ground fault point distance measurement and positioning system, the system comprising:

[0042] An acquisition module, used for acquiring a fault point in a downstream line of a substation;

[0043] A filtering module, configured to configure a signal source in the substation, and filter the pseudo fault points in the fault points through reflection of the signal source to obtain the real fault points;

[0044] A determination module, used to determine the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located;

[0045] The determination module is further used to input the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point;

[0046] The determination module is further configured to determine the line type of the line where the ground fault point is located if the real fault point is a ground fault point;

[0047] A calculation module is used to calculate the distance from the ground fault point to the substation according to the line type.

[0048] The embodiments of the present invention include the following advantages:

[0049] A method and system for measuring and locating a ground fault point in a distribution network provided by an embodiment of the present invention first obtains a fault point in a downstream line of a substation; then configures a signal source in the substation, and filters pseudo fault points in the fault point through reflection of the signal source to obtain a real fault point; determines a target feature according to zero-sequence current and zero-sequence voltage of the line where the real fault point is located; inputs the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point; if the real fault point is a ground fault point, determines the line type of the line where the ground fault point is located; and calculates the distance from the ground fault point to the substation according to the line type. Compared with the current method of measuring the distance and locating the grounding fault point by manual line patrol, the present application determines the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located; the target feature is input into the grounding fault identification model to determine whether the real fault point is the grounding fault point; if the real fault point is the grounding fault point, the line type of the line where the grounding fault point is located is determined; the distance from the grounding fault point to the substation is calculated according to the line type, so that the efficiency and accuracy of measuring the distance and locating the grounding fault point can be improved through the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flow chart of a method for measuring and locating a ground fault point in a distribution network provided by an embodiment of the present invention;

[0051] Figure 2 It is a schematic diagram of traveling wave propagation when a signal source is superimposed provided by an embodiment of the present invention;

[0052] Figure 3 It is a structural schematic diagram of a distribution network grounding fault point distance measurement and positioning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0054] See also Figure 1 , a method for measuring and locating a ground fault point in a distribution network provided by an embodiment of the present invention, the method specifically includes S101-S106:

[0055] S101, obtaining a fault point in a downstream line of a substation.

[0056] The substation monitors and locates the single-phase grounding fault point of the distribution network at a single end, and transmits the location result, i.e. the specific location information of the grounding fault point, to the existing dispatching automation system. Specifically, the substation is usually equipped with various monitoring equipment, such as multi-function power meters, gas sensors, SF6 concentration detectors, etc. These devices can monitor the operation status of the substation in real time. Through these monitoring data, abnormal situations can be discovered in time, so as to quickly determine the fault point in the downstream line.

[0057] In an optional embodiment provided by the application, the step of obtaining a fault point in a downstream line of the substation includes:

[0058] S1011, obtaining transient traveling waves, voltages and currents generated by the downstream lines of the substation when a fault occurs, as well as data recorded by a fault recorder.

[0059] The application of transient traveling waves in transmission line fault location is an efficient and accurate method. By analyzing the propagation characteristics of transient traveling waves, the location of the fault point can be quickly determined.

[0060] The fault recorder can record the voltage and current waveforms when a fault occurs. These data are important basis for fault analysis. By analyzing the recorded data, the changes in electrical quantities before and after the fault can be observed, thereby determining the nature and location of the fault.

[0061] S1012, determining a first fault point through the transient traveling wave; determining a second fault point through the voltage and current; and determining a third fault point through the data recorded by the fault recorder.

[0062] In this embodiment, the process of determining the first fault point by transient traveling waves is as follows: the substation is the measuring point end, and the transient traveling wave generated by the voltage mutation at the fault point will propagate to both ends of the line. Due to the mutual coupling between the three phases, Clark transformation can be used for decoupling, and the quantities of phases A, B, and C are converted into 0-mode, 1-mode, and 2-mode components. Assuming that the system is balanced and transposed, 1-mode and 2-mode are equal (called line mode components). Since the speed of zero-mode and line-mode waves is different, the time to reach the measuring point is also different. According to the following formula, the electrical distance between the fault point F and the measuring point of substation B can be solved as:

[0063] s=Δtv1v0 / <v1-v0>

[0064] Where: s is the distance from the fault point F to the measuring point of substation B via points F2 and F1; v1 is the line mode wave velocity; t1 is the time it takes for the line mode to reach the measuring point of substation B from the fault point; v0 is the zero mode wave velocity; t0 is the time it takes for the zero mode to reach the measuring point of substation B from the fault point; Δt is the time difference between the two.

[0065] In this embodiment, the impedance of the fault circuit can be calculated based on the voltage and current measured during the fault. Since the line length is proportional to the impedance, the reactance between the fault point and the measurement point can be obtained by constructing a voltage balance equation and using an analytical method to determine the location of the fault point.

[0066] Under the conditions that the system operation mode is determined and the line parameters are known, when a transmission line fails, the voltage and current at the measuring point are functions of the distance from the fault point. Therefore, this embodiment can use the voltage and current at the measuring point recorded during the fault to obtain the location of the fault point through analysis and calculation.

[0067] S1013: Determine the first fault point, the second fault point, and the third fault point as fault points in a downstream line.

[0068] It should be noted that the types of the first fault point, the second fault point and the third fault point in this embodiment include various forms, such as the fault type may be: short circuit fault, open circuit fault, poor contact fault, lightning tripping fault and external force damage fault, etc. This embodiment does not make specific limitations on this.

[0069] S102, configuring a signal source in the substation, and filtering the pseudo fault points among the fault points through reflection of the signal source to obtain the real fault point.

[0070] Specifically, the signal source is configured in the substation, and the pseudo fault point in the fault point is filtered through the reflection of the signal source to obtain the real fault point, including: configuring the signal source in the substation so that the substation sends out a forward wave through the fault points corresponding to N position points, and generates a reflected wave after reaching the fault point, and the transmitted wave reaches the substation after passing through N position points; if the forward wave and the reflected wave generated by the fault point are both transmitted and refracted at the N position points, the fault point is determined to be a pseudo fault point.

[0071] For example, Figure 2 A schematic diagram of traveling wave propagation when a signal source is superimposed is provided in this embodiment. According to the signal emitted by the signal source, the reflected wave is detected, and the pseudo fault points are eliminated in sequence: assuming that W1 is the grounding fault point, the traveling wave u0 emitted by substation B passes through points F1 and F3 to reach W1, and the reflected wave uw1 generated at point W1 passes through F3 and F1 to reach the substation B side. According to the distribution line branch topology analysis, the previous traveling wave and the reflected wave generated at point W1 will both be transmitted and refracted at points F1 and F3.

[0072] Assuming that F is the grounding fault point, the traveling wave u0 emitted by substation B passes through points F1 and F2 to reach F. The reflected wave uf generated at point F then passes through F2 and F1 to reach the substation B side. According to the distribution line branch topology analysis, the previous traveling wave and the reflected wave generated at point F will only be transmitted and refracted at point F1.

[0073] The actual detected traveling wave at the measuring point B of the substation is detected, and combined with the analysis and comparison of the line branch topology structure, the pseudo fault point is checked and F is determined to be the real grounding fault point. For further confirmation, the regular action of the active control signal source is supplemented by the radiated wave at the T1 point behind the fault point for auxiliary analysis.

[0074] S103, determining the target feature according to the zero-sequence current and zero-sequence voltage of the line where the actual fault point is located.

[0075] In an optional embodiment provided in the present application, determining the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located includes:

[0076] S1031, determining a current spectrum characteristic diagram and a voltage spectrum characteristic diagram corresponding to the zero-sequence current and the zero-sequence voltage of the line where the real fault point is located, respectively.

[0077] Specifically, this embodiment samples the zero-sequence current and zero-sequence voltage in the transmission line to obtain time domain waveform data, and then performs necessary preprocessing on the collected time domain data, such as removing noise and filtering, to improve the accuracy of subsequent analysis. Then, the fast Fourier transform (FFT) algorithm is used to convert the time domain signal into a frequency domain signal. The frequency domain signal obtained by the FFT transform usually contains amplitude and phase information in complex form, that is, the amplitude and phase of each frequency component can be calculated using the corresponding mathematical formula or software function. Finally, the amplitude of the frequency domain signal is plotted as a spectrum diagram using a drawing tool, and the spectrum diagram usually uses frequency as the horizontal axis and amplitude as the vertical axis.

[0078] Furthermore, this embodiment can obtain amplitude modulation - frequency modulation signals with center frequencies of 50Hz, 150Hz, 300Hz and 400Hz for analysis, determine the spectrum feature graph that can best express the most obvious characteristics of zero-sequence current and zero-sequence voltage when a fault occurs, and then determine the spectrum feature graph with the most obvious characteristics as the current spectrum feature graph and the voltage spectrum feature graph.

[0079] S1032: Determine a current characteristic value and a voltage characteristic value according to the current spectrum characteristic diagram and the voltage spectrum characteristic diagram, respectively.

[0080] The current characteristic values ​​include the current amplitude, frequency and phase; the voltage characteristic values ​​include the voltage amplitude, frequency and phase.

[0081] S1033: Determine the current spectrum characteristic graph, the voltage spectrum characteristic graph, the current characteristic value, and the voltage characteristic value as the target characteristics.

[0082] S104: input the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point.

[0083] In an optional embodiment provided in the present application, inputting the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point includes:

[0084] S1041, inputting the target feature into a ground fault identification model, predicting the current spectrum characteristic diagram and the current characteristic value through a first identification model in the ground fault identification model to obtain a first prediction value, and predicting the voltage spectrum characteristic diagram and the voltage characteristic value through a second identification model to obtain a second prediction value.

[0085] In this embodiment, the ground fault identification model includes a first identification model and a second identification model, the first identification model is used to predict a first prediction value based on current related data, and the second identification model is used to predict a second prediction value based on voltage related data. The first prediction value and the second prediction value are used for the probability value of the ground fault point corresponding to the fault point.

[0086] S1042: Obtain a final prediction result according to the first prediction value and the second prediction value.

[0087] Specifically, in this embodiment, the first prediction value and the second prediction value can be weighted to obtain the final prediction result; or the first prediction value and the second prediction value can be averaged to obtain the final prediction result, which is not specifically limited in this embodiment.

[0088] S1043: Determine whether the actual fault point is a grounding fault point based on the final prediction result.

[0089] Among them, the training process of the ground fault identification model is: obtaining a sample data set for training the ground fault identification model, the sample data set includes sample data and corresponding sample labels, and the sample label indicates whether the sample data belongs to a ground fault point; determining the sample data characteristics according to the zero-sequence current and zero-sequence voltage in the sample data; inputting the sample data characteristics into the ground fault identification model to obtain a first prediction value and a second prediction value; calculating a loss value according to the first prediction value, the second prediction value and the sample label; when the loss value is less than a preset value, completing the training of the ground fault identification model.

[0090] In this embodiment, the ground fault identification model selects LSTM as the time series feature classifier, and its principle is as follows:

[0091]

[0092] Among them, i t is the input gate; o t is the output gate; m t is the memory unit; f t is the forget gate; t is the output of the hidden layer, and h t Will be used as a forgetting factor to participate in the calculation of the next LSTM unit; x t is the input sequence; W is the weight vector; V is the recursive weight vector; b is the offset weight vector; c t The current input unit status.

[0093] In this embodiment, according to the different types of grounding fault points in the distribution network, the characteristics of the transition resistance of the grounding points, including tree branch grounding, cement road surface grounding, water and grass grounding, electric shock accidents, cable skin grounding and arc grounding, can be analyzed, and then the numerical range of various types of transition resistance can be determined; a composite sequence network including the grounding point transition resistance is constructed, and vector analysis and theoretical deduction are performed on the electrical related quantities to establish a grounding fault type identification model, so as to determine the specific type of the grounding fault through the grounding fault type identification model, thereby quickly maintaining the fault based on the fault type.

[0094] S105: If the real fault point is a ground fault point, determine the line type of the line where the ground fault point is located.

[0095] In an optional embodiment provided in the present application, the determining the line type of the line where the ground fault point is located includes:

[0096] S1051, determining the lengths between the ground fault point and the first substation and the second substation as a first length and a second length respectively.

[0097] Among them, the ground fault point can be represented by f, and its corresponding fault line is L1. The first length between the ground fault point and the first substation is l1, and the second length between the ground fault point and the second substation is l2; the M end is the first section of the fault line (i.e., the first substation), and the N end is the end of the fault line (i.e., the second substation); the line MN length is l MN ; A traveling wave signal measuring device is installed at both ends of M and N. The device has a real-time communication function and can obtain the voltage traveling wave signal U at the measuring point. m , U n , and upload the acquired traveling wave information.

[0098] S1052: Calculate a discrimination coefficient by using the first length, the second length, and the line mode wave velocity when a fault occurs at the ground fault point.

[0099] When a line fault occurs, the traveling wave signal measured at the M end is transformed by Karenbauer to obtain the line mode wave component x1 and the zero mode wave component x0. Since the line mode wave velocity v1 is greater than the zero mode wave velocity v0, the line mode wave generated by the fault will reach the M end first, and the zero mode wave will reach the M end later. At this time, the time difference between the two arriving at the M end is recorded as T1. According to the relationship between line length, time and wave velocity, the following formula is obtained:

[0100]

[0101] After 2-3 cycles of the fault, the fault voltage traveling wave is avoided. At the peak of the zero-sequence voltage, a small parallel resistor is added to the neutral point arc suppression coil. At this time, a traveling wave will be generated at the neutral point. Since the amplitude changes of the three-phase voltage and current are equal, the traveling wave only contains the zero-mode component x0. The traveling wave measurement device at the M end can measure the zero-mode wave signal. The time when the zero-mode wave is detected is t1.

[0102] When the zero-mode wave generated at the arc suppression coil reaches the fault point, due to the presence of the fault point, the three-phase line is asymmetrical, and the zero-mode wave will generate a line-mode wave at the fault point and propagate to both ends of the line. The M end can detect the line-mode voltage wave x generated by the reflection of the fault point. m1 , assuming that the time when the reflected line mode wave generated by the fault point reaches the M terminal is t2; the N terminal can detect the line mode voltage wave x generated by the refraction or reflection of the fault point n1 , assume that the time when the refracted line mode wave generated by the fault point reaches the N end is t3. Let T2 = t2-t1, T3 = t3-t1, and the following formula is obtained based on the relationship between line length, time and wave speed:

[0103]

[0104] When a single-phase ground fault occurs at any position on the trunk line, the sum of the distances that the line mode wave propagates from the fault point to both ends is a constant value l MN Therefore, the time consumed by the line mode wave to propagate on the line should be a constant, that is, the time it takes for the line mode wave to propagate on the line MN.

[0105] When the fault occurs on the branch, the line mode wave needs to propagate not only on the trunk line but also on the branch. The propagation time is the sum of the propagation time on the trunk line and the propagation time on the branch. Therefore, the time consumed by the line mode wave to propagate on the line is greater than the time it takes for the line mode wave to propagate when the fault occurs on the trunk line. Based on this characteristic, the fault section discrimination coefficient K1 is defined as:

[0106]

[0107] T MN It indicates the time taken for the line mode wave to propagate from the M end to the N end on the line MN;

[0108]

[0109] S1053: Determine the line type of the line where the ground fault point is located according to the discrimination coefficient.

[0110] In this embodiment, when the fault occurs on the trunk line, the fault section discrimination coefficient is equal to 1, and when the fault occurs on the branch, the fault section discrimination coefficient is greater than 1.

[0111] S106: Calculate the distance from the ground fault point to the substation according to the line type.

[0112] Specifically, calculating the distance from the ground fault point to the substation according to the line type includes: if the line type is a main line, calculating the distance from the ground fault point to the substation according to a first formula; if the line type is a branch line, calculating the distance from the ground fault point to the substation according to a second formula.

[0113] The first formula is:

[0114]

[0115] Where: T MSi Indicates that the line mode wave starts from the branch point S i The time it takes to propagate to the M end; v cable is the line mode wave velocity of the cable line; l MSi The branch point S i The distance to the M end of the line;

[0116] The second formula is:

[0117]

[0118] l fSi The fault point and branch point S i The distance between.

[0119] Furthermore, this embodiment can also provide basic data for distance measurement and location of fault points for distribution lines with many branch lines by using the law of traveling wave propagation and reflection at different impedances, wavelet analysis, and identification technology of each traveling wave head at a single-end measuring point of the line according to the structure of the distribution network. Based on the neutral point high-resistance grounding method and the neutral point arc suppression coil parallel resistance grounding method, the traveling wave generated by temporarily changing the source resistance value during the grounding process and the influence of the signal source on the traveling wave are used to study the method of pseudo-fault point identification and elimination technology, and combined with the grounding line selection technology, the purpose of fault line selection and fault section location of the entire substation 10kv level network is achieved.

[0120] This embodiment provides a method for measuring and locating a ground fault point in a distribution network. First, a fault point in a downstream line of a substation is obtained; then a signal source is configured in the substation, and the pseudo fault point in the fault point is filtered through the reflection of the signal source to obtain a real fault point; the target feature is determined according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located; the target feature is input into a ground fault identification model to determine whether the real fault point is a ground fault point; if the real fault point is a ground fault point, the line type of the line where the ground fault point is located is determined; and the distance from the ground fault point to the substation is calculated according to the line type. Compared with the current method of measuring and locating the ground fault point by manual line patrol, the present application determines the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located; the target feature is input into a ground fault identification model to determine whether the real fault point is a ground fault point; if the real fault point is a ground fault point, the line type of the line where the ground fault point is located is determined; and the distance from the ground fault point to the substation is calculated according to the line type, so that the efficiency and accuracy of measuring and locating the ground fault point can be improved through the present application.

[0121] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0122] In one embodiment, a system for measuring and locating ground fault points in a distribution network is provided. Figure 3 As shown, the functional modules of the distribution network ground fault point distance measurement and positioning system are described in detail as follows:

[0123] An acquisition module 31 is used to acquire a fault point in a downstream line of a substation;

[0124] A filtering module 32 is used to configure a signal source in the substation, and filter the pseudo fault points in the fault points to obtain the real fault points through reflection of the signal source;

[0125] A determination module 33, configured to determine a target feature according to a zero-sequence current and a zero-sequence voltage of a line where the real fault point is located;

[0126] The determination module 33 is further used to input the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point;

[0127] The determination module 33 is further configured to determine the line type of the line where the ground fault point is located if the real fault point is a ground fault point;

[0128] The calculation module 34 is used to calculate the distance from the ground fault point to the substation according to the line type.

[0129] In an optional embodiment, the acquisition module 31 is specifically configured to:

[0130] Obtaining transient traveling waves, voltages and currents generated by the downstream lines of the substation when a fault occurs, as well as data recorded by a fault recorder;

[0131] Determine the first fault point through the transient traveling wave; determine the second fault point through the voltage and current; determine the third fault point through the data recorded by the fault recorder;

[0132] The first fault point, the second fault point and the third fault point are determined as fault points in a downstream line.

[0133] In an optional embodiment, the filtering module 32 is specifically configured to:

[0134] A signal source is configured in the substation so that the substation transmits a forward wave through the fault points corresponding to N positions, and generates a reflected wave after reaching the fault point, and the transmitted wave reaches the substation after passing through N positions;

[0135] If the forward wave and the reflected wave generated by the fault point are both transmitted and refracted at N positions, the fault point is determined to be a pseudo fault point.

[0136] In an optional embodiment, the determination module 33 is specifically configured to:

[0137] Determine a current spectrum characteristic diagram and a voltage spectrum characteristic diagram corresponding to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located, respectively;

[0138] Determine a current characteristic value and a voltage characteristic value according to the current spectrum characteristic diagram and the voltage spectrum characteristic diagram respectively;

[0139] The current spectrum characteristic diagram, the voltage spectrum characteristic diagram, the current characteristic value, and the voltage characteristic value are determined as the target characteristics.

[0140] In an optional embodiment, the current characteristic value includes the amplitude, frequency and phase of the current; and the voltage characteristic value includes the amplitude, frequency and phase of the voltage.

[0141] In an optional embodiment, the determination module 33 is specifically configured to:

[0142] The target feature is input into a ground fault identification model, and the current spectrum characteristic diagram and the current characteristic value are predicted by a first identification model in the ground fault identification model to obtain a first prediction value, and the voltage spectrum characteristic diagram and the voltage characteristic value are predicted by a second identification model in the ground fault identification model to obtain a second prediction value;

[0143] Obtaining a final prediction result according to the first prediction value and the second prediction value;

[0144] Whether the actual fault point is a grounding fault point is determined by the final prediction result.

[0145] In an optional embodiment, the distribution network ground fault point distance measurement and positioning system further includes a training module 35 for training a ground fault identification model, which is specifically used for:

[0146] Acquire a sample data set for training the ground fault identification model, wherein the sample data set includes sample data and corresponding sample labels;

[0147] Determine sample data characteristics according to the zero-sequence current and zero-sequence voltage in the sample data;

[0148] Inputting the sample data feature into the ground fault identification model to obtain a first prediction value and a second prediction value;

[0149] Calculate a loss value according to the first predicted value, the second predicted value and the sample label;

[0150] When the loss value is less than a preset value, the training of the ground fault identification model is completed.

[0151] In an optional embodiment, the determining module 33 is specifically configured to:

[0152] Determine the lengths between the ground fault point and the first substation and the second substation as the first length and the second length respectively;

[0153] Calculating a discrimination coefficient by using the first length, the second length and the line mode wave velocity when a fault occurs at the ground fault point;

[0154] The line type of the line where the ground fault point is located is determined according to the discrimination coefficient.

[0155] In an optional embodiment, the calculation module 34 is specifically configured to:

[0156] If the line type is a main line, the distance from the ground fault point to the substation is calculated according to a first formula;

[0157] If the line type is a branch line, the distance from the ground fault point to the substation is calculated according to the second formula.

[0158] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0159] For the specific limitations of the ground fault point distance measurement and positioning system for the distribution network, please refer to the limitations of the ground fault point distance measurement and positioning method for the distribution network mentioned above, which will not be repeated here. Each module in the above-mentioned device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0160] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0161] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for measuring and locating a ground fault point in a distribution network, characterized in that: The method comprises: Obtain the fault point in the downstream line of the substation; A signal source is configured in the substation, and a pseudo fault point in the fault point is filtered out through reflection of the signal source to obtain a real fault point; Determine the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located; Inputting the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point; If the real fault point is a ground fault point, determining the line type of the line where the ground fault point is located; The distance from the ground fault point to the substation is calculated according to the line type.

2. The method according to claim 1, characterized in that The obtaining of the fault point in the downstream line of the substation includes: Obtaining transient traveling waves, voltages and currents generated by the downstream lines of the substation when a fault occurs, as well as data recorded by a fault recorder; Determine the first fault point through the transient traveling wave; determine the second fault point through the voltage and current; determine the third fault point through the data recorded by the fault recorder; The first fault point, the second fault point and the third fault point are determined as fault points in a downstream line.

3. The method according to claim 2, characterized in that The configuring a signal source in the substation and filtering the pseudo fault points in the fault points through reflection of the signal source to obtain the real fault points includes: A signal source is configured in the substation so that the substation transmits a forward wave through the fault points corresponding to N position points, generates a reflected wave after reaching the fault point, and the transmitted wave reaches the substation after passing through N position points; If the forward wave and the reflected wave generated by the fault point are both transmitted and refracted at N positions, the fault point is determined to be a pseudo fault point.

4. The method according to claim 2 or 3, characterized in that: The determining of the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located includes: Determine a current spectrum characteristic diagram and a voltage spectrum characteristic diagram corresponding to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located, respectively; Determine a current characteristic value and a voltage characteristic value according to the current spectrum characteristic diagram and the voltage spectrum characteristic diagram respectively; The current spectrum characteristic diagram, the voltage spectrum characteristic diagram, the current characteristic value, and the voltage characteristic value are determined as the target characteristics.

5. The method according to claim 4, characterized in that The current characteristic values ​​include the amplitude, frequency and phase of the current; the voltage characteristic values ​​include the amplitude, frequency and phase of the voltage.

6. The method according to claim 4, characterized in that The step of inputting the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point includes: The target feature is input into a ground fault identification model, and the current spectrum characteristic diagram and the current characteristic value are predicted by a first identification model in the ground fault identification model to obtain a first prediction value, and the voltage spectrum characteristic diagram and the voltage characteristic value are predicted by a second identification model in the ground fault identification model to obtain a second prediction value; Obtaining a final prediction result according to the first prediction value and the second prediction value; Whether the actual fault point is a grounding fault point is determined by the final prediction result.

7. The method according to claim 5, characterized in that The training process of the ground fault identification model is as follows: Acquire a sample data set for training the ground fault identification model, wherein the sample data set includes sample data and corresponding sample labels; Determine sample data characteristics according to the zero-sequence current and zero-sequence voltage in the sample data; Inputting the sample data feature into the ground fault identification model to obtain a first prediction value and a second prediction value; Calculate a loss value according to the first predicted value, the second predicted value and the sample label; When the loss value is less than a preset value, the training of the ground fault identification model is completed.

8. The method according to claim 1, characterized in that The determining the line type of the line where the ground fault point is located includes: Determine the lengths between the ground fault point and the first substation and the second substation as the first length and the second length respectively; Calculating a discrimination coefficient by using the first length, the second length and the line mode wave velocity when a fault occurs at the ground fault point; The line type of the line where the ground fault point is located is determined according to the discrimination coefficient.

9. The method according to claim 8, characterized in that The calculating the distance from the ground fault point to the substation according to the line type includes: If the line type is a main line, the distance from the ground fault point to the substation is calculated according to a first formula; If the line type is a branch line, the distance from the ground fault point to the substation is calculated according to the second formula.

10. A distribution network ground fault point distance measurement and positioning system, characterized in that: The system comprises: An acquisition module, used for acquiring a fault point in a downstream line of a substation; A filtering module, configured to configure a signal source in the substation, and filter the pseudo fault points in the fault points through reflection of the signal source to obtain the real fault points; A determination module, used to determine the target feature according to the zero-sequence current and zero-sequence voltage of the line where the real fault point is located; The determination module is further used to input the target feature into a ground fault identification model to determine whether the real fault point is a ground fault point; The determination module is further configured to determine the line type of the line where the ground fault point is located if the real fault point is a ground fault point; A calculation module is used to calculate the distance from the ground fault point to the substation according to the line type.

Images